Token | an |
Token ID | 281 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
yss | +0.134 |
theorem | +0.134 |
isoft | +0.131 |
�� | +0.129 |
ramid | +0.128 |
Neg logit contributions | |
>>>>>>>> | -0.159 |
Eisenhower | -0.142 |
selves | -0.138 |
Chavez | -0.138 |
agers | -0.135 |
Token | excess |
Token ID | 6992 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
>>>>>>>> | +0.360 |
Eisenhower | +0.322 |
selves | +0.307 |
Chavez | +0.306 |
agers | +0.305 |
Neg logit contributions | |
theorem | -0.379 |
yss | -0.379 |
isoft | -0.371 |
ramid | -0.363 |
�� | -0.362 |
Token | of |
Token ID | 286 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
>>>>>>>> | +1.615 |
Eisenhower | +1.428 |
Chavez | +1.381 |
selves | +1.375 |
ances | +1.367 |
Neg logit contributions | |
yss | -1.565 |
theorem | -1.550 |
isoft | -1.539 |
ramid | -1.538 |
�� | -1.530 |
Token | money |
Token ID | 1637 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
theorem | +0.343 |
yss | +0.342 |
isoft | +0.336 |
ramid | +0.331 |
�� | +0.330 |
Neg logit contributions | |
>>>>>>>> | -0.275 |
Eisenhower | -0.237 |
selves | -0.231 |
Chavez | -0.229 |
agers | -0.224 |
Token | supply |
Token ID | 5127 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
theorem | +3.409 |
yss | +3.336 |
isoft | +3.225 |
rons | +3.163 |
ramid | +3.156 |
Neg logit contributions | |
>>>>>>>> | -3.401 |
Eisenhower | -2.947 |
selves | -2.892 |
Chavez | -2.848 |
agers | -2.801 |
Token | camoufl |
Token ID | 31962 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
>>>>>>>> | +1.685 |
Eisenhower | +1.457 |
selves | +1.413 |
Chavez | +1.407 |
ances | +1.378 |
Neg logit contributions | |
yss | -2.251 |
theorem | -2.215 |
isoft | -2.215 |
�� | -2.193 |
ramid | -2.187 |
Token | ages |
Token ID | 1095 |
Feature activation | +6.70e+00 |
Pos logit contributions | |
>>>>>>>> | +4.576 |
agers | +4.269 |
ager | +3.903 |
ances | +3.775 |
ages | +3.619 |
Neg logit contributions | |
�� | -15.890 |
theorem | -15.512 |
yss | -15.426 |
isoft | -15.008 |
ramid | -14.978 |
Token | these |
Token ID | 777 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
>>>>>>>> | +4.706 |
Eisenhower | +4.250 |
Chavez | +4.091 |
agers | +4.034 |
selves | +4.034 |
Neg logit contributions | |
�� | -5.576 |
yss | -5.550 |
isoft | -5.494 |
ramid | -5.352 |
theorem | -5.302 |
Token | factors |
Token ID | 5087 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
>>>>>>>> | +1.778 |
Eisenhower | +1.562 |
selves | +1.541 |
Chavez | +1.506 |
ances | +1.504 |
Neg logit contributions | |
yss | -1.702 |
theorem | -1.680 |
isoft | -1.668 |
�� | -1.647 |
ramid | -1.629 |
Token | by |
Token ID | 416 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
theorem | +1.238 |
yss | +1.232 |
isoft | +1.197 |
ramid | +1.178 |
�� | +1.165 |
Neg logit contributions | |
>>>>>>>> | -1.231 |
Eisenhower | -1.073 |
selves | -1.058 |
Chavez | -1.037 |
agers | -1.020 |
Token | keeping |
Token ID | 5291 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
>>>>>>>> | +0.340 |
Eisenhower | +0.303 |
selves | +0.295 |
Chavez | +0.294 |
agers | +0.288 |
Neg logit contributions | |
yss | -0.301 |
theorem | -0.298 |
isoft | -0.293 |
ramid | -0.287 |
�� | -0.287 |
Token | MORE |
Token ID | 12011 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
>>>>>>>> | +1.654 |
Eisenhower | +1.409 |
Chavez | +1.359 |
ager | +1.324 |
selves | +1.323 |
Neg logit contributions | |
yss | -2.358 |
isoft | -2.338 |
ramid | -2.318 |
theorem | -2.313 |
�� | -2.285 |
Token | and |
Token ID | 290 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
theorem | +0.323 |
yss | +0.320 |
isoft | +0.311 |
ramid | +0.306 |
rons | +0.300 |
Neg logit contributions | |
>>>>>>>> | -0.312 |
Eisenhower | -0.271 |
selves | -0.265 |
Chavez | -0.262 |
agers | -0.257 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
theorem | +4.235 |
yss | +4.168 |
isoft | +4.028 |
rons | +3.957 |
ramid | +3.939 |
Neg logit contributions | |
>>>>>>>> | -2.430 |
selves | -1.962 |
Eisenhower | -1.929 |
agers | -1.874 |
א | -1.857 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
>>>>>>>> | +0.621 |
Eisenhower | +0.426 |
Chavez | +0.384 |
selves | +0.375 |
ances | +0.313 |
Neg logit contributions | |
yss | -2.967 |
theorem | -2.959 |
isoft | -2.920 |
�� | -2.910 |
ramid | -2.880 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
>>>>>>>> | +1.618 |
Eisenhower | +1.132 |
Chavez | +1.074 |
selves | +1.055 |
ances | +1.009 |
Neg logit contributions | |
isoft | -5.415 |
yss | -5.405 |
theorem | -5.389 |
�� | -5.292 |
ramid | -5.267 |
Token | Diane |
Token ID | 26542 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
>>>>>>>> | +1.763 |
Eisenhower | +1.341 |
selves | +1.128 |
Chavez | +1.119 |
ances | +1.084 |
Neg logit contributions | |
�� | -8.090 |
theorem | -7.999 |
yss | -7.897 |
isoft | -7.803 |
uilt | -7.736 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
>>>>>>>> | +0.401 |
Eisenhower | +0.329 |
Rodham | +0.001 |
Chavez | -0.352 |
Clinton | -0.562 |
Neg logit contributions | |
yss | -19.130 |
isoft | -19.063 |
theorem | -18.847 |
�� | -18.685 |
uilt | -18.569 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +7.11e+00 |
Pos logit contributions | |
>>>>>>>> | +1.770 |
Eisenhower | +1.148 |
Chavez | +0.986 |
selves | +0.981 |
Clinton | +0.889 |
Neg logit contributions | |
theorem | -9.225 |
yss | -9.107 |
isoft | -9.061 |
ramid | -8.964 |
�� | -8.939 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
>>>>>>>> | +4.333 |
Eisenhower | +3.569 |
Clinton | +3.480 |
selves | +3.436 |
agers | +3.367 |
Neg logit contributions | |
theorem | -6.878 |
�� | -6.727 |
yss | -6.688 |
isoft | -6.565 |
ramid | -6.429 |
Token | : |
Token ID | 25 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
>>>>>>>> | +2.619 |
Eisenhower | +2.227 |
selves | +2.155 |
agers | +2.142 |
Chavez | +2.140 |
Neg logit contributions | |
theorem | -3.652 |
yss | -3.567 |
�� | -3.538 |
isoft | -3.518 |
ramid | -3.500 |
Token | ' |
Token ID | 705 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
>>>>>>>> | +1.416 |
Eisenhower | +1.230 |
Chavez | +1.187 |
selves | +1.175 |
agers | +1.160 |
Neg logit contributions | |
theorem | -1.749 |
yss | -1.736 |
isoft | -1.675 |
�� | -1.670 |
ramid | -1.657 |
Token | presidential |
Token ID | 4787 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
theorem | +0.426 |
yss | +0.424 |
isoft | +0.414 |
ramid | +0.408 |
�� | +0.405 |
Neg logit contributions | |
>>>>>>>> | -0.238 |
Eisenhower | -0.196 |
selves | -0.190 |
Chavez | -0.187 |
agers | -0.181 |
Token | nominee |
Token ID | 10429 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
>>>>>>>> | +1.737 |
Eisenhower | +1.473 |
Chavez | +1.411 |
selves | +1.393 |
agers | +1.371 |
Neg logit contributions | |
yss | -2.981 |
theorem | -2.951 |
isoft | -2.899 |
�� | -2.893 |
ramid | -2.881 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +6.52e+00 |
Pos logit contributions | |
>>>>>>>> | +2.159 |
Eisenhower | +1.655 |
Chavez | +1.513 |
ances | +1.405 |
selves | +1.372 |
Neg logit contributions | |
yss | -6.536 |
isoft | -6.471 |
theorem | -6.464 |
�� | -6.456 |
ramid | -6.410 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
>>>>>>>> | +1.395 |
Eisenhower | +0.881 |
Chavez | +0.779 |
Clinton | +0.668 |
selves | +0.657 |
Neg logit contributions | |
�� | -8.802 |
yss | -8.756 |
isoft | -8.653 |
theorem | -8.636 |
ramid | -8.564 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
>>>>>>>> | +4.701 |
Eisenhower | +4.075 |
Chavez | +4.001 |
selves | +3.810 |
ances | +3.787 |
Neg logit contributions | |
isoft | -5.992 |
�� | -5.950 |
theorem | -5.881 |
yss | -5.843 |
ramid | -5.792 |
Token | Diane |
Token ID | 26542 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
>>>>>>>> | +1.675 |
Eisenhower | +1.239 |
selves | +1.097 |
ances | +1.045 |
Chavez | +0.967 |
Neg logit contributions | |
�� | -7.197 |
theorem | -7.154 |
yss | -7.054 |
isoft | -6.997 |
uilt | -6.874 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +7.55e+00 |
Pos logit contributions | |
>>>>>>>> | +0.393 |
Eisenhower | +0.271 |
Rodham | +0.002 |
Chavez | -0.452 |
Rockefeller | -0.630 |
Neg logit contributions | |
yss | -18.846 |
isoft | -18.779 |
theorem | -18.581 |
�� | -18.367 |
uilt | -18.239 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +6.48e+00 |
Pos logit contributions | |
>>>>>>>> | +1.905 |
Eisenhower | +1.166 |
Chavez | +1.048 |
selves | +1.012 |
Clinton | +0.942 |
Neg logit contributions | |
theorem | -9.949 |
yss | -9.841 |
isoft | -9.784 |
�� | -9.684 |
ramid | -9.674 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
>>>>>>>> | +4.265 |
Eisenhower | +3.548 |
selves | +3.452 |
Clinton | +3.401 |
agers | +3.334 |
Neg logit contributions | |
theorem | -6.000 |
yss | -5.842 |
�� | -5.839 |
isoft | -5.725 |
ramid | -5.606 |
Token | : |
Token ID | 25 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
>>>>>>>> | +2.733 |
Eisenhower | +2.312 |
Chavez | +2.234 |
selves | +2.230 |
agers | +2.227 |
Neg logit contributions | |
theorem | -3.817 |
yss | -3.720 |
�� | -3.712 |
isoft | -3.688 |
ramid | -3.645 |
Token | ' |
Token ID | 705 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
>>>>>>>> | +0.982 |
Eisenhower | +0.849 |
Chavez | +0.819 |
selves | +0.819 |
agers | +0.805 |
Neg logit contributions | |
theorem | -1.172 |
yss | -1.162 |
isoft | -1.124 |
�� | -1.113 |
ramid | -1.109 |
Token | ites |
Token ID | 2737 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
>>>>>>>> | +0.382 |
Eisenhower | +0.328 |
selves | +0.316 |
Chavez | +0.316 |
agers | +0.311 |
Neg logit contributions | |
yss | -0.506 |
theorem | -0.505 |
isoft | -0.494 |
�� | -0.489 |
ramid | -0.487 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
>>>>>>>> | +0.474 |
Eisenhower | +0.407 |
selves | +0.401 |
Chavez | +0.394 |
agers | +0.386 |
Neg logit contributions | |
yss | -0.534 |
theorem | -0.530 |
isoft | -0.516 |
�� | -0.513 |
ramid | -0.511 |
Token |
|
Token ID | 198 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
theorem | +1.158 |
yss | +1.150 |
isoft | +1.116 |
ramid | +1.100 |
�� | +1.088 |
Neg logit contributions | |
>>>>>>>> | -0.991 |
Eisenhower | -0.856 |
selves | -0.834 |
Chavez | -0.826 |
agers | -0.801 |
Token |
|
Token ID | 198 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
theorem | +1.958 |
yss | +1.931 |
isoft | +1.873 |
ramid | +1.849 |
rons | +1.836 |
Neg logit contributions | |
>>>>>>>> | -1.688 |
Eisenhower | -1.447 |
selves | -1.420 |
Chavez | -1.404 |
agers | -1.387 |
Token | Israel |
Token ID | 14040 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
theorem | +2.233 |
yss | +2.214 |
isoft | +2.149 |
ramid | +2.107 |
rons | +2.082 |
Neg logit contributions | |
>>>>>>>> | -2.084 |
Eisenhower | -1.808 |
selves | -1.773 |
Chavez | -1.751 |
agers | -1.717 |
Token | se |
Token ID | 384 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
>>>>>>>> | +0.114 |
Eisenhower | +0.098 |
selves | +0.096 |
Chavez | +0.095 |
agers | +0.092 |
Neg logit contributions | |
theorem | -0.140 |
yss | -0.139 |
isoft | -0.134 |
ramid | -0.133 |
�� | -0.132 |
Token | izes |
Token ID | 4340 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
>>>>>>>> | +6.527 |
ances | +5.597 |
Chavez | +5.185 |
selves | +5.144 |
ager | +5.113 |
Neg logit contributions | |
�� | -12.424 |
theorem | -12.102 |
ramid | -12.087 |
isoft | -11.725 |
yss | -11.443 |
Token | every |
Token ID | 790 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
>>>>>>>> | +1.540 |
Eisenhower | +1.345 |
selves | +1.303 |
Chavez | +1.299 |
agers | +1.272 |
Neg logit contributions | |
theorem | -1.685 |
yss | -1.677 |
isoft | -1.654 |
ramid | -1.629 |
�� | -1.618 |
Token | opportunity |
Token ID | 3663 |
Feature activation | -8.42e-02 |
Pos logit contributions | |
theorem | +2.455 |
yss | +2.431 |
isoft | +2.357 |
ramid | +2.313 |
rons | +2.282 |
Neg logit contributions | |
>>>>>>>> | -2.446 |
Eisenhower | -2.125 |
selves | -2.085 |
Chavez | -2.057 |
agers | -2.022 |
Token | to |
Token ID | 284 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
yss | +0.063 |
theorem | +0.063 |
isoft | +0.061 |
ramid | +0.059 |
�� | +0.059 |
Neg logit contributions | |
>>>>>>>> | -0.070 |
Eisenhower | -0.062 |
selves | -0.060 |
Chavez | -0.060 |
ances | -0.058 |
Token | reiterate |
Token ID | 49852 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
>>>>>>>> | +0.443 |
Eisenhower | +0.391 |
selves | +0.382 |
Chavez | +0.380 |
agers | +0.369 |
Neg logit contributions | |
yss | -0.456 |
theorem | -0.453 |
isoft | -0.439 |
�� | -0.437 |
ramid | -0.429 |
Token | MORE |
Token ID | 12011 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
>>>>>>>> | +0.576 |
selves | +0.478 |
Eisenhower | +0.463 |
ances | +0.461 |
agers | +0.455 |
Neg logit contributions | |
theorem | -0.831 |
yss | -0.826 |
isoft | -0.811 |
rons | -0.794 |
ramid | -0.787 |
Token | and |
Token ID | 290 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
theorem | +0.051 |
yss | +0.050 |
isoft | +0.049 |
ramid | +0.048 |
rons | +0.047 |
Neg logit contributions | |
>>>>>>>> | -0.044 |
Eisenhower | -0.038 |
selves | -0.037 |
Chavez | -0.036 |
agers | -0.035 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
theorem | +3.845 |
yss | +3.801 |
isoft | +3.675 |
rons | +3.588 |
ramid | +3.585 |
Neg logit contributions | |
>>>>>>>> | -3.350 |
Eisenhower | -2.815 |
selves | -2.809 |
agers | -2.716 |
Chavez | -2.691 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
>>>>>>>> | +0.497 |
Eisenhower | +0.351 |
selves | +0.334 |
Chavez | +0.324 |
ances | +0.292 |
Neg logit contributions | |
theorem | -1.878 |
yss | -1.872 |
isoft | -1.838 |
ramid | -1.816 |
�� | -1.804 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
>>>>>>>> | +1.457 |
selves | +1.043 |
Eisenhower | +1.032 |
Chavez | +0.988 |
ances | +0.955 |
Neg logit contributions | |
theorem | -4.281 |
yss | -4.266 |
isoft | -4.233 |
ramid | -4.125 |
�� | -4.122 |
Token | Diane |
Token ID | 26542 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
>>>>>>>> | +1.512 |
Eisenhower | +1.147 |
selves | +0.987 |
Chavez | +0.950 |
ances | +0.945 |
Neg logit contributions | |
�� | -6.738 |
theorem | -6.710 |
yss | -6.626 |
isoft | -6.602 |
uilt | -6.463 |
Token | Rodham |
Token ID | 41848 |
Feature activation | +6.96e+00 |
Pos logit contributions | |
>>>>>>>> | +0.559 |
Eisenhower | +0.391 |
Rodham | +0.001 |
Chavez | -0.289 |
Clinton | -0.521 |
Neg logit contributions | |
yss | -18.765 |
isoft | -18.706 |
theorem | -18.498 |
�� | -18.237 |
uilt | -18.200 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
>>>>>>>> | +1.806 |
Eisenhower | +1.176 |
Chavez | +1.020 |
selves | +1.014 |
Clinton | +0.897 |
Neg logit contributions | |
theorem | -9.145 |
yss | -9.052 |
isoft | -8.985 |
ramid | -8.887 |
�� | -8.855 |
Token | Sanders |
Token ID | 26747 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
>>>>>>>> | +3.820 |
Eisenhower | +3.141 |
Clinton | +3.017 |
selves | +3.005 |
agers | +2.928 |
Neg logit contributions | |
theorem | -6.225 |
yss | -6.064 |
�� | -6.055 |
isoft | -5.953 |
ramid | -5.820 |
Token | : |
Token ID | 25 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
>>>>>>>> | +2.396 |
Eisenhower | +2.022 |
selves | +1.961 |
Chavez | +1.942 |
agers | +1.936 |
Neg logit contributions | |
theorem | -3.490 |
yss | -3.404 |
�� | -3.380 |
isoft | -3.367 |
ramid | -3.335 |
Token | ' |
Token ID | 705 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
>>>>>>>> | +1.206 |
Eisenhower | +1.049 |
Chavez | +1.014 |
selves | +1.000 |
agers | +0.988 |
Neg logit contributions | |
theorem | -1.495 |
yss | -1.485 |
�� | -1.428 |
isoft | -1.428 |
ramid | -1.415 |
Token | up |
Token ID | 510 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
>>>>>>>> | +2.698 |
Eisenhower | +2.341 |
selves | +2.319 |
Chavez | +2.249 |
agers | +2.214 |
Neg logit contributions | |
theorem | -2.930 |
yss | -2.890 |
isoft | -2.840 |
�� | -2.810 |
ramid | -2.786 |
Token | and |
Token ID | 290 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
>>>>>>>> | +1.367 |
Eisenhower | +1.196 |
Chavez | +1.158 |
selves | +1.157 |
ances | +1.132 |
Neg logit contributions | |
theorem | -1.483 |
yss | -1.455 |
isoft | -1.432 |
�� | -1.403 |
ramid | -1.401 |
Token | down |
Token ID | 866 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
>>>>>>>> | +0.789 |
Eisenhower | +0.683 |
selves | +0.663 |
Chavez | +0.661 |
agers | +0.637 |
Neg logit contributions | |
theorem | -0.966 |
yss | -0.955 |
isoft | -0.938 |
ramid | -0.924 |
�� | -0.924 |
Token | the |
Token ID | 262 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
theorem | +1.485 |
yss | +1.471 |
isoft | +1.428 |
ramid | +1.402 |
rons | +1.384 |
Neg logit contributions | |
>>>>>>>> | -1.375 |
Eisenhower | -1.188 |
selves | -1.165 |
Chavez | -1.149 |
agers | -1.128 |
Token | eastern |
Token ID | 10183 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
>>>>>>>> | +1.410 |
Eisenhower | +1.213 |
Chavez | +1.163 |
selves | +1.149 |
agers | +1.117 |
Neg logit contributions | |
theorem | -1.833 |
yss | -1.829 |
isoft | -1.790 |
�� | -1.753 |
ramid | -1.753 |
Token | se |
Token ID | 384 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
>>>>>>>> | +0.225 |
Eisenhower | +0.196 |
selves | +0.191 |
Chavez | +0.189 |
agers | +0.185 |
Neg logit contributions | |
theorem | -0.232 |
yss | -0.231 |
isoft | -0.225 |
ramid | -0.220 |
�� | -0.218 |
Token | ab |
Token ID | 397 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
>>>>>>>> | +4.017 |
ager | +2.876 |
ances | +2.671 |
agers | +2.561 |
vice | +2.548 |
Neg logit contributions | |
�� | -15.298 |
theorem | -14.760 |
ramid | -14.629 |
isoft | -14.612 |
yss | -14.560 |
Token | oard |
Token ID | 11953 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
>>>>>>>> | +3.574 |
Eisenhower | +3.145 |
ager | +3.091 |
agers | +3.038 |
selves | +3.025 |
Neg logit contributions | |
yss | -3.163 |
theorem | -3.147 |
�� | -3.082 |
ramid | -2.985 |
isoft | -2.919 |
Token | . |
Token ID | 13 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
theorem | +1.959 |
yss | +1.940 |
isoft | +1.882 |
ramid | +1.849 |
rons | +1.825 |
Neg logit contributions | |
>>>>>>>> | -1.839 |
Eisenhower | -1.591 |
selves | -1.559 |
Chavez | -1.538 |
agers | -1.511 |
Token | They |
Token ID | 1119 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
>>>>>>>> | +2.505 |
Eisenhower | +2.119 |
selves | +2.084 |
Chavez | +2.029 |
א | +1.947 |
Neg logit contributions | |
theorem | -3.476 |
yss | -3.424 |
isoft | -3.367 |
ramid | -3.343 |
�� | -3.320 |
Token | now |
Token ID | 783 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
>>>>>>>> | +0.647 |
Eisenhower | +0.546 |
selves | +0.542 |
Chavez | +0.528 |
agers | +0.519 |
Neg logit contributions | |
theorem | -0.802 |
yss | -0.793 |
isoft | -0.768 |
�� | -0.766 |
ramid | -0.756 |
Token | doubt |
Token ID | 4719 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
yss | +0.835 |
theorem | +0.824 |
isoft | +0.809 |
ramid | +0.798 |
�� | +0.789 |
Neg logit contributions | |
>>>>>>>> | -0.853 |
Eisenhower | -0.748 |
selves | -0.726 |
Chavez | -0.722 |
ances | -0.706 |
Token | about |
Token ID | 546 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
theorem | +2.117 |
yss | +2.107 |
isoft | +2.046 |
ramid | +2.023 |
�� | +1.997 |
Neg logit contributions | |
>>>>>>>> | -2.060 |
Eisenhower | -1.797 |
selves | -1.758 |
Chavez | -1.738 |
agers | -1.707 |
Token | a |
Token ID | 257 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
theorem | +2.511 |
yss | +2.459 |
isoft | +2.393 |
ramid | +2.334 |
rons | +2.319 |
Neg logit contributions | |
>>>>>>>> | -2.324 |
Eisenhower | -1.990 |
selves | -1.967 |
Chavez | -1.923 |
agers | -1.893 |
Token | World |
Token ID | 2159 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
theorem | +2.011 |
yss | +1.984 |
isoft | +1.926 |
ramid | +1.891 |
rons | +1.867 |
Neg logit contributions | |
>>>>>>>> | -1.853 |
Eisenhower | -1.599 |
selves | -1.569 |
Chavez | -1.545 |
agers | -1.519 |
Token | Cup |
Token ID | 5454 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
theorem | +2.108 |
yss | +2.098 |
isoft | +2.041 |
ramid | +2.005 |
rons | +1.981 |
Neg logit contributions | |
>>>>>>>> | -1.765 |
Eisenhower | -1.514 |
selves | -1.473 |
Chavez | -1.461 |
agers | -1.436 |
Token | semi |
Token ID | 10663 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
>>>>>>>> | +2.761 |
Eisenhower | +2.407 |
Chavez | +2.327 |
selves | +2.295 |
agers | +2.267 |
Neg logit contributions | |
yss | -3.134 |
theorem | -3.032 |
�� | -3.025 |
isoft | -2.999 |
ramid | -2.974 |
Token | - |
Token ID | 12 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
>>>>>>>> | +6.307 |
Chavez | +5.178 |
selves | +5.154 |
ager | +5.146 |
clusive | +5.134 |
Neg logit contributions | |
yss | -11.975 |
�� | -11.625 |
theorem | -11.616 |
rons | -11.561 |
isoft | -11.388 |
Token | final |
Token ID | 20311 |
Feature activation | +6.46e+00 |
Pos logit contributions | |
>>>>>>>> | +3.783 |
selves | +3.269 |
Eisenhower | +3.268 |
agers | +3.234 |
ances | +3.199 |
Neg logit contributions | |
yss | -4.025 |
theorem | -4.024 |
�� | -3.873 |
ramid | -3.796 |
isoft | -3.783 |
Token | between |
Token ID | 1022 |
Feature activation | +6.18e+00 |
Pos logit contributions | |
>>>>>>>> | +4.647 |
Eisenhower | +3.950 |
Chavez | +3.847 |
ances | +3.798 |
selves | +3.798 |
Neg logit contributions | |
yss | -5.365 |
�� | -5.154 |
ramid | -5.130 |
theorem | -5.053 |
isoft | -5.016 |
Token | two |
Token ID | 734 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
>>>>>>>> | +3.953 |
Eisenhower | +3.457 |
Chavez | +3.360 |
selves | +3.208 |
agers | +3.197 |
Neg logit contributions | |
yss | -5.700 |
ramid | -5.502 |
isoft | -5.485 |
theorem | -5.476 |
�� | -5.448 |
Token | such |
Token ID | 884 |
Feature activation | +7.88e+00 |
Pos logit contributions | |
>>>>>>>> | +1.979 |
Eisenhower | +1.724 |
selves | +1.667 |
Chavez | +1.659 |
agers | +1.616 |
Neg logit contributions | |
yss | -2.562 |
theorem | -2.509 |
isoft | -2.479 |
ramid | -2.467 |
�� | -2.450 |
Token | last |
Token ID | 938 |
Feature activation | -7.57e+00 |
Pos logit contributions | |
yss | +0.008 |
theorem | +0.008 |
isoft | +0.008 |
ramid | +0.008 |
�� | +0.008 |
Neg logit contributions | |
>>>>>>>> | -0.008 |
Eisenhower | -0.007 |
Chavez | -0.007 |
selves | -0.007 |
agers | -0.007 |
Token | year |
Token ID | 614 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
theorem | +4.677 |
yss | +4.476 |
isoft | +4.325 |
rons | +4.203 |
ramid | +4.180 |
Neg logit contributions | |
>>>>>>>> | -7.184 |
selves | -6.311 |
Eisenhower | -6.264 |
agers | -6.092 |
Chavez | -6.072 |
Token | , |
Token ID | 11 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
theorem | +1.748 |
yss | +1.730 |
isoft | +1.680 |
ramid | +1.649 |
rons | +1.633 |
Neg logit contributions | |
>>>>>>>> | -1.539 |
Eisenhower | -1.321 |
selves | -1.298 |
Chavez | -1.274 |
agers | -1.255 |
Token | its |
Token ID | 663 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
theorem | +0.036 |
yss | +0.036 |
isoft | +0.035 |
ramid | +0.034 |
�� | +0.034 |
Neg logit contributions | |
>>>>>>>> | -0.032 |
Eisenhower | -0.028 |
Chavez | -0.027 |
selves | -0.027 |
agers | -0.026 |
Token | website |
Token ID | 3052 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
>>>>>>>> | +2.294 |
Eisenhower | +2.023 |
Chavez | +1.973 |
selves | +1.964 |
agers | +1.924 |
Neg logit contributions | |
yss | -2.467 |
theorem | -2.450 |
�� | -2.402 |
isoft | -2.388 |
ramid | -2.368 |
Token | disp |
Token ID | 4596 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
theorem | +0.031 |
yss | +0.031 |
isoft | +0.030 |
�� | +0.030 |
ramid | +0.030 |
Neg logit contributions | |
>>>>>>>> | -0.030 |
Eisenhower | -0.026 |
Chavez | -0.026 |
selves | -0.025 |
ances | -0.025 |
Token | ensed |
Token ID | 15385 |
Feature activation | +7.92e+00 |
Pos logit contributions | |
>>>>>>>> | +5.113 |
ances | +4.947 |
agers | +4.444 |
arer | +4.444 |
outs | +4.430 |
Neg logit contributions | |
theorem | -12.969 |
�� | -12.963 |
yss | -12.352 |
ramid | -12.129 |
isoft | -11.854 |
Token | with |
Token ID | 351 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
>>>>>>>> | +5.188 |
Eisenhower | +4.600 |
Chavez | +4.443 |
ances | +4.324 |
selves | +4.279 |
Neg logit contributions | |
isoft | -6.828 |
yss | -6.820 |
theorem | -6.798 |
ramid | -6.757 |
�� | -6.538 |
Token | nudity |
Token ID | 42156 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
>>>>>>>> | +0.953 |
Eisenhower | +0.845 |
Chavez | +0.819 |
selves | +0.806 |
ances | +0.786 |
Neg logit contributions | |
yss | -1.069 |
theorem | -1.064 |
isoft | -1.042 |
�� | -1.015 |
ramid | -1.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
yss | +0.261 |
theorem | +0.260 |
isoft | +0.253 |
ramid | +0.249 |
�� | +0.247 |
Neg logit contributions | |
>>>>>>>> | -0.241 |
Eisenhower | -0.209 |
Chavez | -0.203 |
selves | -0.201 |
ances | -0.199 |
Token | As |
Token ID | 1081 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
>>>>>>>> | +1.281 |
Eisenhower | +1.101 |
Chavez | +1.071 |
selves | +1.065 |
ances | +1.014 |
Neg logit contributions | |
theorem | -1.708 |
yss | -1.690 |
isoft | -1.627 |
ramid | -1.611 |
�� | -1.599 |
Token | Marvel |
Token ID | 9923 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
>>>>>>>> | +1.087 |
Eisenhower | +0.947 |
Chavez | +0.920 |
selves | +0.917 |
ances | +0.887 |
Neg logit contributions | |
theorem | -1.182 |
yss | -1.176 |
isoft | -1.140 |
ramid | -1.129 |
�� | -1.126 |
Token | Studios |
Token ID | 13799 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
theorem | +2.788 |
yss | +2.763 |
isoft | +2.682 |
ramid | +2.633 |
rons | +2.600 |
Neg logit contributions | |
>>>>>>>> | -2.555 |
Eisenhower | -2.205 |
selves | -2.161 |
Chavez | -2.131 |
agers | -2.092 |
Token | as |
Token ID | 355 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
theorem | +0.386 |
yss | +0.383 |
isoft | +0.370 |
ramid | +0.366 |
�� | +0.366 |
Neg logit contributions | |
>>>>>>>> | -0.354 |
Eisenhower | -0.305 |
selves | -0.299 |
Chavez | -0.296 |
agers | -0.290 |
Token | sometimes |
Token ID | 3360 |
Feature activation | +6.94e+00 |
Pos logit contributions | |
>>>>>>>> | +3.472 |
Eisenhower | +2.973 |
Chavez | +2.897 |
selves | +2.875 |
ances | +2.857 |
Neg logit contributions | |
theorem | -4.136 |
yss | -4.097 |
�� | -4.053 |
ramid | -4.025 |
isoft | -3.982 |
Token | things |
Token ID | 1243 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
>>>>>>>> | +4.879 |
Eisenhower | +4.143 |
Chavez | +4.095 |
ances | +3.987 |
agers | +3.911 |
Neg logit contributions | |
�� | -5.965 |
yss | -5.819 |
theorem | -5.767 |
ramid | -5.703 |
isoft | -5.685 |
Token | se |
Token ID | 384 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
>>>>>>>> | +1.923 |
Eisenhower | +1.645 |
Chavez | +1.589 |
selves | +1.576 |
ances | +1.547 |
Neg logit contributions | |
yss | -2.592 |
theorem | -2.571 |
�� | -2.506 |
isoft | -2.506 |
ramid | -2.480 |
Token | ep |
Token ID | 538 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
>>>>>>>> | +7.146 |
ances | +5.804 |
ager | +5.802 |
Chavez | +5.674 |
clusive | +5.621 |
Neg logit contributions | |
theorem | -11.334 |
�� | -11.326 |
ramid | -11.232 |
yss | -11.052 |
isoft | -11.021 |
Token | out |
Token ID | 503 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
>>>>>>>> | +0.141 |
Eisenhower | +0.121 |
selves | +0.120 |
Chavez | +0.117 |
agers | +0.115 |
Neg logit contributions | |
theorem | -0.180 |
yss | -0.178 |
isoft | -0.173 |
�� | -0.170 |
ramid | -0.170 |
Token | into |
Token ID | 656 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
theorem | +0.187 |
yss | +0.185 |
isoft | +0.180 |
ramid | +0.178 |
�� | +0.178 |
Neg logit contributions | |
>>>>>>>> | -0.175 |
Eisenhower | -0.151 |
selves | -0.149 |
Chavez | -0.147 |
ances | -0.144 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
>>>>>>>> | +1.928 |
Eisenhower | +1.683 |
Chavez | +1.639 |
selves | +1.625 |
agers | +1.593 |
Neg logit contributions | |
theorem | -2.180 |
yss | -2.178 |
�� | -2.114 |
ramid | -2.103 |
isoft | -2.082 |
Token | world |
Token ID | 995 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
>>>>>>>> | +1.191 |
Eisenhower | +1.049 |
Chavez | +1.014 |
selves | +1.007 |
agers | +0.983 |
Neg logit contributions | |
theorem | -1.301 |
yss | -1.296 |
isoft | -1.251 |
ramid | -1.250 |
�� | -1.236 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
>>>>>>>> | +2.288 |
Eisenhower | +2.014 |
Chavez | +1.956 |
agers | +1.911 |
selves | +1.906 |
Neg logit contributions | |
theorem | -2.667 |
yss | -2.614 |
isoft | -2.568 |
�� | -2.534 |
ramid | -2.522 |
Token | A |
Token ID | 317 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
>>>>>>>> | +0.926 |
Eisenhower | +0.790 |
Chavez | +0.764 |
selves | +0.763 |
agers | +0.733 |
Neg logit contributions | |
theorem | -1.177 |
yss | -1.166 |
isoft | -1.133 |
ramid | -1.115 |
�� | -1.100 |
Token | decade |
Token ID | 5707 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
theorem | +1.449 |
yss | +1.441 |
isoft | +1.402 |
ramid | +1.373 |
�� | +1.358 |
Neg logit contributions | |
>>>>>>>> | -1.302 |
Eisenhower | -1.115 |
selves | -1.094 |
Chavez | -1.083 |
agers | -1.059 |
Token | ago |
Token ID | 2084 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
theorem | +0.665 |
yss | +0.660 |
isoft | +0.632 |
ramid | +0.622 |
�� | +0.611 |
Neg logit contributions | |
>>>>>>>> | -1.015 |
Eisenhower | -0.904 |
selves | -0.889 |
Chavez | -0.881 |
agers | -0.868 |
Token | when |
Token ID | 618 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
theorem | +1.868 |
yss | +1.852 |
isoft | +1.794 |
ramid | +1.761 |
rons | +1.752 |
Neg logit contributions | |
>>>>>>>> | -1.709 |
Eisenhower | -1.476 |
selves | -1.453 |
Chavez | -1.425 |
agers | -1.403 |
Token | se |
Token ID | 384 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
>>>>>>>> | +0.248 |
Eisenhower | +0.214 |
Chavez | +0.206 |
selves | +0.205 |
agers | +0.201 |
Neg logit contributions | |
theorem | -0.270 |
yss | -0.268 |
isoft | -0.261 |
ramid | -0.257 |
�� | -0.252 |
Token | ared |
Token ID | 1144 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
>>>>>>>> | +8.350 |
ances | +7.341 |
ager | +7.169 |
agers | +7.090 |
Eisenhower | +6.989 |
Neg logit contributions | |
theorem | -9.742 |
�� | -9.562 |
ramid | -9.367 |
yss | -9.313 |
isoft | -9.215 |
Token | a |
Token ID | 257 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
>>>>>>>> | +2.936 |
Eisenhower | +2.554 |
Chavez | +2.500 |
selves | +2.454 |
agers | +2.411 |
Neg logit contributions | |
yss | -3.000 |
theorem | -2.987 |
isoft | -2.948 |
�� | -2.875 |
ramid | -2.858 |
Token | hi |
Token ID | 5303 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
>>>>>>>> | +0.715 |
Eisenhower | +0.611 |
Chavez | +0.599 |
selves | +0.598 |
agers | +0.581 |
Neg logit contributions | |
theorem | -0.748 |
yss | -0.741 |
isoft | -0.724 |
�� | -0.700 |
rons | -0.698 |
Token | was |
Token ID | 373 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
>>>>>>>> | +2.419 |
Eisenhower | +2.029 |
selves | +1.996 |
Chavez | +1.974 |
agers | +1.972 |
Neg logit contributions | |
theorem | -2.695 |
yss | -2.677 |
�� | -2.582 |
isoft | -2.573 |
ramid | -2.555 |
Token | a |
Token ID | 257 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
theorem | +0.466 |
yss | +0.465 |
isoft | +0.448 |
ramid | +0.442 |
�� | +0.439 |
Neg logit contributions | |
>>>>>>>> | -0.422 |
Eisenhower | -0.368 |
selves | -0.357 |
Chavez | -0.357 |
agers | -0.346 |
Token | ant |
Token ID | 415 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
>>>>>>>> | +1.578 |
Eisenhower | +1.357 |
Chavez | +1.303 |
ager | +1.292 |
agers | +1.289 |
Neg logit contributions | |
theorem | -2.514 |
yss | -2.493 |
isoft | -2.423 |
ramid | -2.404 |
�� | -2.397 |
Token |
|
Token ID | 198 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
>>>>>>>> | +0.826 |
Eisenhower | +0.706 |
selves | +0.692 |
Chavez | +0.681 |
agers | +0.669 |
Neg logit contributions | |
theorem | -0.984 |
yss | -0.976 |
isoft | -0.948 |
ramid | -0.931 |
rons | -0.921 |
Token |
|
Token ID | 198 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
>>>>>>>> | +1.374 |
Eisenhower | +1.164 |
selves | +1.133 |
Chavez | +1.108 |
ances | +1.082 |
Neg logit contributions | |
theorem | -1.993 |
yss | -1.991 |
isoft | -1.938 |
�� | -1.930 |
ramid | -1.899 |
Token | - |
Token ID | 12 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
>>>>>>>> | +1.535 |
Eisenhower | +1.301 |
selves | +1.268 |
Chavez | +1.249 |
agers | +1.226 |
Neg logit contributions | |
theorem | -1.937 |
yss | -1.923 |
isoft | -1.865 |
ramid | -1.835 |
�� | -1.821 |
Token | Cond |
Token ID | 9724 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
theorem | +0.802 |
yss | +0.794 |
isoft | +0.771 |
ramid | +0.759 |
�� | +0.748 |
Neg logit contributions | |
>>>>>>>> | -0.710 |
Eisenhower | -0.612 |
selves | -0.600 |
Chavez | -0.591 |
agers | -0.579 |
Token | esc |
Token ID | 3798 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
>>>>>>>> | +3.821 |
Eisenhower | +3.303 |
ances | +3.210 |
ager | +3.195 |
clusive | +3.191 |
Neg logit contributions | |
theorem | -4.172 |
yss | -3.966 |
�� | -3.951 |
ramid | -3.888 |
isoft | -3.805 |
Token | ending |
Token ID | 1571 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
>>>>>>>> | +4.617 |
ager | +3.791 |
clusive | +3.767 |
agers | +3.758 |
ances | +3.757 |
Neg logit contributions | |
theorem | -12.945 |
�� | -12.555 |
yss | -12.294 |
ramid | -11.993 |
isoft | -11.873 |
Token | , |
Token ID | 11 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
>>>>>>>> | +3.390 |
Eisenhower | +2.899 |
selves | +2.823 |
Chavez | +2.784 |
ances | +2.705 |
Neg logit contributions | |
theorem | -4.353 |
yss | -4.344 |
isoft | -4.241 |
ramid | -4.219 |
�� | -4.131 |
Token | P |
Token ID | 350 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
>>>>>>>> | +1.737 |
Eisenhower | +1.536 |
selves | +1.490 |
Chavez | +1.475 |
א | +1.416 |
Neg logit contributions | |
theorem | -1.972 |
yss | -1.951 |
isoft | -1.901 |
ramid | -1.891 |
�� | -1.864 |
Token | ious |
Token ID | 699 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
>>>>>>>> | +2.555 |
Eisenhower | +2.268 |
agers | +2.202 |
ager | +2.193 |
ances | +2.175 |
Neg logit contributions | |
theorem | -2.283 |
yss | -2.227 |
isoft | -2.176 |
�� | -2.175 |
ramid | -2.105 |
Token | , |
Token ID | 11 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
>>>>>>>> | +1.120 |
Eisenhower | +0.961 |
selves | +0.940 |
Chavez | +0.927 |
agers | +0.908 |
Neg logit contributions | |
theorem | -1.326 |
yss | -1.314 |
isoft | -1.277 |
ramid | -1.256 |
rons | -1.240 |
Token | go |
Token ID | 467 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
>>>>>>>> | +1.488 |
Eisenhower | +1.297 |
selves | +1.278 |
Chavez | +1.252 |
agers | +1.224 |
Neg logit contributions | |
yss | -1.656 |
theorem | -1.645 |
isoft | -1.623 |
�� | -1.595 |
ramid | -1.587 |
Token | at |
Token ID | 379 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
>>>>>>>> | +1.643 |
Eisenhower | +1.449 |
selves | +1.433 |
Chavez | +1.393 |
ances | +1.363 |
Neg logit contributions | |
theorem | -1.845 |
yss | -1.823 |
isoft | -1.809 |
�� | -1.800 |
ramid | -1.765 |
Token | it |
Token ID | 340 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
theorem | +0.845 |
yss | +0.837 |
isoft | +0.816 |
ramid | +0.801 |
�� | +0.789 |
Neg logit contributions | |
>>>>>>>> | -0.772 |
Eisenhower | -0.669 |
selves | -0.653 |
Chavez | -0.647 |
agers | -0.634 |
Token | like |
Token ID | 588 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
>>>>>>>> | +2.586 |
selves | +2.261 |
Eisenhower | +2.248 |
Chavez | +2.160 |
ances | +2.133 |
Neg logit contributions | |
yss | -3.156 |
isoft | -3.148 |
theorem | -3.144 |
ramid | -3.104 |
�� | -3.084 |
Token | 36 |
Token ID | 4570 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
>>>>>>>> | +2.084 |
Eisenhower | +1.859 |
Chavez | +1.790 |
selves | +1.780 |
agers | +1.738 |
Neg logit contributions | |
theorem | -2.354 |
isoft | -2.351 |
yss | -2.342 |
ramid | -2.285 |
�� | -2.278 |
Token | se |
Token ID | 384 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
>>>>>>>> | +3.825 |
Eisenhower | +3.313 |
selves | +3.282 |
ances | +3.230 |
agers | +3.210 |
Neg logit contributions | |
theorem | -4.577 |
yss | -4.522 |
isoft | -4.522 |
�� | -4.460 |
ramid | -4.460 |
Token | ag |
Token ID | 363 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
>>>>>>>> | +7.928 |
ances | +7.285 |
ager | +7.068 |
agers | +7.041 |
selves | +6.891 |
Neg logit contributions | |
theorem | -9.765 |
�� | -9.502 |
ramid | -9.469 |
isoft | -9.039 |
yss | -9.003 |
Token | ull |
Token ID | 724 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
>>>>>>>> | +3.211 |
Eisenhower | +2.868 |
ances | +2.848 |
selves | +2.809 |
agers | +2.755 |
Neg logit contributions | |
theorem | -3.028 |
yss | -2.980 |
�� | -2.956 |
isoft | -2.925 |
ramid | -2.883 |
Token | s |
Token ID | 82 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
theorem | +1.228 |
yss | +1.210 |
isoft | +1.154 |
ramid | +1.124 |
rons | +1.108 |
Neg logit contributions | |
>>>>>>>> | -2.203 |
Eisenhower | -1.978 |
selves | -1.948 |
Chavez | -1.930 |
agers | -1.904 |
Token | fighting |
Token ID | 4330 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
>>>>>>>> | +0.352 |
Eisenhower | +0.307 |
selves | +0.302 |
Chavez | +0.297 |
agers | +0.292 |
Neg logit contributions | |
theorem | -0.359 |
yss | -0.358 |
isoft | -0.350 |
ramid | -0.344 |
�� | -0.341 |
Token | over |
Token ID | 625 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
>>>>>>>> | +0.849 |
Eisenhower | +0.750 |
Chavez | +0.730 |
selves | +0.729 |
agers | +0.704 |
Neg logit contributions | |
yss | -0.910 |
theorem | -0.902 |
isoft | -0.895 |
ramid | -0.880 |
�� | -0.879 |
Token | Multiple |
Token ID | 31217 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
>>>>>>>> | +0.321 |
Eisenhower | +0.270 |
selves | +0.266 |
Chavez | +0.260 |
agers | +0.258 |
Neg logit contributions | |
theorem | -0.372 |
yss | -0.368 |
isoft | -0.356 |
ramid | -0.352 |
�� | -0.351 |
Token | NHL |
Token ID | 9481 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
theorem | +2.053 |
yss | +2.026 |
isoft | +1.957 |
ramid | +1.917 |
rons | +1.903 |
Neg logit contributions | |
>>>>>>>> | -2.196 |
Eisenhower | -1.919 |
selves | -1.880 |
Chavez | -1.861 |
agers | -1.823 |
Token | sources |
Token ID | 4237 |
Feature activation | +7.02e+00 |
Pos logit contributions | |
>>>>>>>> | +2.060 |
Eisenhower | +1.761 |
selves | +1.733 |
agers | +1.710 |
Chavez | +1.704 |
Neg logit contributions | |
theorem | -2.456 |
yss | -2.453 |
isoft | -2.365 |
�� | -2.355 |
ramid | -2.320 |
Token | – |
Token ID | 784 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
>>>>>>>> | +4.745 |
Eisenhower | +4.160 |
selves | +4.028 |
Chavez | +3.992 |
ances | +3.973 |
Neg logit contributions | |
�� | -6.064 |
yss | -5.945 |
theorem | -5.850 |
isoft | -5.806 |
ramid | -5.698 |
Token | one |
Token ID | 530 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
>>>>>>>> | +2.541 |
Eisenhower | +2.162 |
selves | +2.119 |
Chavez | +2.110 |
agers | +2.045 |
Neg logit contributions | |
yss | -3.243 |
theorem | -3.231 |
ramid | -3.145 |
isoft | -3.137 |
�� | -3.123 |
Token | very |
Token ID | 845 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
>>>>>>>> | +0.939 |
Eisenhower | +0.822 |
selves | +0.801 |
Chavez | +0.796 |
ances | +0.774 |
Neg logit contributions | |
yss | -0.985 |
theorem | -0.980 |
isoft | -0.953 |
ramid | -0.943 |
�� | -0.933 |
Token | close |
Token ID | 1969 |
Feature activation | +8.11e+00 |
Pos logit contributions | |
>>>>>>>> | +7.309 |
Eisenhower | +6.584 |
Chavez | +6.396 |
ager | +6.195 |
selves | +6.074 |
Neg logit contributions | |
yss | -10.413 |
�� | -10.314 |
ramid | -10.294 |
isoft | -10.135 |
theorem | -9.948 |
Token | to |
Token ID | 284 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
>>>>>>>> | +6.141 |
Eisenhower | +5.398 |
Chavez | +5.246 |
selves | +5.235 |
ances | +5.117 |
Neg logit contributions | |
yss | -6.206 |
theorem | -6.105 |
isoft | -6.069 |
ramid | -5.906 |
�� | -5.782 |
Token | the |
Token ID | 262 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
>>>>>>>> | +3.472 |
Eisenhower | +3.038 |
selves | +2.959 |
Chavez | +2.952 |
agers | +2.889 |
Neg logit contributions | |
yss | -3.523 |
theorem | -3.522 |
isoft | -3.438 |
ramid | -3.429 |
�� | -3.349 |
Token | situation |
Token ID | 3074 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
>>>>>>>> | +2.308 |
Eisenhower | +1.984 |
selves | +1.937 |
Chavez | +1.911 |
agers | +1.894 |
Neg logit contributions | |
yss | -2.926 |
theorem | -2.853 |
isoft | -2.821 |
ramid | -2.782 |
�� | -2.778 |
Token | – |
Token ID | 784 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
>>>>>>>> | +2.625 |
Eisenhower | +2.245 |
selves | +2.195 |
Chavez | +2.152 |
agers | +2.105 |
Neg logit contributions | |
yss | -3.451 |
theorem | -3.429 |
ramid | -3.365 |
isoft | -3.363 |
�� | -3.322 |
Token | one |
Token ID | 530 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
>>>>>>>> | +2.595 |
Eisenhower | +2.322 |
selves | +2.276 |
Chavez | +2.225 |
agers | +2.211 |
Neg logit contributions | |
yss | -2.711 |
theorem | -2.640 |
�� | -2.633 |
isoft | -2.632 |
ramid | -2.564 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
>>>>>>>> | +1.511 |
Eisenhower | +1.330 |
selves | +1.306 |
Chavez | +1.282 |
agers | +1.253 |
Neg logit contributions | |
yss | -1.672 |
theorem | -1.663 |
isoft | -1.634 |
�� | -1.610 |
ramid | -1.590 |
Token | I |
Token ID | 314 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
>>>>>>>> | +0.785 |
Eisenhower | +0.679 |
selves | +0.656 |
Chavez | +0.654 |
א | +0.620 |
Neg logit contributions | |
theorem | -0.997 |
yss | -0.983 |
isoft | -0.964 |
�� | -0.947 |
ramid | -0.945 |
Token | think |
Token ID | 892 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
theorem | +1.577 |
yss | +1.570 |
isoft | +1.521 |
ramid | +1.493 |
�� | +1.489 |
Neg logit contributions | |
>>>>>>>> | -1.381 |
Eisenhower | -1.191 |
selves | -1.164 |
Chavez | -1.151 |
agers | -1.129 |
Token | FINAL |
Token ID | 25261 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
theorem | +0.507 |
yss | +0.501 |
isoft | +0.490 |
ramid | +0.481 |
�� | +0.477 |
Neg logit contributions | |
>>>>>>>> | -0.461 |
Eisenhower | -0.400 |
selves | -0.390 |
Chavez | -0.386 |
agers | -0.378 |
Token | EX |
Token ID | 7788 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
>>>>>>>> | +2.913 |
Eisenhower | +2.495 |
selves | +2.404 |
Chavez | +2.394 |
א | +2.296 |
Neg logit contributions | |
yss | -3.615 |
theorem | -3.544 |
isoft | -3.486 |
ramid | -3.462 |
�� | -3.386 |
Token | AM |
Token ID | 2390 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
>>>>>>>> | +4.470 |
א | +2.974 |
Eisenhower | +2.918 |
VICE | +2.855 |
Chavez | +2.797 |
Neg logit contributions | |
�� | -13.871 |
yss | -13.734 |
isoft | -13.669 |
theorem | -13.531 |
uilt | -13.408 |
Token | came |
Token ID | 1625 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
>>>>>>>> | +3.920 |
Eisenhower | +3.425 |
selves | +3.340 |
Chavez | +3.303 |
agers | +3.273 |
Neg logit contributions | |
yss | -4.826 |
theorem | -4.809 |
isoft | -4.730 |
�� | -4.669 |
ramid | -4.629 |
Token | out |
Token ID | 503 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
>>>>>>>> | +2.486 |
Eisenhower | +2.184 |
selves | +2.149 |
Chavez | +2.107 |
ances | +2.014 |
Neg logit contributions | |
theorem | -3.598 |
yss | -3.569 |
isoft | -3.539 |
�� | -3.506 |
ramid | -3.462 |
Token | a |
Token ID | 257 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
>>>>>>>> | +2.930 |
Eisenhower | +2.622 |
Chavez | +2.551 |
selves | +2.547 |
ances | +2.444 |
Neg logit contributions | |
yss | -3.395 |
�� | -3.390 |
isoft | -3.378 |
theorem | -3.376 |
ramid | -3.320 |
Token | little |
Token ID | 1310 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
>>>>>>>> | +1.511 |
Eisenhower | +1.291 |
Chavez | +1.257 |
selves | +1.245 |
agers | +1.204 |
Neg logit contributions | |
yss | -1.892 |
theorem | -1.890 |
isoft | -1.865 |
�� | -1.831 |
ramid | -1.816 |
Token | that |
Token ID | 326 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
theorem | +1.010 |
yss | +1.001 |
isoft | +0.973 |
ramid | +0.957 |
�� | +0.948 |
Neg logit contributions | |
>>>>>>>> | -0.897 |
Eisenhower | -0.773 |
selves | -0.754 |
Chavez | -0.747 |
agers | -0.731 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
theorem | +2.478 |
yss | +2.452 |
isoft | +2.378 |
ramid | +2.330 |
rons | +2.309 |
Neg logit contributions | |
>>>>>>>> | -2.318 |
Eisenhower | -2.001 |
selves | -1.969 |
Chavez | -1.932 |
agers | -1.905 |
Token | air |
Token ID | 1633 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
>>>>>>>> | +0.769 |
Eisenhower | +0.660 |
Chavez | +0.638 |
selves | +0.636 |
agers | +0.616 |
Neg logit contributions | |
yss | -0.951 |
theorem | -0.943 |
isoft | -0.922 |
�� | -0.916 |
ramid | -0.908 |
Token | strikes |
Token ID | 8956 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
theorem | +1.850 |
yss | +1.834 |
isoft | +1.785 |
ramid | +1.757 |
rons | +1.736 |
Neg logit contributions | |
>>>>>>>> | -1.360 |
Eisenhower | -1.150 |
selves | -1.124 |
Chavez | -1.106 |
agers | -1.083 |
Token | targeted |
Token ID | 7977 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
>>>>>>>> | +1.984 |
Eisenhower | +1.715 |
selves | +1.688 |
Chavez | +1.675 |
ances | +1.603 |
Neg logit contributions | |
theorem | -2.546 |
yss | -2.527 |
�� | -2.472 |
isoft | -2.464 |
ramid | -2.429 |
Token | hide |
Token ID | 7808 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
theorem | +1.671 |
yss | +1.653 |
isoft | +1.606 |
ramid | +1.577 |
rons | +1.559 |
Neg logit contributions | |
>>>>>>>> | -1.468 |
Eisenhower | -1.261 |
selves | -1.237 |
Chavez | -1.217 |
agers | -1.197 |
Token | outs |
Token ID | 5269 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
>>>>>>>> | +2.257 |
outs | +1.959 |
agers | +1.632 |
ances | +1.572 |
Eisenhower | +1.395 |
Neg logit contributions | |
�� | -15.178 |
theorem | -15.075 |
yss | -14.856 |
isoft | -14.529 |
ramid | -14.311 |
Token | of |
Token ID | 286 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
>>>>>>>> | +2.518 |
Eisenhower | +2.276 |
Chavez | +2.212 |
selves | +2.184 |
agers | +2.107 |
Neg logit contributions | |
yss | -2.824 |
theorem | -2.790 |
isoft | -2.742 |
�� | -2.721 |
ramid | -2.713 |
Token | militants |
Token ID | 13162 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
>>>>>>>> | +0.776 |
Eisenhower | +0.673 |
Chavez | +0.655 |
selves | +0.652 |
agers | +0.636 |
Neg logit contributions | |
theorem | -0.980 |
yss | -0.977 |
isoft | -0.949 |
�� | -0.948 |
ramid | -0.940 |
Token | who |
Token ID | 508 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
theorem | +0.394 |
yss | +0.392 |
isoft | +0.381 |
ramid | +0.376 |
�� | +0.373 |
Neg logit contributions | |
>>>>>>>> | -0.355 |
Eisenhower | -0.310 |
selves | -0.304 |
Chavez | -0.301 |
agers | -0.292 |
Token | were |
Token ID | 547 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
theorem | +1.890 |
yss | +1.870 |
isoft | +1.817 |
ramid | +1.786 |
rons | +1.768 |
Neg logit contributions | |
>>>>>>>> | -1.646 |
Eisenhower | -1.408 |
selves | -1.376 |
Chavez | -1.357 |
agers | -1.336 |
Token | , |
Token ID | 11 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
>>>>>>>> | +0.484 |
Eisenhower | +0.418 |
selves | +0.411 |
Chavez | +0.403 |
ances | +0.396 |
Neg logit contributions | |
yss | -0.539 |
theorem | -0.539 |
isoft | -0.525 |
ramid | -0.517 |
�� | -0.514 |
Token | giving |
Token ID | 3501 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
>>>>>>>> | +0.357 |
Eisenhower | +0.308 |
selves | +0.300 |
Chavez | +0.297 |
agers | +0.291 |
Neg logit contributions | |
theorem | -0.415 |
yss | -0.412 |
isoft | -0.403 |
ramid | -0.397 |
�� | -0.396 |
Token | her |
Token ID | 607 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
>>>>>>>> | +3.183 |
Eisenhower | +2.770 |
selves | +2.650 |
Chavez | +2.602 |
ances | +2.578 |
Neg logit contributions | |
theorem | -4.164 |
ramid | -4.106 |
yss | -4.090 |
isoft | -4.066 |
�� | -4.007 |
Token | my |
Token ID | 616 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
>>>>>>>> | +1.998 |
Eisenhower | +1.728 |
selves | +1.684 |
Chavez | +1.649 |
agers | +1.620 |
Neg logit contributions | |
theorem | -2.582 |
yss | -2.566 |
isoft | -2.516 |
ramid | -2.493 |
�� | -2.489 |
Token | best |
Token ID | 1266 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
theorem | +0.519 |
yss | +0.515 |
isoft | +0.505 |
ramid | +0.497 |
�� | +0.493 |
Neg logit contributions | |
>>>>>>>> | -0.400 |
Eisenhower | -0.344 |
selves | -0.335 |
Chavez | -0.328 |
ances | -0.321 |
Token | sed |
Token ID | 10081 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
theorem | +0.169 |
yss | +0.169 |
isoft | +0.164 |
ramid | +0.161 |
�� | +0.159 |
Neg logit contributions | |
>>>>>>>> | -0.157 |
Eisenhower | -0.137 |
selves | -0.133 |
Chavez | -0.132 |
agers | -0.130 |
Token | uctive |
Token ID | 45857 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
>>>>>>>> | +4.976 |
ager | +4.190 |
ances | +3.796 |
Eisenhower | +3.790 |
ance | +3.776 |
Neg logit contributions | |
theorem | -12.365 |
yss | -12.029 |
ramid | -11.846 |
�� | -11.746 |
isoft | -11.727 |
Token | eyes |
Token ID | 2951 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
>>>>>>>> | +3.073 |
Eisenhower | +2.744 |
selves | +2.642 |
Chavez | +2.581 |
ager | +2.565 |
Neg logit contributions | |
yss | -3.442 |
theorem | -3.398 |
isoft | -3.387 |
�� | -3.381 |
ramid | -3.352 |
Token | as |
Token ID | 355 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
theorem | +0.512 |
yss | +0.507 |
isoft | +0.492 |
ramid | +0.483 |
�� | +0.476 |
Neg logit contributions | |
>>>>>>>> | -0.505 |
Eisenhower | -0.439 |
selves | -0.430 |
Chavez | -0.425 |
agers | -0.417 |
Token | I |
Token ID | 314 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
>>>>>>>> | +2.311 |
Eisenhower | +2.007 |
selves | +1.936 |
Chavez | +1.917 |
ances | +1.892 |
Neg logit contributions | |
theorem | -2.678 |
yss | -2.651 |
isoft | -2.615 |
ramid | -2.593 |
�� | -2.537 |
Token | 've |
Token ID | 1053 |
Feature activation | -7.52e+00 |
Pos logit contributions | |
theorem | +0.940 |
yss | +0.935 |
isoft | +0.909 |
ramid | +0.893 |
�� | +0.885 |
Neg logit contributions | |
>>>>>>>> | -0.824 |
Eisenhower | -0.709 |
selves | -0.695 |
Chavez | -0.684 |
agers | -0.672 |
Token | Then |
Token ID | 6423 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
theorem | +0.181 |
yss | +0.179 |
isoft | +0.174 |
ramid | +0.171 |
�� | +0.170 |
Neg logit contributions | |
>>>>>>>> | -0.156 |
Eisenhower | -0.132 |
selves | -0.130 |
Chavez | -0.127 |
agers | -0.125 |
Token | , |
Token ID | 11 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
theorem | +3.320 |
yss | +3.287 |
isoft | +3.185 |
ramid | +3.114 |
rons | +3.105 |
Neg logit contributions | |
>>>>>>>> | -3.161 |
Eisenhower | -2.743 |
selves | -2.690 |
Chavez | -2.654 |
agers | -2.628 |
Token | a |
Token ID | 257 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
theorem | +1.810 |
yss | +1.793 |
isoft | +1.739 |
ramid | +1.710 |
�� | +1.686 |
Neg logit contributions | |
>>>>>>>> | -1.767 |
Eisenhower | -1.533 |
selves | -1.503 |
Chavez | -1.485 |
agers | -1.451 |
Token | more |
Token ID | 517 |
Feature activation | +9.14e+00 |
Pos logit contributions | |
>>>>>>>> | +0.894 |
Eisenhower | +0.771 |
selves | +0.762 |
Chavez | +0.753 |
א | +0.727 |
Neg logit contributions | |
yss | -0.922 |
theorem | -0.914 |
isoft | -0.892 |
ramid | -0.877 |
�� | -0.873 |
Token | - |
Token ID | 12 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
>>>>>>>> | +6.171 |
Eisenhower | +5.467 |
Chavez | +5.269 |
deserving | +5.112 |
selves | +5.071 |
Neg logit contributions | |
yss | -7.711 |
�� | -7.597 |
ramid | -7.508 |
isoft | -7.475 |
theorem | -7.457 |
Token | det |
Token ID | 15255 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
>>>>>>>> | +3.796 |
selves | +3.299 |
Eisenhower | +3.293 |
ager | +3.219 |
agers | +3.216 |
Neg logit contributions | |
theorem | -4.126 |
yss | -4.060 |
�� | -3.966 |
isoft | -3.908 |
ramid | -3.877 |
Token | ailed |
Token ID | 6255 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
>>>>>>>> | +5.282 |
ances | +4.376 |
selves | +4.364 |
clusive | +4.324 |
atro | +4.317 |
Neg logit contributions | |
theorem | -11.769 |
�� | -11.590 |
yss | -11.333 |
isoft | -11.052 |
ramid | -10.994 |
Token | Mic |
Token ID | 7631 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
>>>>>>>> | +5.495 |
Eisenhower | +4.875 |
selves | +4.733 |
Chavez | +4.670 |
ager | +4.542 |
Neg logit contributions | |
yss | -5.305 |
isoft | -5.103 |
ramid | -5.061 |
theorem | -5.000 |
�� | -4.967 |
Token | piece |
Token ID | 3704 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
>>>>>>>> | +0.634 |
Eisenhower | +0.557 |
selves | +0.554 |
Chavez | +0.542 |
agers | +0.533 |
Neg logit contributions | |
yss | -0.528 |
theorem | -0.526 |
isoft | -0.502 |
ramid | -0.498 |
�� | -0.493 |
Token | published |
Token ID | 3199 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
>>>>>>>> | +4.558 |
Eisenhower | +3.920 |
selves | +3.919 |
Chavez | +3.841 |
agers | +3.778 |
Neg logit contributions | |
theorem | -4.616 |
yss | -4.591 |
ramid | -4.494 |
isoft | -4.472 |
�� | -4.444 |
Token | yesterday |
Token ID | 7415 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
>>>>>>>> | +0.484 |
Eisenhower | +0.421 |
selves | +0.416 |
Chavez | +0.409 |
agers | +0.399 |
Neg logit contributions | |
theorem | -0.488 |
yss | -0.481 |
isoft | -0.473 |
ramid | -0.464 |
�� | -0.460 |
Token | a |
Token ID | 257 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
theorem | +0.424 |
yss | +0.422 |
isoft | +0.409 |
ramid | +0.403 |
�� | +0.399 |
Neg logit contributions | |
>>>>>>>> | -0.383 |
Eisenhower | -0.335 |
selves | -0.325 |
Chavez | -0.322 |
agers | -0.317 |
Token | health |
Token ID | 1535 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
yss | +0.672 |
theorem | +0.667 |
isoft | +0.652 |
ramid | +0.637 |
�� | +0.636 |
Neg logit contributions | |
>>>>>>>> | -0.630 |
Eisenhower | -0.548 |
selves | -0.533 |
Chavez | -0.529 |
agers | -0.515 |
Token | department |
Token ID | 5011 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
yss | +0.228 |
theorem | +0.227 |
isoft | +0.220 |
ramid | +0.216 |
�� | +0.215 |
Neg logit contributions | |
>>>>>>>> | -0.195 |
Eisenhower | -0.169 |
selves | -0.163 |
Chavez | -0.162 |
agers | -0.158 |
Token | program |
Token ID | 1430 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
>>>>>>>> | +2.446 |
Eisenhower | +2.196 |
Chavez | +2.089 |
selves | +2.063 |
ager | +2.054 |
Neg logit contributions | |
yss | -3.004 |
theorem | -2.935 |
isoft | -2.927 |
�� | -2.863 |
ramid | -2.789 |
Token | that |
Token ID | 326 |
Feature activation | -3.19e-03 |
Pos logit contributions | |
>>>>>>>> | +0.160 |
Eisenhower | +0.141 |
Chavez | +0.135 |
selves | +0.134 |
agers | +0.131 |
Neg logit contributions | |
theorem | -0.194 |
yss | -0.194 |
isoft | -0.190 |
ramid | -0.185 |
�� | -0.185 |
Token | disp |
Token ID | 4596 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
theorem | +0.003 |
yss | +0.003 |
isoft | +0.003 |
�� | +0.003 |
ramid | +0.003 |
Neg logit contributions | |
>>>>>>>> | -0.002 |
Eisenhower | -0.002 |
Chavez | -0.002 |
selves | -0.002 |
ances | -0.002 |
Token | enses |
Token ID | 4541 |
Feature activation | +8.99e+00 |
Pos logit contributions | |
ances | +5.564 |
>>>>>>>> | +5.403 |
outs | +4.843 |
arer | +4.722 |
agers | +4.714 |
Neg logit contributions | |
�� | -12.341 |
theorem | -11.697 |
isoft | -10.867 |
ramid | -10.804 |
yss | -10.739 |
Token | condoms |
Token ID | 33298 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
>>>>>>>> | +6.196 |
Eisenhower | +5.520 |
Chavez | +5.234 |
ances | +5.175 |
selves | +5.121 |
Neg logit contributions | |
isoft | -7.396 |
�� | -7.374 |
yss | -7.366 |
theorem | -7.270 |
ramid | -7.208 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
>>>>>>>> | +1.333 |
Eisenhower | +1.175 |
selves | +1.152 |
Chavez | +1.138 |
ances | +1.118 |
Neg logit contributions | |
yss | -1.397 |
theorem | -1.387 |
isoft | -1.368 |
ramid | -1.336 |
�� | -1.333 |
Token | birth |
Token ID | 4082 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
theorem | +1.101 |
yss | +1.094 |
isoft | +1.060 |
ramid | +1.040 |
�� | +1.030 |
Neg logit contributions | |
>>>>>>>> | -1.197 |
Eisenhower | -1.050 |
selves | -1.026 |
Chavez | -1.017 |
agers | -1.000 |
Token | control |
Token ID | 1630 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
theorem | +0.620 |
yss | +0.614 |
isoft | +0.586 |
ramid | +0.572 |
�� | +0.561 |
Neg logit contributions | |
>>>>>>>> | -1.244 |
Eisenhower | -1.122 |
selves | -1.106 |
Chavez | -1.095 |
agers | -1.085 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
>>>>>>>> | +0.807 |
Eisenhower | +0.701 |
selves | +0.685 |
Chavez | +0.683 |
ances | +0.663 |
Neg logit contributions | |
yss | -0.903 |
theorem | -0.901 |
isoft | -0.882 |
�� | -0.874 |
ramid | -0.867 |
Token | so |
Token ID | 523 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
>>>>>>>> | +0.152 |
Eisenhower | +0.132 |
selves | +0.128 |
Chavez | +0.128 |
ances | +0.124 |
Neg logit contributions | |
theorem | -0.179 |
yss | -0.178 |
isoft | -0.174 |
�� | -0.171 |
ramid | -0.171 |
Token | it |
Token ID | 340 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
>>>>>>>> | +4.018 |
Eisenhower | +3.547 |
selves | +3.455 |
Chavez | +3.455 |
agers | +3.405 |
Neg logit contributions | |
�� | -4.995 |
theorem | -4.961 |
isoft | -4.890 |
yss | -4.875 |
ramid | -4.811 |
Token | 's |
Token ID | 338 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
>>>>>>>> | +2.867 |
Eisenhower | +2.481 |
selves | +2.449 |
ances | +2.427 |
Chavez | +2.420 |
Neg logit contributions | |
theorem | -4.326 |
yss | -4.311 |
�� | -4.284 |
isoft | -4.270 |
ramid | -4.149 |
Token | something |
Token ID | 1223 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
>>>>>>>> | +0.179 |
Eisenhower | +0.157 |
selves | +0.153 |
Chavez | +0.152 |
agers | +0.148 |
Neg logit contributions | |
theorem | -0.193 |
yss | -0.192 |
isoft | -0.189 |
�� | -0.186 |
ramid | -0.185 |
Token | quite |
Token ID | 2407 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
>>>>>>>> | +2.514 |
Eisenhower | +2.202 |
selves | +2.141 |
Chavez | +2.115 |
ances | +2.059 |
Neg logit contributions | |
theorem | -3.283 |
yss | -3.278 |
isoft | -3.217 |
�� | -3.212 |
ramid | -3.182 |
Token | different |
Token ID | 1180 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
>>>>>>>> | +7.120 |
Eisenhower | +6.361 |
Chavez | +6.312 |
selves | +6.187 |
deserving | +6.091 |
Neg logit contributions | |
�� | -10.151 |
yss | -10.058 |
isoft | -10.006 |
ramid | -9.984 |
uilt | -9.854 |
Token | to |
Token ID | 284 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
>>>>>>>> | +1.394 |
Eisenhower | +1.210 |
selves | +1.196 |
Chavez | +1.183 |
ances | +1.153 |
Neg logit contributions | |
theorem | -1.534 |
yss | -1.533 |
isoft | -1.512 |
�� | -1.499 |
ramid | -1.487 |
Token | what |
Token ID | 644 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
>>>>>>>> | +2.238 |
Eisenhower | +1.948 |
selves | +1.892 |
Chavez | +1.891 |
agers | +1.836 |
Neg logit contributions | |
theorem | -2.656 |
yss | -2.654 |
isoft | -2.601 |
�� | -2.569 |
ramid | -2.545 |
Token | we |
Token ID | 356 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
theorem | +0.628 |
yss | +0.623 |
isoft | +0.607 |
ramid | +0.595 |
�� | +0.591 |
Neg logit contributions | |
>>>>>>>> | -0.589 |
Eisenhower | -0.514 |
selves | -0.500 |
Chavez | -0.497 |
agers | -0.486 |
Token | 've |
Token ID | 1053 |
Feature activation | -8.13e+00 |
Pos logit contributions | |
theorem | +2.249 |
yss | +2.228 |
isoft | +2.165 |
ramid | +2.128 |
rons | +2.101 |
Neg logit contributions | |
>>>>>>>> | -1.900 |
Eisenhower | -1.629 |
selves | -1.595 |
Chavez | -1.571 |
agers | -1.541 |
Token | a |
Token ID | 257 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
theorem | +1.100 |
yss | +1.093 |
isoft | +1.065 |
ramid | +1.048 |
�� | +1.035 |
Neg logit contributions | |
>>>>>>>> | -0.854 |
Eisenhower | -0.728 |
selves | -0.707 |
Chavez | -0.700 |
agers | -0.683 |
Token | subdued |
Token ID | 38759 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
theorem | +1.624 |
yss | +1.610 |
isoft | +1.564 |
ramid | +1.536 |
�� | +1.515 |
Neg logit contributions | |
>>>>>>>> | -1.498 |
Eisenhower | -1.295 |
selves | -1.267 |
Chavez | -1.251 |
agers | -1.227 |
Token | and |
Token ID | 290 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
>>>>>>>> | +1.988 |
Eisenhower | +1.770 |
Chavez | +1.694 |
selves | +1.666 |
ances | +1.627 |
Neg logit contributions | |
yss | -2.237 |
theorem | -2.227 |
isoft | -2.223 |
�� | -2.177 |
ramid | -2.171 |
Token | traditional |
Token ID | 4569 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
>>>>>>>> | +0.570 |
Eisenhower | +0.490 |
selves | +0.472 |
Chavez | +0.471 |
agers | +0.457 |
Neg logit contributions | |
theorem | -0.723 |
yss | -0.719 |
isoft | -0.705 |
ramid | -0.693 |
�� | -0.686 |
Token | entrance |
Token ID | 10384 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
>>>>>>>> | +1.546 |
Eisenhower | +1.358 |
Chavez | +1.289 |
selves | +1.286 |
ances | +1.249 |
Neg logit contributions | |
theorem | -1.866 |
yss | -1.848 |
isoft | -1.841 |
�� | -1.795 |
ramid | -1.787 |
Token | utterly |
Token ID | 15950 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
>>>>>>>> | +2.317 |
Eisenhower | +2.014 |
selves | +1.934 |
Chavez | +1.929 |
ances | +1.917 |
Neg logit contributions | |
yss | -2.512 |
theorem | -2.482 |
isoft | -2.445 |
ramid | -2.394 |
�� | -2.379 |
Token | devoid |
Token ID | 34065 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
>>>>>>>> | +6.845 |
Eisenhower | +6.311 |
Chavez | +6.052 |
ances | +5.958 |
selves | +5.950 |
Neg logit contributions | |
�� | -10.144 |
yss | -10.098 |
isoft | -9.899 |
theorem | -9.773 |
ramid | -9.741 |
Token | of |
Token ID | 286 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
>>>>>>>> | +3.565 |
Eisenhower | +3.155 |
selves | +3.012 |
Chavez | +3.004 |
ances | +2.978 |
Neg logit contributions | |
yss | -4.008 |
theorem | -3.958 |
isoft | -3.926 |
ramid | -3.925 |
�� | -3.887 |
Token | fog |
Token ID | 19558 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
theorem | +2.095 |
yss | +2.076 |
isoft | +2.016 |
ramid | +1.982 |
rons | +1.960 |
Neg logit contributions | |
>>>>>>>> | -1.715 |
Eisenhower | -1.464 |
selves | -1.434 |
Chavez | -1.411 |
agers | -1.385 |
Token | machines |
Token ID | 8217 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
theorem | +5.350 |
yss | +5.239 |
isoft | +5.122 |
rons | +5.017 |
ramid | +4.963 |
Neg logit contributions | |
>>>>>>>> | -5.525 |
Eisenhower | -4.772 |
selves | -4.702 |
Chavez | -4.652 |
agers | -4.570 |
Token | or |
Token ID | 393 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
theorem | +1.128 |
yss | +1.121 |
isoft | +1.091 |
ramid | +1.072 |
�� | +1.059 |
Neg logit contributions | |
>>>>>>>> | -1.029 |
Eisenhower | -0.894 |
selves | -0.872 |
Chavez | -0.862 |
ances | -0.843 |
Token | the |
Token ID | 262 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
theorem | +2.178 |
yss | +2.164 |
isoft | +2.098 |
ramid | +2.052 |
�� | +2.031 |
Neg logit contributions | |
>>>>>>>> | -2.390 |
Eisenhower | -2.094 |
selves | -2.049 |
Chavez | -2.036 |
agers | -1.993 |
Token | full |
Token ID | 1336 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
>>>>>>>> | +1.000 |
Eisenhower | +0.867 |
selves | +0.835 |
Chavez | +0.834 |
agers | +0.806 |
Neg logit contributions | |
yss | -1.133 |
theorem | -1.120 |
isoft | -1.114 |
�� | -1.092 |
ramid | -1.087 |
Token | list |
Token ID | 1351 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
>>>>>>>> | +4.794 |
Eisenhower | +4.284 |
Chavez | +4.134 |
Rockefeller | +4.013 |
selves | +4.013 |
Neg logit contributions | |
yss | -4.851 |
isoft | -4.822 |
theorem | -4.729 |
ramid | -4.713 |
�� | -4.708 |
Token | . |
Token ID | 13 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
theorem | +0.161 |
yss | +0.161 |
isoft | +0.157 |
ramid | +0.154 |
�� | +0.153 |
Neg logit contributions | |
>>>>>>>> | -0.159 |
Eisenhower | -0.138 |
selves | -0.135 |
Chavez | -0.134 |
ances | -0.131 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
>>>>>>>> | +0.515 |
Eisenhower | +0.442 |
selves | +0.426 |
Chavez | +0.425 |
ances | +0.404 |
Neg logit contributions | |
theorem | -0.679 |
yss | -0.674 |
isoft | -0.657 |
ramid | -0.647 |
�� | -0.644 |
Token | Last |
Token ID | 5956 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
theorem | +2.659 |
yss | +2.642 |
isoft | +2.572 |
ramid | +2.523 |
rons | +2.488 |
Neg logit contributions | |
>>>>>>>> | -2.398 |
Eisenhower | -2.082 |
selves | -2.039 |
Chavez | -2.017 |
agers | -1.965 |
Token | weekend |
Token ID | 5041 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
theorem | +9.932 |
yss | +9.356 |
isoft | +9.120 |
omi | +8.813 |
rons | +8.788 |
Neg logit contributions | |
>>>>>>>> | -12.229 |
selves | -10.626 |
Eisenhower | -10.446 |
agers | -10.181 |
Chavez | -10.081 |
Token | in |
Token ID | 287 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
theorem | +3.317 |
yss | +3.272 |
isoft | +3.193 |
ramid | +3.104 |
rons | +3.093 |
Neg logit contributions | |
>>>>>>>> | -3.077 |
Eisenhower | -2.640 |
selves | -2.620 |
Chavez | -2.541 |
agers | -2.532 |
Token | the |
Token ID | 262 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
>>>>>>>> | +2.314 |
Eisenhower | +2.030 |
Chavez | +1.978 |
selves | +1.922 |
agers | +1.876 |
Neg logit contributions | |
yss | -3.255 |
theorem | -3.226 |
isoft | -3.136 |
ramid | -3.133 |
�� | -3.101 |
Token | largest |
Token ID | 4387 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
>>>>>>>> | +1.808 |
Eisenhower | +1.579 |
Chavez | +1.511 |
selves | +1.506 |
agers | +1.455 |
Neg logit contributions | |
yss | -2.374 |
theorem | -2.372 |
isoft | -2.297 |
ramid | -2.280 |
�� | -2.244 |
Token | show |
Token ID | 905 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
theorem | +1.598 |
yss | +1.588 |
isoft | +1.543 |
ramid | +1.519 |
�� | +1.499 |
Neg logit contributions | |
>>>>>>>> | -1.351 |
Eisenhower | -1.161 |
selves | -1.133 |
Chavez | -1.121 |
agers | -1.096 |
Token | gesture |
Token ID | 18342 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
yss | +0.128 |
theorem | +0.128 |
isoft | +0.125 |
ramid | +0.123 |
�� | +0.123 |
Neg logit contributions | |
>>>>>>>> | -0.111 |
Eisenhower | -0.095 |
selves | -0.093 |
Chavez | -0.092 |
ances | -0.090 |
Token | of |
Token ID | 286 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
>>>>>>>> | +1.589 |
Eisenhower | +1.378 |
selves | +1.365 |
Chavez | +1.330 |
ances | +1.314 |
Neg logit contributions | |
yss | -1.767 |
theorem | -1.742 |
isoft | -1.721 |
ramid | -1.700 |
�� | -1.698 |
Token | protest |
Token ID | 5402 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
theorem | +0.405 |
yss | +0.404 |
isoft | +0.393 |
ramid | +0.387 |
�� | +0.384 |
Neg logit contributions | |
>>>>>>>> | -0.368 |
Eisenhower | -0.319 |
selves | -0.311 |
Chavez | -0.309 |
agers | -0.300 |
Token | . |
Token ID | 13 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
>>>>>>>> | +0.346 |
Eisenhower | +0.299 |
selves | +0.296 |
Chavez | +0.290 |
ances | +0.288 |
Neg logit contributions | |
theorem | -0.370 |
yss | -0.369 |
isoft | -0.360 |
ramid | -0.354 |
�� | -0.352 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
>>>>>>>> | +1.626 |
Eisenhower | +1.413 |
selves | +1.369 |
Chavez | +1.368 |
ances | +1.290 |
Neg logit contributions | |
theorem | -2.119 |
yss | -2.108 |
isoft | -2.058 |
ramid | -2.028 |
�� | -2.019 |
Token | Last |
Token ID | 5956 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
theorem | +2.253 |
yss | +2.237 |
isoft | +2.175 |
ramid | +2.135 |
rons | +2.106 |
Neg logit contributions | |
>>>>>>>> | -2.032 |
Eisenhower | -1.760 |
selves | -1.724 |
Chavez | -1.703 |
agers | -1.664 |
Token | Chance |
Token ID | 11809 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
theorem | +9.505 |
yss | +9.010 |
isoft | +8.761 |
omi | +8.452 |
rons | +8.433 |
Neg logit contributions | |
>>>>>>>> | -11.679 |
selves | -10.162 |
Eisenhower | -10.003 |
agers | -9.744 |
Chavez | -9.651 |
Token | to |
Token ID | 284 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
>>>>>>>> | +1.293 |
Eisenhower | +1.120 |
Chavez | +1.092 |
selves | +1.079 |
agers | +1.055 |
Neg logit contributions | |
yss | -1.348 |
theorem | -1.330 |
isoft | -1.306 |
�� | -1.300 |
ramid | -1.275 |
Token | See |
Token ID | 4091 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
>>>>>>>> | +2.146 |
Eisenhower | +1.907 |
Chavez | +1.858 |
selves | +1.842 |
agers | +1.767 |
Neg logit contributions | |
theorem | -2.190 |
yss | -2.187 |
isoft | -2.125 |
�� | -2.099 |
ramid | -2.070 |
Token | the |
Token ID | 262 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
>>>>>>>> | +2.450 |
Eisenhower | +2.155 |
Chavez | +2.096 |
selves | +2.044 |
ances | +1.993 |
Neg logit contributions | |
yss | -3.017 |
theorem | -3.004 |
isoft | -2.946 |
ramid | -2.910 |
�� | -2.909 |
Token | Small |
Token ID | 10452 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
>>>>>>>> | +1.413 |
Eisenhower | +1.251 |
Chavez | +1.219 |
selves | +1.213 |
agers | +1.169 |
Neg logit contributions | |
theorem | -1.600 |
yss | -1.582 |
isoft | -1.535 |
ramid | -1.513 |
�� | -1.502 |
Token | } |
Token ID | 1782 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
theorem | +0.830 |
yss | +0.823 |
isoft | +0.798 |
ramid | +0.780 |
�� | +0.773 |
Neg logit contributions | |
>>>>>>>> | -0.879 |
Eisenhower | -0.768 |
selves | -0.755 |
Chavez | -0.746 |
ances | -0.731 |
Token | } |
Token ID | 1782 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
theorem | +2.817 |
yss | +2.785 |
isoft | +2.692 |
ramid | +2.640 |
rons | +2.607 |
Neg logit contributions | |
>>>>>>>> | -2.940 |
Eisenhower | -2.559 |
selves | -2.512 |
Chavez | -2.480 |
agers | -2.452 |
Token | if |
Token ID | 611 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
theorem | +3.880 |
yss | +3.821 |
isoft | +3.689 |
ramid | +3.627 |
rons | +3.560 |
Neg logit contributions | |
>>>>>>>> | -3.879 |
Eisenhower | -3.371 |
selves | -3.300 |
Chavez | -3.276 |
agers | -3.232 |
Token | ($ |
Token ID | 7198 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
theorem | +2.433 |
yss | +2.398 |
isoft | +2.319 |
ramid | +2.268 |
rons | +2.238 |
Neg logit contributions | |
>>>>>>>> | -2.998 |
Eisenhower | -2.637 |
selves | -2.598 |
Chavez | -2.568 |
agers | -2.530 |
Token | Use |
Token ID | 11041 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
theorem | +4.179 |
yss | +4.148 |
isoft | +4.038 |
ramid | +3.924 |
rons | +3.897 |
Neg logit contributions | |
>>>>>>>> | -4.439 |
Eisenhower | -3.851 |
Chavez | -3.777 |
selves | -3.757 |
agers | -3.653 |
Token | Current |
Token ID | 11297 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
theorem | +3.330 |
yss | +3.291 |
isoft | +3.203 |
ramid | +3.137 |
rons | +3.096 |
Neg logit contributions | |
>>>>>>>> | -3.434 |
Eisenhower | -2.988 |
selves | -2.933 |
Chavez | -2.911 |
agers | -2.843 |
Token | Wall |
Token ID | 22401 |
Feature activation | -9.48e+00 |
Pos logit contributions | |
theorem | +9.016 |
yss | +8.793 |
isoft | +8.654 |
ramid | +8.358 |
rons | +8.223 |
Neg logit contributions | |
>>>>>>>> | -9.666 |
Eisenhower | -8.552 |
Chavez | -8.444 |
selves | -8.295 |
agers | -8.237 |
Token | paper |
Token ID | 20189 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
yss | +6.087 |
theorem | +6.073 |
isoft | +5.887 |
rons | +5.625 |
ramid | +5.613 |
Neg logit contributions | |
>>>>>>>> | -8.388 |
Eisenhower | -7.416 |
Chavez | -7.313 |
selves | -7.208 |
agers | -6.991 |
Token | As |
Token ID | 1722 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
theorem | +1.290 |
yss | +1.278 |
isoft | +1.241 |
ramid | +1.219 |
rons | +1.204 |
Neg logit contributions | |
>>>>>>>> | -1.137 |
Eisenhower | -0.978 |
selves | -0.958 |
Chavez | -0.944 |
agers | -0.927 |
Token | Source |
Token ID | 7416 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
theorem | +0.310 |
yss | +0.307 |
isoft | +0.295 |
�� | +0.292 |
ramid | +0.290 |
Neg logit contributions | |
>>>>>>>> | -0.348 |
Eisenhower | -0.304 |
selves | -0.300 |
Chavez | -0.291 |
agers | -0.289 |
Token | ) |
Token ID | 8 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
theorem | +0.389 |
yss | +0.386 |
isoft | +0.374 |
ramid | +0.369 |
�� | +0.366 |
Neg logit contributions | |
>>>>>>>> | -0.322 |
Eisenhower | -0.276 |
selves | -0.270 |
Chavez | -0.265 |
agers | -0.260 |
Token | infrastructure |
Token ID | 6884 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
yss | +0.079 |
theorem | +0.079 |
isoft | +0.077 |
ramid | +0.075 |
�� | +0.075 |
Neg logit contributions | |
>>>>>>>> | -0.073 |
Eisenhower | -0.063 |
selves | -0.062 |
Chavez | -0.061 |
agers | -0.060 |
Token | projects |
Token ID | 4493 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
theorem | +1.561 |
yss | +1.551 |
isoft | +1.505 |
ramid | +1.473 |
�� | +1.456 |
Neg logit contributions | |
>>>>>>>> | -1.656 |
Eisenhower | -1.446 |
selves | -1.417 |
Chavez | -1.402 |
agers | -1.375 |
Token | . |
Token ID | 13 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
>>>>>>>> | +0.111 |
Eisenhower | +0.096 |
selves | +0.095 |
Chavez | +0.093 |
agers | +0.091 |
Neg logit contributions | |
theorem | -0.117 |
yss | -0.117 |
isoft | -0.114 |
ramid | -0.112 |
�� | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
theorem | +0.311 |
yss | +0.308 |
isoft | +0.299 |
ramid | +0.295 |
�� | +0.293 |
Neg logit contributions | |
>>>>>>>> | -0.256 |
Eisenhower | -0.220 |
selves | -0.215 |
Chavez | -0.212 |
agers | -0.205 |
Token |
|
Token ID | 198 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
theorem | +0.276 |
yss | +0.274 |
isoft | +0.266 |
ramid | +0.262 |
rons | +0.259 |
Neg logit contributions | |
>>>>>>>> | -0.217 |
Eisenhower | -0.184 |
selves | -0.180 |
Chavez | -0.178 |
agers | -0.174 |
Token | Last |
Token ID | 5956 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
theorem | +0.658 |
yss | +0.651 |
isoft | +0.631 |
ramid | +0.621 |
�� | +0.617 |
Neg logit contributions | |
>>>>>>>> | -0.602 |
Eisenhower | -0.517 |
selves | -0.507 |
Chavez | -0.498 |
agers | -0.490 |
Token | week |
Token ID | 1285 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
theorem | +8.555 |
yss | +8.201 |
isoft | +7.833 |
rons | +7.624 |
ramid | +7.613 |
Neg logit contributions | |
>>>>>>>> | -10.752 |
selves | -9.420 |
Eisenhower | -9.204 |
agers | -9.069 |
Chavez | -8.927 |
Token | , |
Token ID | 11 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
theorem | +5.526 |
yss | +5.454 |
isoft | +5.317 |
rons | +5.168 |
ramid | +5.162 |
Neg logit contributions | |
>>>>>>>> | -5.142 |
selves | -4.438 |
Eisenhower | -4.426 |
agers | -4.297 |
Chavez | -4.239 |
Token | residents |
Token ID | 5085 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
theorem | +2.145 |
yss | +2.126 |
isoft | +2.067 |
ramid | +2.035 |
rons | +2.008 |
Neg logit contributions | |
>>>>>>>> | -1.706 |
Eisenhower | -1.455 |
selves | -1.421 |
Chavez | -1.402 |
agers | -1.371 |
Token | of |
Token ID | 286 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
>>>>>>>> | +1.849 |
Eisenhower | +1.632 |
Chavez | +1.599 |
selves | +1.593 |
ances | +1.539 |
Neg logit contributions | |
yss | -1.886 |
theorem | -1.884 |
isoft | -1.840 |
ramid | -1.818 |
�� | -1.796 |
Token | more |
Token ID | 517 |
Feature activation | +6.30e+00 |
Pos logit contributions | |
>>>>>>>> | +0.799 |
Eisenhower | +0.688 |
Chavez | +0.662 |
selves | +0.658 |
agers | +0.635 |
Neg logit contributions | |
theorem | -1.122 |
yss | -1.120 |
isoft | -1.090 |
ramid | -1.077 |
�� | -1.066 |
Token | PT |
Token ID | 11571 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
theorem | +0.734 |
yss | +0.727 |
isoft | +0.704 |
ramid | +0.692 |
rons | +0.683 |
Neg logit contributions | |
>>>>>>>> | -0.734 |
Eisenhower | -0.638 |
selves | -0.626 |
Chavez | -0.617 |
agers | -0.606 |
Token | PowerPoint |
Token ID | 43563 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
theorem | +3.962 |
yss | +3.906 |
isoft | +3.756 |
ramid | +3.636 |
rons | +3.580 |
Neg logit contributions | |
>>>>>>>> | -6.296 |
Eisenhower | -5.620 |
selves | -5.545 |
Chavez | -5.485 |
ances | -5.414 |
Token | slide |
Token ID | 10649 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
theorem | +0.535 |
yss | +0.529 |
isoft | +0.511 |
ramid | +0.500 |
rons | +0.493 |
Neg logit contributions | |
>>>>>>>> | -0.654 |
Eisenhower | -0.576 |
selves | -0.566 |
Chavez | -0.560 |
agers | -0.551 |
Token |
|
Token ID | 198 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
theorem | +0.084 |
yss | +0.083 |
isoft | +0.081 |
ramid | +0.080 |
�� | +0.080 |
Neg logit contributions | |
>>>>>>>> | -0.061 |
Eisenhower | -0.052 |
selves | -0.051 |
Chavez | -0.050 |
ances | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
theorem | +3.154 |
yss | +3.093 |
isoft | +2.983 |
ramid | +2.976 |
rons | +2.962 |
Neg logit contributions | |
>>>>>>>> | -2.970 |
Eisenhower | -2.535 |
selves | -2.508 |
Chavez | -2.482 |
WithNo | -2.473 |
Token | Power |
Token ID | 13434 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
theorem | +1.814 |
yss | +1.812 |
isoft | +1.702 |
ramid | +1.671 |
rons | +1.633 |
Neg logit contributions | |
>>>>>>>> | -3.531 |
Eisenhower | -3.206 |
selves | -3.175 |
Chavez | -3.136 |
agers | -3.115 |
Token | Point |
Token ID | 12727 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
theorem | +8.710 |
yss | +8.472 |
omi | +7.680 |
isoft | +7.660 |
rons | +7.407 |
Neg logit contributions | |
>>>>>>>> | -10.729 |
selves | -9.617 |
Eisenhower | -9.228 |
agers | -8.953 |
Chavez | -8.856 |
Token | slide |
Token ID | 10649 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
theorem | +3.492 |
yss | +3.369 |
isoft | +3.287 |
ramid | +3.236 |
rons | +3.157 |
Neg logit contributions | |
>>>>>>>> | -4.845 |
Eisenhower | -4.274 |
selves | -4.225 |
agers | -4.169 |
Chavez | -4.134 |
Token | PNG |
Token ID | 36182 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
theorem | +0.264 |
yss | +0.262 |
isoft | +0.255 |
ramid | +0.250 |
rons | +0.247 |
Neg logit contributions | |
>>>>>>>> | -0.238 |
Eisenhower | -0.205 |
selves | -0.201 |
Chavez | -0.198 |
agers | -0.195 |
Token | larger |
Token ID | 4025 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
theorem | +2.212 |
yss | +2.186 |
isoft | +2.115 |
ramid | +2.079 |
rons | +2.051 |
Neg logit contributions | |
>>>>>>>> | -2.408 |
Eisenhower | -2.106 |
selves | -2.068 |
Chavez | -2.040 |
agers | -2.006 |
Token | image |
Token ID | 2939 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
theorem | +0.951 |
yss | +0.941 |
isoft | +0.902 |
ramid | +0.878 |
�� | +0.865 |
Neg logit contributions | |
>>>>>>>> | -1.709 |
Eisenhower | -1.534 |
selves | -1.513 |
Chavez | -1.497 |
agers | -1.478 |
Token | they |
Token ID | 484 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
>>>>>>>> | +1.159 |
Eisenhower | +1.007 |
selves | +0.981 |
Chavez | +0.979 |
agers | +0.949 |
Neg logit contributions | |
theorem | -1.292 |
yss | -1.276 |
isoft | -1.268 |
ramid | -1.249 |
�� | -1.233 |
Token | measured |
Token ID | 8630 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
>>>>>>>> | +1.447 |
Eisenhower | +1.275 |
selves | +1.260 |
Chavez | +1.243 |
ances | +1.216 |
Neg logit contributions | |
yss | -1.272 |
theorem | -1.250 |
�� | -1.224 |
isoft | -1.192 |
ramid | -1.187 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
theorem | +1.130 |
yss | +1.121 |
isoft | +1.093 |
ramid | +1.067 |
�� | +1.056 |
Neg logit contributions | |
>>>>>>>> | -1.115 |
Eisenhower | -0.971 |
selves | -0.947 |
Chavez | -0.941 |
agers | -0.923 |
Token | levels |
Token ID | 2974 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
yss | +0.905 |
theorem | +0.903 |
isoft | +0.882 |
ramid | +0.853 |
�� | +0.847 |
Neg logit contributions | |
>>>>>>>> | -1.041 |
Eisenhower | -0.918 |
Chavez | -0.893 |
selves | -0.890 |
agers | -0.873 |
Token | of |
Token ID | 286 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
theorem | +2.356 |
yss | +2.302 |
isoft | +2.228 |
ramid | +2.177 |
rons | +2.173 |
Neg logit contributions | |
>>>>>>>> | -3.011 |
Eisenhower | -2.630 |
selves | -2.625 |
Chavez | -2.556 |
agers | -2.521 |
Token | uranium |
Token ID | 22010 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
theorem | +3.078 |
yss | +3.036 |
isoft | +2.934 |
ramid | +2.887 |
rons | +2.856 |
Neg logit contributions | |
>>>>>>>> | -3.147 |
Eisenhower | -2.729 |
selves | -2.696 |
Chavez | -2.640 |
agers | -2.600 |
Token | , |
Token ID | 11 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
theorem | +8.793 |
yss | +8.326 |
rons | +8.121 |
isoft | +8.080 |
ramid | +7.982 |
Neg logit contributions | |
>>>>>>>> | -10.209 |
selves | -9.158 |
Eisenhower | -8.823 |
agers | -8.673 |
Chavez | -8.567 |
Token | thor |
Token ID | 41899 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
theorem | +3.364 |
yss | +3.325 |
isoft | +3.225 |
ramid | +3.166 |
rons | +3.131 |
Neg logit contributions | |
>>>>>>>> | -3.343 |
Eisenhower | -2.900 |
selves | -2.852 |
Chavez | -2.804 |
agers | -2.760 |
Token | ium |
Token ID | 1505 |
Feature activation | -8.90e+00 |
Pos logit contributions | |
yss | +3.171 |
theorem | +3.140 |
isoft | +2.970 |
rons | +2.870 |
ramid | +2.822 |
Neg logit contributions | |
>>>>>>>> | -9.034 |
Eisenhower | -8.082 |
selves | -8.021 |
Chavez | -7.952 |
agers | -7.850 |
Token | and |
Token ID | 290 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
theorem | +6.127 |
yss | +5.968 |
rons | +5.738 |
isoft | +5.673 |
ramid | +5.662 |
Neg logit contributions | |
>>>>>>>> | -7.428 |
selves | -6.485 |
Eisenhower | -6.441 |
Chavez | -6.229 |
agers | -6.212 |
Token | lead |
Token ID | 1085 |
Feature activation | -8.57e+00 |
Pos logit contributions | |
theorem | +3.664 |
yss | +3.592 |
isoft | +3.482 |
ramid | +3.419 |
rons | +3.410 |
Neg logit contributions | |
>>>>>>>> | -3.854 |
Eisenhower | -3.329 |
selves | -3.303 |
Chavez | -3.221 |
agers | -3.193 |
Token | its |
Token ID | 663 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
>>>>>>>> | +1.386 |
Eisenhower | +1.218 |
selves | +1.199 |
Chavez | +1.183 |
ances | +1.155 |
Neg logit contributions | |
yss | -1.554 |
theorem | -1.527 |
�� | -1.508 |
isoft | -1.492 |
ramid | -1.451 |
Token | detriment |
Token ID | 42959 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
>>>>>>>> | +2.052 |
Eisenhower | +1.808 |
selves | +1.766 |
Chavez | +1.746 |
ances | +1.675 |
Neg logit contributions | |
yss | -3.031 |
isoft | -2.951 |
theorem | -2.944 |
�� | -2.915 |
ramid | -2.908 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
>>>>>>>> | +0.713 |
Eisenhower | +0.614 |
selves | +0.613 |
Chavez | +0.591 |
ances | +0.588 |
Neg logit contributions | |
theorem | -0.781 |
yss | -0.780 |
isoft | -0.758 |
ramid | -0.750 |
�� | -0.742 |
Token |
|
Token ID | 198 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
>>>>>>>> | +0.097 |
Eisenhower | +0.085 |
selves | +0.082 |
Chavez | +0.081 |
ances | +0.078 |
Neg logit contributions | |
theorem | -0.116 |
yss | -0.116 |
isoft | -0.112 |
ramid | -0.111 |
�� | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
theorem | +0.843 |
yss | +0.833 |
isoft | +0.809 |
ramid | +0.798 |
rons | +0.790 |
Neg logit contributions | |
>>>>>>>> | -0.689 |
Eisenhower | -0.587 |
selves | -0.575 |
Chavez | -0.568 |
agers | -0.558 |
Token | Last |
Token ID | 5956 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
theorem | +1.289 |
yss | +1.276 |
isoft | +1.238 |
ramid | +1.218 |
�� | +1.205 |
Neg logit contributions | |
>>>>>>>> | -1.191 |
Eisenhower | -1.026 |
selves | -1.005 |
Chavez | -0.990 |
agers | -0.973 |
Token | night |
Token ID | 1755 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
theorem | +8.363 |
yss | +7.941 |
isoft | +7.589 |
omi | +7.369 |
ramid | +7.357 |
Neg logit contributions | |
>>>>>>>> | -10.516 |
selves | -9.181 |
Eisenhower | -8.978 |
agers | -8.901 |
Chavez | -8.769 |
Token | President |
Token ID | 1992 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
theorem | +3.120 |
yss | +3.093 |
isoft | +3.002 |
ramid | +2.931 |
rons | +2.911 |
Neg logit contributions | |
>>>>>>>> | -2.871 |
Eisenhower | -2.476 |
selves | -2.450 |
Chavez | -2.393 |
agers | -2.369 |
Token | Obama |
Token ID | 2486 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
theorem | +5.578 |
yss | +5.549 |
isoft | +5.400 |
ramid | +5.317 |
rons | +5.311 |
Neg logit contributions | |
>>>>>>>> | -2.182 |
selves | -1.622 |
Eisenhower | -1.558 |
agers | -1.500 |
ances | -1.493 |
Token | acknowledged |
Token ID | 10810 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
>>>>>>>> | +0.959 |
Eisenhower | +0.857 |
Chavez | +0.827 |
selves | +0.818 |
ances | +0.800 |
Neg logit contributions | |
theorem | -0.964 |
yss | -0.956 |
isoft | -0.936 |
�� | -0.935 |
ramid | -0.926 |
Token | � |
Token ID | 564 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
>>>>>>>> | +1.902 |
Eisenhower | +1.662 |
Chavez | +1.594 |
selves | +1.556 |
ances | +1.555 |
Neg logit contributions | |
theorem | -2.270 |
yss | -2.259 |
isoft | -2.233 |
ramid | -2.211 |
�� | -2.208 |
Token | or |
Token ID | 273 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
theorem | +2.447 |
yss | +2.424 |
isoft | +2.343 |
ramid | +2.307 |
�� | +2.279 |
Neg logit contributions | |
>>>>>>>> | -2.551 |
Eisenhower | -2.225 |
selves | -2.188 |
Chavez | -2.159 |
agers | -2.119 |
Token | rh |
Token ID | 17179 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
>>>>>>>> | +0.272 |
Eisenhower | +0.230 |
selves | +0.226 |
Chavez | +0.222 |
ances | +0.221 |
Neg logit contributions | |
theorem | -0.349 |
yss | -0.347 |
isoft | -0.335 |
�� | -0.335 |
ramid | -0.330 |
Token | age |
Token ID | 496 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
yss | +4.464 |
theorem | +4.424 |
isoft | +4.340 |
rons | +4.258 |
omi | +4.242 |
Neg logit contributions | |
>>>>>>>> | -2.177 |
Eisenhower | -1.725 |
Chavez | -1.654 |
selves | -1.584 |
א | -1.522 |
Token | ," |
Token ID | 553 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
theorem | +2.279 |
yss | +2.253 |
isoft | +2.187 |
ramid | +2.146 |
rons | +2.120 |
Neg logit contributions | |
>>>>>>>> | -2.170 |
Eisenhower | -1.877 |
selves | -1.841 |
Chavez | -1.816 |
agers | -1.785 |
Token | said |
Token ID | 531 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
theorem | +2.671 |
yss | +2.650 |
isoft | +2.578 |
ramid | +2.523 |
rons | +2.496 |
Neg logit contributions | |
>>>>>>>> | -2.272 |
Eisenhower | -1.943 |
selves | -1.907 |
Chavez | -1.874 |
agers | -1.833 |
Token | Raj |
Token ID | 13308 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
theorem | +2.493 |
yss | +2.474 |
isoft | +2.402 |
ramid | +2.349 |
rons | +2.323 |
Neg logit contributions | |
>>>>>>>> | -2.269 |
Eisenhower | -1.942 |
selves | -1.910 |
Chavez | -1.870 |
agers | -1.837 |
Token | k |
Token ID | 74 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
yss | +8.285 |
isoft | +8.233 |
theorem | +7.896 |
ramid | +7.758 |
rons | +7.735 |
Neg logit contributions | |
>>>>>>>> | -10.395 |
selves | -8.729 |
Eisenhower | -8.682 |
WithNo | -8.558 |
Chavez | -8.525 |
Token | ot |
Token ID | 313 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
theorem | +2.365 |
yss | +2.358 |
isoft | +2.307 |
ramid | +2.240 |
rons | +2.184 |
Neg logit contributions | |
>>>>>>>> | -3.548 |
Eisenhower | -3.131 |
selves | -3.081 |
Chavez | -3.046 |
א | -2.997 |
Token | Tal |
Token ID | 7193 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
theorem | +2.087 |
yss | +2.065 |
isoft | +2.016 |
ramid | +1.974 |
rons | +1.951 |
Neg logit contributions | |
>>>>>>>> | -1.709 |
Eisenhower | -1.453 |
selves | -1.427 |
Chavez | -1.400 |
agers | -1.371 |
Token | uka |
Token ID | 14852 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
>>>>>>>> | +1.802 |
Eisenhower | +1.573 |
agers | +1.540 |
Chavez | +1.536 |
selves | +1.534 |
Neg logit contributions | |
theorem | -2.038 |
yss | -2.024 |
isoft | -1.937 |
�� | -1.922 |
ramid | -1.913 |
Token | police |
Token ID | 1644 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
>>>>>>>> | +1.177 |
Eisenhower | +1.017 |
selves | +0.984 |
Chavez | +0.981 |
agers | +0.965 |
Neg logit contributions | |
theorem | -1.436 |
yss | -1.418 |
isoft | -1.375 |
ramid | -1.364 |
�� | -1.356 |
Token | by |
Token ID | 416 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
theorem | +2.855 |
yss | +2.832 |
isoft | +2.746 |
ramid | +2.693 |
�� | +2.654 |
Neg logit contributions | |
>>>>>>>> | -2.900 |
Eisenhower | -2.525 |
selves | -2.476 |
Chavez | -2.445 |
agers | -2.404 |
Token | stacking |
Token ID | 41228 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
theorem | +1.090 |
yss | +1.088 |
isoft | +1.050 |
ramid | +1.028 |
�� | +1.012 |
Neg logit contributions | |
>>>>>>>> | -1.463 |
Eisenhower | -1.302 |
selves | -1.274 |
Chavez | -1.265 |
agers | -1.243 |
Token | alternating |
Token ID | 39623 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
theorem | +1.681 |
yss | +1.663 |
isoft | +1.610 |
ramid | +1.582 |
rons | +1.563 |
Neg logit contributions | |
>>>>>>>> | -1.673 |
Eisenhower | -1.451 |
selves | -1.426 |
Chavez | -1.406 |
agers | -1.381 |
Token | layers |
Token ID | 11685 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
theorem | +3.753 |
yss | +3.663 |
isoft | +3.541 |
rons | +3.506 |
ramid | +3.492 |
Neg logit contributions | |
>>>>>>>> | -3.302 |
Eisenhower | -2.813 |
selves | -2.791 |
Chavez | -2.715 |
agers | -2.680 |
Token | of |
Token ID | 286 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
theorem | +1.100 |
yss | +1.097 |
isoft | +1.064 |
ramid | +1.039 |
�� | +1.023 |
Neg logit contributions | |
>>>>>>>> | -1.220 |
Eisenhower | -1.072 |
selves | -1.050 |
Chavez | -1.041 |
agers | -1.023 |
Token | zinc |
Token ID | 31861 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
theorem | +2.636 |
yss | +2.596 |
isoft | +2.508 |
ramid | +2.469 |
rons | +2.447 |
Neg logit contributions | |
>>>>>>>> | -2.788 |
Eisenhower | -2.416 |
selves | -2.382 |
Chavez | -2.344 |
agers | -2.309 |
Token | , |
Token ID | 11 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
theorem | +7.975 |
yss | +7.616 |
rons | +7.562 |
ramid | +7.423 |
isoft | +7.194 |
Neg logit contributions | |
>>>>>>>> | -10.537 |
Eisenhower | -9.123 |
selves | -9.036 |
Chavez | -8.863 |
WithNo | -8.781 |
Token | br |
Token ID | 865 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
theorem | +3.522 |
yss | +3.467 |
isoft | +3.347 |
ramid | +3.296 |
rons | +3.267 |
Neg logit contributions | |
>>>>>>>> | -3.841 |
Eisenhower | -3.337 |
selves | -3.293 |
Chavez | -3.240 |
agers | -3.190 |
Token | ine |
Token ID | 500 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
>>>>>>>> | +1.720 |
Eisenhower | +1.475 |
selves | +1.440 |
ances | +1.439 |
Chavez | +1.424 |
Neg logit contributions | |
theorem | -2.145 |
yss | -2.067 |
�� | -2.048 |
isoft | -2.029 |
ramid | -1.976 |
Token | - |
Token ID | 12 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
theorem | +0.466 |
yss | +0.462 |
isoft | +0.450 |
ramid | +0.442 |
�� | +0.439 |
Neg logit contributions | |
>>>>>>>> | -0.392 |
Eisenhower | -0.336 |
selves | -0.328 |
Chavez | -0.324 |
ances | -0.317 |
Token | so |
Token ID | 568 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
>>>>>>>> | +0.381 |
selves | +0.335 |
Eisenhower | +0.335 |
Chavez | +0.323 |
agers | +0.323 |
Neg logit contributions | |
theorem | -0.368 |
yss | -0.365 |
isoft | -0.351 |
�� | -0.347 |
ramid | -0.342 |
Token | lead |
Token ID | 1085 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
theorem | +2.942 |
yss | +2.907 |
isoft | +2.825 |
ramid | +2.775 |
rons | +2.750 |
Neg logit contributions | |
>>>>>>>> | -2.617 |
Eisenhower | -2.248 |
selves | -2.213 |
Chavez | -2.171 |
agers | -2.132 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
theorem | +4.159 |
yss | +4.085 |
isoft | +3.955 |
ramid | +3.893 |
rons | +3.856 |
Neg logit contributions | |
>>>>>>>> | -4.253 |
Eisenhower | -3.696 |
selves | -3.650 |
Chavez | -3.564 |
agers | -3.512 |
Token | ind |
Token ID | 773 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
theorem | +1.243 |
yss | +1.236 |
isoft | +1.200 |
ramid | +1.178 |
�� | +1.168 |
Neg logit contributions | |
>>>>>>>> | -1.134 |
Eisenhower | -0.982 |
selves | -0.958 |
Chavez | -0.949 |
agers | -0.931 |
Token | ium |
Token ID | 1505 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
>>>>>>>> | +2.162 |
Eisenhower | +1.979 |
agers | +1.956 |
selves | +1.952 |
ager | +1.940 |
Neg logit contributions | |
theorem | -1.271 |
�� | -1.251 |
yss | -1.223 |
isoft | -1.200 |
ramid | -1.127 |
Token | and |
Token ID | 290 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
theorem | +2.307 |
yss | +2.285 |
isoft | +2.217 |
ramid | +2.177 |
rons | +2.148 |
Neg logit contributions | |
>>>>>>>> | -2.197 |
Eisenhower | -1.903 |
selves | -1.865 |
Chavez | -1.840 |
agers | -1.808 |
Token | zinc |
Token ID | 31861 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
theorem | +2.404 |
yss | +2.379 |
isoft | +2.307 |
ramid | +2.266 |
rons | +2.238 |
Neg logit contributions | |
>>>>>>>> | -2.319 |
Eisenhower | -2.009 |
selves | -1.971 |
Chavez | -1.943 |
agers | -1.910 |
Token | and |
Token ID | 290 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
theorem | +8.306 |
yss | +7.996 |
isoft | +7.836 |
rons | +7.782 |
ramid | +7.701 |
Neg logit contributions | |
>>>>>>>> | -9.562 |
Eisenhower | -8.393 |
selves | -8.356 |
Chavez | -8.071 |
WithNo | -8.002 |
Token | other |
Token ID | 584 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
theorem | +3.503 |
yss | +3.467 |
isoft | +3.355 |
ramid | +3.306 |
rons | +3.281 |
Neg logit contributions | |
>>>>>>>> | -3.208 |
Eisenhower | -2.762 |
selves | -2.719 |
Chavez | -2.667 |
agers | -2.619 |
Token | metals |
Token ID | 21782 |
Feature activation | -6.65e+00 |
Pos logit contributions | |
theorem | +3.344 |
yss | +3.301 |
isoft | +3.200 |
ramid | +3.145 |
rons | +3.121 |
Neg logit contributions | |
>>>>>>>> | -3.324 |
Eisenhower | -2.885 |
selves | -2.838 |
Chavez | -2.794 |
agers | -2.736 |
Token | . |
Token ID | 13 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
theorem | +5.074 |
yss | +4.977 |
isoft | +4.840 |
ramid | +4.744 |
rons | +4.730 |
Neg logit contributions | |
>>>>>>>> | -5.287 |
Eisenhower | -4.572 |
selves | -4.504 |
Chavez | -4.414 |
agers | -4.349 |
Token |
|
Token ID | 198 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
>>>>>>>> | +0.416 |
Eisenhower | +0.354 |
selves | +0.345 |
Chavez | +0.342 |
agers | +0.331 |
Neg logit contributions | |
theorem | -0.556 |
yss | -0.552 |
isoft | -0.536 |
ramid | -0.527 |
�� | -0.524 |
Token | Hon |
Token ID | 8835 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
theorem | +3.514 |
yss | +3.465 |
isoft | +3.353 |
ramid | +3.292 |
rons | +3.265 |
Neg logit contributions | |
>>>>>>>> | -3.179 |
Eisenhower | -2.714 |
selves | -2.681 |
Chavez | -2.622 |
agers | -2.598 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
theorem | +4.638 |
yss | +4.608 |
isoft | +4.426 |
ramid | +4.341 |
rons | +4.330 |
Neg logit contributions | |
>>>>>>>> | -5.022 |
selves | -4.305 |
Eisenhower | -4.291 |
Chavez | -4.177 |
agers | -4.093 |
Token | Transport |
Token ID | 19940 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
theorem | +1.530 |
yss | +1.516 |
isoft | +1.475 |
ramid | +1.450 |
�� | +1.430 |
Neg logit contributions | |
>>>>>>>> | -1.383 |
Eisenhower | -1.197 |
selves | -1.168 |
Chavez | -1.157 |
agers | -1.131 |
Token | Minister |
Token ID | 4139 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
theorem | +0.932 |
yss | +0.922 |
isoft | +0.896 |
ramid | +0.882 |
�� | +0.871 |
Neg logit contributions | |
>>>>>>>> | -0.817 |
Eisenhower | -0.709 |
selves | -0.691 |
Chavez | -0.684 |
agers | -0.669 |
Token | of |
Token ID | 286 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
theorem | +1.798 |
yss | +1.782 |
isoft | +1.731 |
ramid | +1.702 |
�� | +1.681 |
Neg logit contributions | |
>>>>>>>> | -1.637 |
Eisenhower | -1.416 |
selves | -1.385 |
Chavez | -1.370 |
agers | -1.343 |
Token | Raj |
Token ID | 13308 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
theorem | +1.554 |
yss | +1.542 |
isoft | +1.498 |
ramid | +1.475 |
�� | +1.458 |
Neg logit contributions | |
>>>>>>>> | -1.224 |
Eisenhower | -1.049 |
selves | -1.022 |
Chavez | -1.010 |
agers | -0.986 |
Token | as |
Token ID | 292 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
yss | +9.862 |
isoft | +9.557 |
theorem | +9.311 |
omi | +9.197 |
ramid | +9.050 |
Neg logit contributions | |
>>>>>>>> | -8.494 |
selves | -7.175 |
Eisenhower | -6.883 |
א | -6.869 |
VICE | -6.847 |
Token | than |
Token ID | 14813 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
>>>>>>>> | +1.432 |
Eisenhower | +1.181 |
selves | +1.160 |
Chavez | +1.128 |
ances | +1.124 |
Neg logit contributions | |
yss | -2.139 |
theorem | -2.126 |
isoft | -2.060 |
�� | -2.045 |
rons | -2.021 |
Token | held |
Token ID | 2714 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
>>>>>>>> | +0.692 |
Eisenhower | +0.597 |
Chavez | +0.577 |
selves | +0.576 |
agers | +0.556 |
Neg logit contributions | |
yss | -0.835 |
theorem | -0.833 |
isoft | -0.803 |
�� | -0.796 |
ramid | -0.795 |
Token | three |
Token ID | 1115 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
>>>>>>>> | +0.157 |
Eisenhower | +0.137 |
selves | +0.133 |
Chavez | +0.132 |
agers | +0.129 |
Neg logit contributions | |
theorem | -0.178 |
yss | -0.177 |
isoft | -0.172 |
ramid | -0.169 |
�� | -0.167 |
Token | meetings |
Token ID | 8292 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
theorem | +2.078 |
yss | +2.058 |
isoft | +1.998 |
ramid | +1.963 |
rons | +1.938 |
Neg logit contributions | |
>>>>>>>> | -1.864 |
Eisenhower | -1.605 |
selves | -1.573 |
Chavez | -1.551 |
agers | -1.523 |
Token | days |
Token ID | 1528 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
theorem | +4.786 |
yss | +4.682 |
isoft | +4.510 |
rons | +4.450 |
ramid | +4.436 |
Neg logit contributions | |
>>>>>>>> | -4.119 |
Eisenhower | -3.509 |
selves | -3.483 |
Chavez | -3.417 |
agers | -3.335 |
Token | has |
Token ID | 468 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
theorem | +1.772 |
yss | +1.757 |
isoft | +1.702 |
ramid | +1.672 |
�� | +1.649 |
Neg logit contributions | |
>>>>>>>> | -1.836 |
Eisenhower | -1.602 |
selves | -1.569 |
Chavez | -1.551 |
agers | -1.524 |
Token | passed |
Token ID | 3804 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
theorem | +2.366 |
yss | +2.320 |
isoft | +2.213 |
ramid | +2.155 |
rons | +2.126 |
Neg logit contributions | |
>>>>>>>> | -4.558 |
Eisenhower | -4.093 |
selves | -4.051 |
Chavez | -4.000 |
agers | -3.957 |
Token | since |
Token ID | 1201 |
Feature activation | -8.64e+00 |
Pos logit contributions | |
theorem | +3.009 |
yss | +2.967 |
isoft | +2.822 |
ramid | +2.740 |
rons | +2.702 |
Neg logit contributions | |
>>>>>>>> | -5.600 |
Eisenhower | -5.035 |
selves | -4.973 |
Chavez | -4.914 |
agers | -4.854 |
Token | the |
Token ID | 262 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
theorem | +6.395 |
yss | +6.166 |
isoft | +5.930 |
rons | +5.884 |
ramid | +5.836 |
Neg logit contributions | |
>>>>>>>> | -7.044 |
selves | -6.128 |
Eisenhower | -6.068 |
Chavez | -5.892 |
ances | -5.855 |
Token | last |
Token ID | 938 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
yss | +1.100 |
theorem | +1.092 |
isoft | +1.068 |
�� | +1.049 |
ramid | +1.045 |
Neg logit contributions | |
>>>>>>>> | -1.354 |
Eisenhower | -1.198 |
selves | -1.162 |
Chavez | -1.161 |
agers | -1.138 |
Token | read |
Token ID | 1100 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
theorem | +7.798 |
yss | +7.216 |
isoft | +6.871 |
rons | +6.809 |
ramid | +6.709 |
Neg logit contributions | |
>>>>>>>> | -10.174 |
selves | -9.076 |
Eisenhower | -8.922 |
WithNo | -8.788 |
Chavez | -8.727 |
Token | / |
Token ID | 14 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
theorem | +2.782 |
yss | +2.746 |
isoft | +2.658 |
ramid | +2.608 |
rons | +2.571 |
Neg logit contributions | |
>>>>>>>> | -3.094 |
Eisenhower | -2.712 |
selves | -2.668 |
Chavez | -2.631 |
agers | -2.589 |
Token | update |
Token ID | 19119 |
Feature activation | -7.13e+00 |
Pos logit contributions | |
theorem | +0.755 |
yss | +0.742 |
isoft | +0.711 |
ramid | +0.695 |
�� | +0.691 |
Neg logit contributions | |
>>>>>>>> | -1.285 |
Eisenhower | -1.147 |
selves | -1.135 |
Chavez | -1.116 |
agers | -1.111 |
Token | and |
Token ID | 290 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
theorem | +5.343 |
yss | +5.210 |
isoft | +5.037 |
ramid | +4.937 |
rons | +4.909 |
Neg logit contributions | |
>>>>>>>> | -5.779 |
Eisenhower | -5.052 |
selves | -5.046 |
Chavez | -4.905 |
agers | -4.860 |
Token | shift |
Token ID | 6482 |
Feature activation | -5.64e+00 |
Pos logit contributions | |
theorem | +2.047 |
yss | +2.028 |
isoft | +1.963 |
ramid | +1.925 |
�� | +1.902 |
Neg logit contributions | |
>>>>>>>> | -2.227 |
Eisenhower | -1.947 |
selves | -1.910 |
Chavez | -1.889 |
agers | -1.857 |
Token | saved |
Token ID | 7448 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
theorem | +2.536 |
yss | +2.512 |
isoft | +2.441 |
ramid | +2.399 |
rons | +2.373 |
Neg logit contributions | |
>>>>>>>> | -2.081 |
Eisenhower | -1.776 |
selves | -1.742 |
Chavez | -1.713 |
agers | -1.681 |
Token | the |
Token ID | 262 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
theorem | +0.693 |
yss | +0.691 |
isoft | +0.673 |
�� | +0.666 |
ramid | +0.666 |
Neg logit contributions | |
>>>>>>>> | -0.453 |
Eisenhower | -0.379 |
selves | -0.369 |
Chavez | -0.363 |
agers | -0.356 |
Token | timestamp |
Token ID | 41033 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
>>>>>>>> | +0.158 |
Eisenhower | +0.140 |
selves | +0.135 |
Chavez | +0.135 |
agers | +0.132 |
Neg logit contributions | |
yss | -0.139 |
theorem | -0.137 |
�� | -0.134 |
isoft | -0.134 |
ramid | -0.132 |
Token | of |
Token ID | 286 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
theorem | +5.263 |
yss | +5.113 |
isoft | +4.930 |
rons | +4.822 |
ramid | +4.806 |
Neg logit contributions | |
>>>>>>>> | -6.022 |
Eisenhower | -5.263 |
selves | -5.199 |
Chavez | -5.111 |
agers | -5.037 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
theorem | +2.086 |
yss | +2.071 |
isoft | +2.008 |
ramid | +1.972 |
�� | +1.952 |
Neg logit contributions | |
>>>>>>>> | -2.005 |
Eisenhower | -1.739 |
selves | -1.702 |
Chavez | -1.683 |
agers | -1.653 |
Token | last |
Token ID | 938 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
yss | +1.052 |
theorem | +1.043 |
isoft | +1.019 |
�� | +1.007 |
ramid | +0.996 |
Neg logit contributions | |
>>>>>>>> | -1.142 |
Eisenhower | -1.004 |
Chavez | -0.973 |
selves | -0.973 |
agers | -0.951 |
Token | time |
Token ID | 640 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
theorem | +8.479 |
yss | +7.922 |
isoft | +7.691 |
ramid | +7.565 |
rons | +7.508 |
Neg logit contributions | |
>>>>>>>> | -9.405 |
selves | -8.326 |
Eisenhower | -8.131 |
WithNo | -7.954 |
agers | -7.951 |
Token | a |
Token ID | 257 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
theorem | +2.930 |
yss | +2.897 |
isoft | +2.811 |
ramid | +2.759 |
rons | +2.724 |
Neg logit contributions | |
>>>>>>>> | -2.816 |
Eisenhower | -2.437 |
selves | -2.394 |
Chavez | -2.358 |
agers | -2.318 |
Token | users |
Token ID | 2985 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
>>>>>>>> | +0.540 |
Eisenhower | +0.481 |
Chavez | +0.470 |
selves | +0.466 |
agers | +0.457 |
Neg logit contributions | |
yss | -0.386 |
theorem | -0.379 |
�� | -0.373 |
isoft | -0.372 |
ramid | -0.365 |
Token | point |
Token ID | 966 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
yss | +0.863 |
theorem | +0.862 |
isoft | +0.824 |
ramid | +0.813 |
�� | +0.812 |
Neg logit contributions | |
>>>>>>>> | -1.033 |
Eisenhower | -0.910 |
selves | -0.891 |
Chavez | -0.882 |
agers | -0.868 |
Token | - |
Token ID | 12 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
yss | +0.832 |
theorem | +0.831 |
isoft | +0.805 |
�� | +0.793 |
ramid | +0.791 |
Neg logit contributions | |
>>>>>>>> | -0.704 |
Eisenhower | -0.606 |
selves | -0.589 |
Chavez | -0.583 |
agers | -0.573 |
Token | even |
Token ID | 772 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
>>>>>>>> | +3.732 |
Eisenhower | +3.302 |
Chavez | +3.186 |
selves | +3.178 |
ances | +3.105 |
Neg logit contributions | |
�� | -4.913 |
yss | -4.880 |
theorem | -4.817 |
isoft | -4.734 |
ramid | -4.726 |
Token | more |
Token ID | 517 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
>>>>>>>> | +1.232 |
Eisenhower | +1.058 |
selves | +1.025 |
Chavez | +1.021 |
agers | +0.994 |
Neg logit contributions | |
yss | -1.807 |
theorem | -1.801 |
isoft | -1.759 |
�� | -1.744 |
ramid | -1.735 |
Token | fun |
Token ID | 1257 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
>>>>>>>> | +4.100 |
Eisenhower | +3.527 |
Chavez | +3.405 |
selves | +3.355 |
ances | +3.304 |
Neg logit contributions | |
�� | -6.326 |
yss | -6.246 |
ramid | -6.213 |
isoft | -6.190 |
theorem | -6.111 |
Token | ," |
Token ID | 553 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
>>>>>>>> | +2.451 |
Eisenhower | +2.100 |
selves | +2.063 |
Chavez | +2.040 |
ances | +2.000 |
Neg logit contributions | |
yss | -3.191 |
theorem | -3.185 |
isoft | -3.160 |
�� | -3.155 |
ramid | -3.089 |
Token | said |
Token ID | 531 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
theorem | +2.548 |
yss | +2.532 |
isoft | +2.448 |
ramid | +2.402 |
rons | +2.382 |
Neg logit contributions | |
>>>>>>>> | -1.933 |
Eisenhower | -1.622 |
selves | -1.600 |
Chavez | -1.561 |
agers | -1.539 |
Token | Raj |
Token ID | 13308 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
theorem | +3.439 |
yss | +3.414 |
isoft | +3.282 |
ramid | +3.223 |
rons | +3.208 |
Neg logit contributions | |
>>>>>>>> | -2.695 |
Eisenhower | -2.238 |
selves | -2.232 |
Chavez | -2.152 |
agers | -2.152 |
Token | N |
Token ID | 399 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
yss | +9.349 |
isoft | +8.998 |
theorem | +8.975 |
rons | +8.706 |
omi | +8.654 |
Neg logit contributions | |
>>>>>>>> | -8.732 |
selves | -7.126 |
Eisenhower | -7.015 |
א | -6.992 |
WithNo | -6.952 |
Token | air |
Token ID | 958 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
theorem | +0.860 |
yss | +0.846 |
isoft | +0.821 |
ramid | +0.809 |
�� | +0.804 |
Neg logit contributions | |
>>>>>>>> | -0.801 |
Eisenhower | -0.701 |
selves | -0.686 |
Chavez | -0.676 |
agers | -0.670 |
Token | , |
Token ID | 11 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
theorem | +1.703 |
yss | +1.691 |
isoft | +1.639 |
ramid | +1.610 |
rons | +1.590 |
Neg logit contributions | |
>>>>>>>> | -1.542 |
Eisenhower | -1.327 |
selves | -1.303 |
Chavez | -1.281 |
agers | -1.259 |
Token | Ford |
Token ID | 8092 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
theorem | +1.511 |
yss | +1.499 |
isoft | +1.461 |
ramid | +1.438 |
rons | +1.422 |
Neg logit contributions | |
>>>>>>>> | -0.992 |
Eisenhower | -0.827 |
selves | -0.807 |
Chavez | -0.793 |
agers | -0.775 |
Token | group |
Token ID | 1448 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
theorem | +0.356 |
yss | +0.352 |
isoft | +0.343 |
ramid | +0.338 |
�� | +0.335 |
Neg logit contributions | |
>>>>>>>> | -0.293 |
Eisenhower | -0.252 |
selves | -0.246 |
Chavez | -0.243 |
agers | -0.238 |
Token | Devon |
Token ID | 36889 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
>>>>>>>> | +0.640 |
Eisenhower | +0.553 |
selves | +0.533 |
Chavez | +0.529 |
agers | +0.517 |
Neg logit contributions | |
theorem | -0.849 |
yss | -0.845 |
isoft | -0.820 |
�� | -0.809 |
ramid | -0.803 |
Token | Energy |
Token ID | 6682 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
>>>>>>>> | +0.867 |
Eisenhower | +0.748 |
selves | +0.732 |
Chavez | +0.722 |
ances | +0.708 |
Neg logit contributions | |
theorem | -1.034 |
yss | -1.021 |
isoft | -0.987 |
�� | -0.974 |
ramid | -0.973 |
Token | . |
Token ID | 13 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
theorem | +1.741 |
yss | +1.724 |
isoft | +1.672 |
ramid | +1.642 |
rons | +1.621 |
Neg logit contributions | |
>>>>>>>> | -1.712 |
Eisenhower | -1.486 |
selves | -1.457 |
Chavez | -1.438 |
agers | -1.413 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
>>>>>>>> | +0.273 |
Eisenhower | +0.235 |
selves | +0.226 |
Chavez | +0.226 |
ances | +0.217 |
Neg logit contributions | |
theorem | -0.361 |
yss | -0.359 |
isoft | -0.348 |
ramid | -0.341 |
�� | -0.341 |
Token |
|
Token ID | 198 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
theorem | +0.099 |
yss | +0.098 |
isoft | +0.095 |
ramid | +0.094 |
�� | +0.093 |
Neg logit contributions | |
>>>>>>>> | -0.076 |
Eisenhower | -0.064 |
selves | -0.063 |
Chavez | -0.062 |
agers | -0.060 |
Token | Last |
Token ID | 5956 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
theorem | +0.367 |
yss | +0.362 |
isoft | +0.351 |
�� | +0.344 |
ramid | +0.344 |
Neg logit contributions | |
>>>>>>>> | -0.336 |
Eisenhower | -0.288 |
selves | -0.281 |
Chavez | -0.277 |
agers | -0.273 |
Token | year |
Token ID | 614 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
theorem | +7.462 |
yss | +7.275 |
isoft | +6.784 |
rons | +6.733 |
omi | +6.732 |
Neg logit contributions | |
>>>>>>>> | -10.264 |
selves | -8.993 |
Eisenhower | -8.870 |
agers | -8.713 |
Chavez | -8.618 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
theorem | +2.890 |
yss | +2.865 |
isoft | +2.774 |
ramid | +2.730 |
rons | +2.722 |
Neg logit contributions | |
>>>>>>>> | -2.672 |
Eisenhower | -2.303 |
selves | -2.295 |
Chavez | -2.213 |
agers | -2.212 |
Token | Pruitt |
Token ID | 39637 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
theorem | +1.290 |
yss | +1.277 |
isoft | +1.243 |
ramid | +1.223 |
�� | +1.214 |
Neg logit contributions | |
>>>>>>>> | -1.043 |
Eisenhower | -0.895 |
selves | -0.865 |
Chavez | -0.864 |
agers | -0.838 |
Token | orchestrated |
Token ID | 37728 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
theorem | +0.452 |
yss | +0.446 |
isoft | +0.433 |
ramid | +0.426 |
�� | +0.424 |
Neg logit contributions | |
>>>>>>>> | -0.435 |
Eisenhower | -0.377 |
selves | -0.368 |
Chavez | -0.365 |
ances | -0.358 |
Token | an |
Token ID | 281 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
theorem | +2.479 |
yss | +2.463 |
isoft | +2.382 |
ramid | +2.345 |
rons | +2.319 |
Neg logit contributions | |
>>>>>>>> | -2.248 |
Eisenhower | -1.934 |
selves | -1.910 |
Chavez | -1.866 |
agers | -1.838 |
Token | Perry |
Token ID | 14105 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
theorem | +0.807 |
yss | +0.799 |
isoft | +0.778 |
ramid | +0.765 |
�� | +0.755 |
Neg logit contributions | |
>>>>>>>> | -0.666 |
Eisenhower | -0.570 |
selves | -0.558 |
Chavez | -0.551 |
agers | -0.538 |
Token | added |
Token ID | 2087 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
theorem | +0.756 |
yss | +0.750 |
isoft | +0.727 |
ramid | +0.715 |
rons | +0.706 |
Neg logit contributions | |
>>>>>>>> | -0.657 |
Eisenhower | -0.566 |
selves | -0.553 |
Chavez | -0.545 |
agers | -0.535 |
Token | . |
Token ID | 13 |
Feature activation | +9.30e-03 |
Pos logit contributions | |
>>>>>>>> | +0.528 |
Eisenhower | +0.460 |
selves | +0.452 |
Chavez | +0.446 |
agers | +0.439 |
Neg logit contributions | |
theorem | -0.507 |
yss | -0.502 |
isoft | -0.485 |
ramid | -0.476 |
rons | -0.470 |
Token |
|
Token ID | 198 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
>>>>>>>> | +0.006 |
Eisenhower | +0.005 |
selves | +0.005 |
Chavez | +0.005 |
agers | +0.005 |
Neg logit contributions | |
theorem | -0.008 |
yss | -0.008 |
isoft | -0.008 |
ramid | -0.008 |
rons | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
>>>>>>>> | +0.140 |
Eisenhower | +0.119 |
selves | +0.116 |
Chavez | +0.114 |
agers | +0.112 |
Neg logit contributions | |
theorem | -0.185 |
yss | -0.183 |
isoft | -0.178 |
ramid | -0.175 |
�� | -0.174 |
Token | Last |
Token ID | 5956 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
theorem | +0.095 |
yss | +0.094 |
isoft | +0.091 |
ramid | +0.090 |
�� | +0.090 |
Neg logit contributions | |
>>>>>>>> | -0.087 |
Eisenhower | -0.074 |
selves | -0.073 |
Chavez | -0.072 |
א | -0.070 |
Token | month |
Token ID | 1227 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
theorem | +7.765 |
yss | +7.618 |
isoft | +7.217 |
rons | +7.032 |
ramid | +7.031 |
Neg logit contributions | |
>>>>>>>> | -10.076 |
selves | -8.757 |
Eisenhower | -8.725 |
agers | -8.553 |
Chavez | -8.409 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
theorem | +3.018 |
yss | +2.990 |
isoft | +2.893 |
ramid | +2.840 |
rons | +2.819 |
Neg logit contributions | |
>>>>>>>> | -2.732 |
Eisenhower | -2.364 |
selves | -2.331 |
Chavez | -2.266 |
agers | -2.262 |
Token | Breitbart |
Token ID | 19923 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
theorem | +1.269 |
yss | +1.257 |
isoft | +1.223 |
ramid | +1.203 |
�� | +1.189 |
Neg logit contributions | |
>>>>>>>> | -1.075 |
Eisenhower | -0.921 |
selves | -0.899 |
Chavez | -0.890 |
agers | -0.869 |
Token | Jerusalem |
Token ID | 10843 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
>>>>>>>> | +0.284 |
Eisenhower | +0.239 |
Chavez | +0.234 |
selves | +0.230 |
א | +0.225 |
Neg logit contributions | |
theorem | -0.429 |
yss | -0.424 |
isoft | -0.412 |
�� | -0.412 |
ramid | -0.409 |
Token | reported |
Token ID | 2098 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
>>>>>>>> | +1.926 |
Eisenhower | +1.696 |
Chavez | +1.696 |
selves | +1.678 |
א | +1.653 |
Neg logit contributions | |
theorem | -1.388 |
yss | -1.386 |
�� | -1.321 |
ramid | -1.320 |
isoft | -1.309 |
Token | owned |
Token ID | 11990 |
Feature activation | -7.28e+00 |
Pos logit contributions | |
theorem | +2.125 |
yss | +2.106 |
isoft | +2.046 |
ramid | +2.010 |
rons | +1.987 |
Neg logit contributions | |
>>>>>>>> | -1.880 |
Eisenhower | -1.618 |
selves | -1.581 |
Chavez | -1.563 |
agers | -1.529 |
Token | data |
Token ID | 1366 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
theorem | +5.404 |
yss | +5.259 |
isoft | +5.015 |
rons | +4.944 |
ramid | +4.942 |
Neg logit contributions | |
>>>>>>>> | -5.923 |
Eisenhower | -5.258 |
Chavez | -5.083 |
selves | -5.078 |
א | -4.995 |
Token | that |
Token ID | 326 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
theorem | +3.253 |
yss | +3.199 |
isoft | +3.092 |
ramid | +3.033 |
rons | +3.007 |
Neg logit contributions | |
>>>>>>>> | -3.736 |
Eisenhower | -3.284 |
selves | -3.215 |
Chavez | -3.189 |
agers | -3.136 |
Token | has |
Token ID | 468 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
theorem | +2.036 |
yss | +2.011 |
isoft | +1.956 |
ramid | +1.925 |
rons | +1.905 |
Neg logit contributions | |
>>>>>>>> | -1.569 |
Eisenhower | -1.334 |
selves | -1.302 |
Chavez | -1.282 |
agers | -1.258 |
Token | not |
Token ID | 407 |
Feature activation | -8.52e+00 |
Pos logit contributions | |
theorem | +4.055 |
yss | +3.972 |
isoft | +3.816 |
ramid | +3.761 |
rons | +3.758 |
Neg logit contributions | |
>>>>>>>> | -4.615 |
Eisenhower | -4.068 |
selves | -3.976 |
Chavez | -3.943 |
agers | -3.871 |
Token | yet |
Token ID | 1865 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
theorem | +4.516 |
yss | +4.404 |
isoft | +4.215 |
rons | +4.166 |
ramid | +4.089 |
Neg logit contributions | |
>>>>>>>> | -8.506 |
Eisenhower | -7.674 |
Chavez | -7.461 |
selves | -7.412 |
agers | -7.352 |
Token | been |
Token ID | 587 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
theorem | +5.454 |
yss | +5.377 |
isoft | +5.035 |
rons | +5.014 |
ramid | +4.857 |
Neg logit contributions | |
>>>>>>>> | -11.635 |
Eisenhower | -10.594 |
WithNo | -10.456 |
utic | -10.415 |
Chavez | -10.278 |
Token | published |
Token ID | 3199 |
Feature activation | -7.96e+00 |
Pos logit contributions | |
theorem | +7.458 |
yss | +7.171 |
isoft | +6.864 |
rons | +6.758 |
ramid | +6.652 |
Neg logit contributions | |
>>>>>>>> | -9.094 |
Eisenhower | -8.135 |
WithNo | -7.887 |
agers | -7.831 |
Chavez | -7.805 |
Token | in |
Token ID | 287 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
theorem | +5.986 |
yss | +5.860 |
isoft | +5.651 |
rons | +5.514 |
ramid | +5.482 |
Neg logit contributions | |
>>>>>>>> | -6.449 |
Eisenhower | -5.650 |
Chavez | -5.463 |
selves | -5.455 |
agers | -5.380 |
Token | a |
Token ID | 257 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
yss | +1.441 |
theorem | +1.439 |
isoft | +1.402 |
ramid | +1.378 |
�� | +1.358 |
Neg logit contributions | |
>>>>>>>> | -1.328 |
Eisenhower | -1.142 |
selves | -1.128 |
Chavez | -1.114 |
agers | -1.090 |
Token | concurrent |
Token ID | 24580 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
yss | +1.961 |
theorem | +1.959 |
isoft | +1.904 |
ramid | +1.868 |
rons | +1.838 |
Neg logit contributions | |
>>>>>>>> | -2.189 |
Eisenhower | -1.901 |
selves | -1.882 |
Chavez | -1.859 |
agers | -1.819 |
Token | I |
Token ID | 314 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
>>>>>>>> | +0.066 |
Eisenhower | +0.057 |
selves | +0.055 |
Chavez | +0.055 |
agers | +0.053 |
Neg logit contributions | |
theorem | -0.086 |
yss | -0.086 |
isoft | -0.084 |
ramid | -0.083 |
�� | -0.082 |
Token | can |
Token ID | 460 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
theorem | +2.974 |
yss | +2.932 |
isoft | +2.854 |
ramid | +2.806 |
rons | +2.788 |
Neg logit contributions | |
>>>>>>>> | -2.349 |
Eisenhower | -1.997 |
selves | -1.956 |
Chavez | -1.921 |
agers | -1.885 |
Token | cite |
Token ID | 21729 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
>>>>>>>> | +1.406 |
Eisenhower | +1.202 |
selves | +1.154 |
Chavez | +1.152 |
agers | +1.145 |
Neg logit contributions | |
yss | -1.701 |
theorem | -1.639 |
isoft | -1.638 |
�� | -1.624 |
ramid | -1.610 |
Token | about |
Token ID | 546 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
theorem | +1.208 |
yss | +1.201 |
isoft | +1.168 |
ramid | +1.149 |
�� | +1.134 |
Neg logit contributions | |
>>>>>>>> | -1.215 |
Eisenhower | -1.058 |
selves | -1.036 |
Chavez | -1.024 |
ances | -0.999 |
Token | my |
Token ID | 616 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
theorem | +0.579 |
yss | +0.575 |
isoft | +0.559 |
ramid | +0.551 |
�� | +0.544 |
Neg logit contributions | |
>>>>>>>> | -0.526 |
Eisenhower | -0.454 |
selves | -0.445 |
Chavez | -0.439 |
agers | -0.430 |
Token | previous |
Token ID | 2180 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
theorem | +2.410 |
yss | +2.381 |
isoft | +2.308 |
ramid | +2.265 |
rons | +2.237 |
Neg logit contributions | |
>>>>>>>> | -2.346 |
Eisenhower | -2.034 |
selves | -1.994 |
Chavez | -1.968 |
agers | -1.935 |
Token | post |
Token ID | 1281 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
theorem | +8.813 |
yss | +8.174 |
isoft | +7.851 |
rons | +7.833 |
ramid | +7.596 |
Neg logit contributions | |
>>>>>>>> | -8.829 |
Eisenhower | -7.584 |
selves | -7.495 |
agers | -7.360 |
Chavez | -7.302 |
Token | , |
Token ID | 11 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
theorem | +2.404 |
yss | +2.379 |
isoft | +2.304 |
ramid | +2.261 |
rons | +2.236 |
Neg logit contributions | |
>>>>>>>> | -2.318 |
Eisenhower | -2.009 |
selves | -1.970 |
Chavez | -1.944 |
agers | -1.912 |
Token | but |
Token ID | 475 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
theorem | +1.838 |
yss | +1.824 |
isoft | +1.771 |
ramid | +1.744 |
�� | +1.720 |
Neg logit contributions | |
>>>>>>>> | -1.717 |
Eisenhower | -1.486 |
selves | -1.455 |
Chavez | -1.436 |
agers | -1.403 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
theorem | +2.171 |
yss | +2.151 |
isoft | +2.087 |
ramid | +2.050 |
rons | +2.021 |
Neg logit contributions | |
>>>>>>>> | -2.064 |
Eisenhower | -1.787 |
selves | -1.751 |
Chavez | -1.729 |
agers | -1.697 |
Token | controversy |
Token ID | 10386 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
yss | +0.129 |
theorem | +0.128 |
isoft | +0.126 |
ramid | +0.123 |
�� | +0.122 |
Neg logit contributions | |
>>>>>>>> | -0.145 |
Eisenhower | -0.128 |
selves | -0.124 |
Chavez | -0.124 |
ances | -0.121 |
Token | / |
Token ID | 1220 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
theorem | +2.714 |
yss | +2.660 |
isoft | +2.555 |
ramid | +2.501 |
rons | +2.475 |
Neg logit contributions | |
>>>>>>>> | -3.823 |
Eisenhower | -3.389 |
selves | -3.350 |
Chavez | -3.310 |
agers | -3.269 |
Token | etc |
Token ID | 14784 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
theorem | +1.729 |
yss | +1.717 |
isoft | +1.658 |
ramid | +1.623 |
rons | +1.606 |
Neg logit contributions | |
>>>>>>>> | -1.903 |
Eisenhower | -1.666 |
selves | -1.631 |
Chavez | -1.621 |
agers | -1.589 |
Token | / |
Token ID | 14 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
theorem | +2.713 |
yss | +2.688 |
isoft | +2.602 |
ramid | +2.554 |
rons | +2.518 |
Neg logit contributions | |
>>>>>>>> | -3.307 |
Eisenhower | -2.929 |
selves | -2.868 |
Chavez | -2.840 |
agers | -2.796 |
Token | pm |
Token ID | 4426 |
Feature activation | -8.57e+00 |
Pos logit contributions | |
yss | +4.981 |
theorem | +4.913 |
isoft | +4.770 |
rons | +4.661 |
ramid | +4.644 |
Neg logit contributions | |
>>>>>>>> | -4.673 |
Eisenhower | -4.044 |
selves | -3.952 |
Chavez | -3.921 |
agers | -3.786 |
Token | / |
Token ID | 14 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
theorem | +5.383 |
yss | +5.360 |
isoft | +5.243 |
ramid | +5.122 |
omi | +5.037 |
Neg logit contributions | |
>>>>>>>> | -7.594 |
Eisenhower | -6.866 |
selves | -6.715 |
Chavez | -6.641 |
א | -6.496 |
Token | power |
Token ID | 6477 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
yss | +2.950 |
theorem | +2.947 |
isoft | +2.826 |
ramid | +2.752 |
rons | +2.742 |
Neg logit contributions | |
>>>>>>>> | -4.570 |
Eisenhower | -4.076 |
selves | -4.005 |
Chavez | -3.993 |
agers | -3.883 |
Token | . |
Token ID | 13 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
theorem | +6.981 |
isoft | +6.707 |
yss | +6.706 |
rons | +6.374 |
omi | +6.346 |
Neg logit contributions | |
>>>>>>>> | -10.164 |
selves | -9.040 |
Eisenhower | -8.998 |
Chavez | -8.740 |
א | -8.523 |
Token | d |
Token ID | 67 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
theorem | +2.980 |
yss | +2.971 |
isoft | +2.850 |
ramid | +2.790 |
rons | +2.749 |
Neg logit contributions | |
>>>>>>>> | -4.622 |
Eisenhower | -4.105 |
selves | -4.050 |
Chavez | -4.022 |
agers | -3.957 |
Token | / |
Token ID | 14 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
theorem | +0.097 |
yss | +0.096 |
isoft | +0.093 |
ramid | +0.091 |
�� | +0.090 |
Neg logit contributions | |
>>>>>>>> | -0.105 |
Eisenhower | -0.092 |
selves | -0.090 |
Chavez | -0.089 |
agers | -0.087 |
Token | wire |
Token ID | 21809 |
Feature activation | -7.01e+00 |
Pos logit contributions | |
theorem | +0.161 |
yss | +0.159 |
isoft | +0.154 |
ramid | +0.151 |
�� | +0.149 |
Neg logit contributions | |
>>>>>>>> | -0.177 |
Eisenhower | -0.156 |
selves | -0.152 |
Chavez | -0.150 |
agers | -0.148 |
Token | less |
Token ID | 1203 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
yss | +4.686 |
theorem | +4.603 |
isoft | +4.515 |
ramid | +4.437 |
rons | +4.370 |
Neg logit contributions | |
>>>>>>>> | -6.162 |
Eisenhower | -5.468 |
Chavez | -5.415 |
selves | -5.356 |
א | -5.208 |
Token | News |
Token ID | 9980 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
>>>>>>>> | +0.153 |
Eisenhower | +0.129 |
selves | +0.127 |
Chavez | +0.126 |
agers | +0.123 |
Neg logit contributions | |
theorem | -0.195 |
yss | -0.192 |
isoft | -0.186 |
ramid | -0.186 |
�� | -0.184 |
Token | recently |
Token ID | 2904 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
theorem | +3.225 |
yss | +3.188 |
isoft | +3.094 |
ramid | +3.033 |
rons | +3.004 |
Neg logit contributions | |
>>>>>>>> | -3.330 |
Eisenhower | -2.906 |
selves | -2.845 |
Chavez | -2.809 |
agers | -2.762 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
theorem | +2.501 |
yss | +2.474 |
isoft | +2.396 |
ramid | +2.350 |
rons | +2.327 |
Neg logit contributions | |
>>>>>>>> | -2.579 |
Eisenhower | -2.248 |
selves | -2.203 |
Chavez | -2.175 |
agers | -2.143 |
Token |
|
Token ID | 198 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
>>>>>>>> | +1.235 |
Eisenhower | +1.054 |
selves | +1.029 |
Chavez | +1.014 |
א | +0.978 |
Neg logit contributions | |
theorem | -1.647 |
yss | -1.633 |
isoft | -1.587 |
ramid | -1.573 |
�� | -1.560 |
Token |
|
Token ID | 198 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
>>>>>>>> | +0.086 |
Eisenhower | +0.073 |
selves | +0.071 |
Chavez | +0.070 |
agers | +0.068 |
Neg logit contributions | |
theorem | -0.114 |
yss | -0.113 |
isoft | -0.110 |
ramid | -0.108 |
�� | -0.107 |
Token | Last |
Token ID | 5956 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
theorem | +0.301 |
yss | +0.298 |
isoft | +0.289 |
ramid | +0.284 |
�� | +0.283 |
Neg logit contributions | |
>>>>>>>> | -0.268 |
Eisenhower | -0.229 |
selves | -0.225 |
Chavez | -0.220 |
agers | -0.217 |
Token | May |
Token ID | 1737 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
theorem | +7.754 |
yss | +7.440 |
isoft | +7.084 |
rons | +6.929 |
omi | +6.881 |
Neg logit contributions | |
>>>>>>>> | -9.962 |
selves | -8.676 |
Eisenhower | -8.673 |
agers | -8.433 |
Chavez | -8.393 |
Token | , |
Token ID | 11 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
>>>>>>>> | +0.059 |
Eisenhower | +0.051 |
selves | +0.049 |
Chavez | +0.049 |
agers | +0.048 |
Neg logit contributions | |
theorem | -0.070 |
yss | -0.070 |
isoft | -0.068 |
ramid | -0.067 |
�� | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
theorem | +0.187 |
yss | +0.185 |
isoft | +0.180 |
ramid | +0.178 |
�� | +0.176 |
Neg logit contributions | |
>>>>>>>> | -0.174 |
Eisenhower | -0.152 |
Chavez | -0.148 |
selves | -0.148 |
agers | -0.143 |
Token | UC |
Token ID | 14417 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
>>>>>>>> | +1.711 |
Eisenhower | +1.491 |
Chavez | +1.441 |
selves | +1.433 |
agers | +1.383 |
Neg logit contributions | |
yss | -2.110 |
theorem | -2.096 |
isoft | -2.044 |
�� | -2.023 |
ramid | -2.016 |
Token | I |
Token ID | 40 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
theorem | +2.249 |
yss | +2.228 |
isoft | +2.164 |
ramid | +2.127 |
rons | +2.105 |
Neg logit contributions | |
>>>>>>>> | -1.898 |
Eisenhower | -1.626 |
selves | -1.596 |
Chavez | -1.567 |
agers | -1.540 |
Token | friend |
Token ID | 1545 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
>>>>>>>> | +1.501 |
Eisenhower | +1.293 |
Chavez | +1.269 |
selves | +1.256 |
agers | +1.202 |
Neg logit contributions | |
yss | -1.713 |
theorem | -1.689 |
isoft | -1.668 |
ramid | -1.646 |
�� | -1.636 |
Token | clarified |
Token ID | 28464 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
>>>>>>>> | +3.089 |
Eisenhower | +2.769 |
Chavez | +2.685 |
ances | +2.626 |
selves | +2.606 |
Neg logit contributions | |
yss | -3.246 |
ramid | -3.193 |
theorem | -3.156 |
�� | -3.156 |
isoft | -3.136 |
Token | — |
Token ID | 960 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
>>>>>>>> | +1.373 |
Eisenhower | +1.187 |
selves | +1.149 |
Chavez | +1.147 |
ances | +1.126 |
Neg logit contributions | |
yss | -1.707 |
theorem | -1.698 |
isoft | -1.678 |
ramid | -1.655 |
�� | -1.639 |
Token | pr |
Token ID | 1050 |
Feature activation | +6.12e+00 |
Pos logit contributions | |
theorem | +0.060 |
yss | +0.060 |
isoft | +0.058 |
ramid | +0.058 |
�� | +0.057 |
Neg logit contributions | |
>>>>>>>> | -0.048 |
Eisenhower | -0.041 |
selves | -0.040 |
Chavez | -0.039 |
agers | -0.039 |
Token | ide |
Token ID | 485 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
>>>>>>>> | +4.372 |
selves | +3.827 |
ances | +3.760 |
Eisenhower | +3.745 |
ager | +3.706 |
Neg logit contributions | |
theorem | -5.085 |
�� | -4.882 |
yss | -4.871 |
ramid | -4.846 |
isoft | -4.819 |
Token | fully |
Token ID | 2759 |
Feature activation | +7.99e+00 |
Pos logit contributions | |
>>>>>>>> | +2.331 |
Eisenhower | +2.036 |
selves | +2.004 |
Chavez | +1.970 |
ances | +1.952 |
Neg logit contributions | |
yss | -2.349 |
theorem | -2.343 |
isoft | -2.289 |
ramid | -2.280 |
�� | -2.253 |
Token | and |
Token ID | 290 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
>>>>>>>> | +4.793 |
Eisenhower | +4.020 |
selves | +3.921 |
Chavez | +3.780 |
ances | +3.748 |
Neg logit contributions | |
yss | -7.405 |
ramid | -7.313 |
isoft | -7.293 |
theorem | -7.286 |
�� | -7.249 |
Token | unp |
Token ID | 8593 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
>>>>>>>> | +1.376 |
Eisenhower | +1.187 |
selves | +1.158 |
Chavez | +1.147 |
ances | +1.118 |
Neg logit contributions | |
yss | -1.605 |
theorem | -1.595 |
isoft | -1.575 |
ramid | -1.550 |
�� | -1.535 |
Token | rompt |
Token ID | 45700 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
>>>>>>>> | +3.458 |
selves | +3.021 |
agers | +2.980 |
Eisenhower | +2.966 |
ances | +2.934 |
Neg logit contributions | |
theorem | -4.643 |
�� | -4.554 |
yss | -4.486 |
isoft | -4.406 |
ramid | -4.374 |
Token | ed |
Token ID | 276 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
theorem | +0.014 |
yss | +0.014 |
isoft | +0.013 |
ramid | +0.013 |
�� | +0.013 |
Neg logit contributions | |
>>>>>>>> | -0.028 |
Eisenhower | -0.026 |
selves | -0.026 |
Chavez | -0.025 |
ances | -0.025 |
Token | — |
Token ID | 960 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
>>>>>>>> | +0.426 |
Eisenhower | +0.359 |
selves | +0.353 |
Chavez | +0.345 |
agers | +0.337 |
Neg logit contributions | |
theorem | -0.580 |
yss | -0.576 |
isoft | -0.561 |
ramid | -0.554 |
�� | -0.545 |
Token | red |
Token ID | 445 |
Feature activation | +9.71e-03 |
Pos logit contributions | |
>>>>>>>> | +2.693 |
Eisenhower | +2.278 |
selves | +2.252 |
agers | +2.196 |
ances | +2.187 |
Neg logit contributions | |
theorem | -4.136 |
�� | -4.041 |
yss | -4.004 |
isoft | -3.927 |
ramid | -3.752 |
Token | the |
Token ID | 262 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
>>>>>>>> | +0.007 |
Eisenhower | +0.006 |
selves | +0.006 |
Chavez | +0.006 |
agers | +0.006 |
Neg logit contributions | |
theorem | -0.008 |
yss | -0.008 |
isoft | -0.008 |
ramid | -0.008 |
�� | -0.008 |
Token | defending |
Token ID | 11749 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
>>>>>>>> | +1.470 |
Eisenhower | +1.276 |
selves | +1.230 |
Chavez | +1.209 |
agers | +1.189 |
Neg logit contributions | |
yss | -2.119 |
theorem | -2.106 |
isoft | -2.071 |
ramid | -2.032 |
�� | -2.018 |
Token | champion |
Token ID | 8783 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
>>>>>>>> | +3.818 |
Eisenhower | +3.436 |
selves | +3.299 |
Chavez | +3.298 |
agers | +3.175 |
Neg logit contributions | |
yss | -4.640 |
isoft | -4.532 |
theorem | -4.521 |
ramid | -4.399 |
�� | -4.344 |
Token | Eagles |
Token ID | 13785 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
>>>>>>>> | +2.627 |
Eisenhower | +2.282 |
selves | +2.162 |
Chavez | +2.137 |
agers | +2.125 |
Neg logit contributions | |
yss | -4.385 |
theorem | -4.338 |
isoft | -4.313 |
ramid | -4.230 |
�� | -4.207 |
Token | 35 |
Token ID | 3439 |
Feature activation | +8.67e+00 |
Pos logit contributions | |
>>>>>>>> | +1.171 |
Eisenhower | +1.022 |
selves | +1.008 |
Chavez | +0.982 |
agers | +0.980 |
Neg logit contributions | |
yss | -1.236 |
theorem | -1.234 |
isoft | -1.202 |
ramid | -1.182 |
�� | -1.175 |
Token | - |
Token ID | 12 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
>>>>>>>> | +4.537 |
Eisenhower | +3.649 |
ances | +3.537 |
selves | +3.513 |
א | +3.493 |
Neg logit contributions | |
yss | -8.603 |
theorem | -8.526 |
isoft | -8.482 |
�� | -8.481 |
ramid | -8.420 |
Token | 10 |
Token ID | 940 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
>>>>>>>> | +2.165 |
Eisenhower | +1.800 |
selves | +1.757 |
ances | +1.699 |
ager | +1.697 |
Neg logit contributions | |
theorem | -3.055 |
yss | -3.001 |
�� | -2.969 |
isoft | -2.891 |
ramid | -2.885 |
Token | behind |
Token ID | 2157 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
>>>>>>>> | +4.447 |
Eisenhower | +3.833 |
selves | +3.789 |
Chavez | +3.695 |
ances | +3.652 |
Neg logit contributions | |
yss | -5.268 |
theorem | -5.245 |
isoft | -5.241 |
ramid | -5.134 |
�� | -5.116 |
Token | Graham |
Token ID | 11520 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
>>>>>>>> | +0.589 |
Eisenhower | +0.511 |
selves | +0.496 |
Chavez | +0.491 |
agers | +0.479 |
Neg logit contributions | |
theorem | -0.683 |
yss | -0.681 |
isoft | -0.662 |
ramid | -0.648 |
�� | -0.639 |
Token | � |
Token ID | 447 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
theorem | +0.020 |
yss | +0.020 |
isoft | +0.020 |
ramid | +0.019 |
�� | +0.019 |
Neg logit contributions | |
>>>>>>>> | -0.017 |
Eisenhower | -0.015 |
selves | -0.014 |
Chavez | -0.014 |
agers | -0.014 |
Token | isse |
Token ID | 20782 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
theorem | +4.298 |
yss | +4.265 |
isoft | +4.112 |
ramid | +4.024 |
rons | +4.005 |
Neg logit contributions | |
>>>>>>>> | -4.152 |
Eisenhower | -3.559 |
selves | -3.506 |
Chavez | -3.477 |
agers | -3.347 |
Token | " |
Token ID | 1 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
>>>>>>>> | +1.002 |
Eisenhower | +0.879 |
selves | +0.850 |
Chavez | +0.835 |
agers | +0.834 |
Neg logit contributions | |
theorem | -1.152 |
yss | -1.145 |
isoft | -1.118 |
ramid | -1.111 |
�� | -1.087 |
Token | is |
Token ID | 318 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
>>>>>>>> | +0.406 |
Eisenhower | +0.351 |
selves | +0.342 |
Chavez | +0.337 |
agers | +0.330 |
Neg logit contributions | |
theorem | -0.471 |
yss | -0.471 |
isoft | -0.459 |
ramid | -0.451 |
�� | -0.446 |
Token | just |
Token ID | 655 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
>>>>>>>> | +1.794 |
Eisenhower | +1.573 |
selves | +1.518 |
Chavez | +1.503 |
agers | +1.475 |
Neg logit contributions | |
yss | -2.137 |
theorem | -2.136 |
isoft | -2.092 |
ramid | -2.069 |
�� | -2.051 |
Token | another |
Token ID | 1194 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
theorem | +0.646 |
yss | +0.642 |
isoft | +0.625 |
ramid | +0.615 |
�� | +0.606 |
Neg logit contributions | |
>>>>>>>> | -0.558 |
Eisenhower | -0.484 |
selves | -0.473 |
Chavez | -0.467 |
agers | -0.457 |
Token | way |
Token ID | 835 |
Feature activation | +7.00e+00 |
Pos logit contributions | |
>>>>>>>> | +0.672 |
Eisenhower | +0.599 |
selves | +0.583 |
Chavez | +0.576 |
agers | +0.561 |
Neg logit contributions | |
yss | -0.642 |
theorem | -0.635 |
isoft | -0.634 |
ramid | -0.621 |
�� | -0.611 |
Token | of |
Token ID | 286 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
>>>>>>>> | +4.954 |
Eisenhower | +4.513 |
selves | +4.316 |
Chavez | +4.294 |
א | +4.223 |
Neg logit contributions | |
isoft | -5.546 |
yss | -5.541 |
theorem | -5.466 |
ramid | -5.441 |
�� | -5.386 |
Token | saying |
Token ID | 2282 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
>>>>>>>> | +2.507 |
Eisenhower | +2.238 |
selves | +2.166 |
Chavez | +2.140 |
agers | +2.097 |
Neg logit contributions | |
theorem | -2.609 |
yss | -2.588 |
isoft | -2.562 |
ramid | -2.534 |
�� | -2.526 |
Token | the |
Token ID | 262 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
>>>>>>>> | +1.598 |
Eisenhower | +1.379 |
selves | +1.339 |
Chavez | +1.317 |
agers | +1.281 |
Neg logit contributions | |
theorem | -2.089 |
yss | -2.070 |
isoft | -2.052 |
ramid | -2.011 |
�� | -1.998 |
Token | beginning |
Token ID | 3726 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
>>>>>>>> | +1.258 |
Eisenhower | +1.096 |
selves | +1.064 |
Chavez | +1.053 |
agers | +1.025 |
Neg logit contributions | |
theorem | -1.527 |
yss | -1.525 |
isoft | -1.511 |
ramid | -1.476 |
�� | -1.465 |
Token | of |
Token ID | 286 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
theorem | +1.257 |
yss | +1.243 |
isoft | +1.202 |
ramid | +1.179 |
rons | +1.162 |
Neg logit contributions | |
>>>>>>>> | -1.380 |
Eisenhower | -1.207 |
selves | -1.186 |
Chavez | -1.171 |
agers | -1.152 |
Token | that |
Token ID | 326 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
>>>>>>>> | +2.820 |
Eisenhower | +2.406 |
selves | +2.332 |
Chavez | +2.325 |
agers | +2.300 |
Neg logit contributions | |
theorem | -3.395 |
isoft | -3.349 |
yss | -3.345 |
�� | -3.288 |
ramid | -3.286 |
Token | , |
Token ID | 11 |
Feature activation | +9.39e-02 |
Pos logit contributions | |
theorem | +0.808 |
yss | +0.808 |
isoft | +0.789 |
ramid | +0.773 |
�� | +0.764 |
Neg logit contributions | |
>>>>>>>> | -0.757 |
Eisenhower | -0.650 |
selves | -0.636 |
Chavez | -0.628 |
ances | -0.615 |
Token | anymore |
Token ID | 7471 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
>>>>>>>> | +0.072 |
Eisenhower | +0.062 |
selves | +0.061 |
Chavez | +0.060 |
agers | +0.059 |
Neg logit contributions | |
theorem | -0.076 |
yss | -0.076 |
isoft | -0.074 |
ramid | -0.074 |
�� | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
>>>>>>>> | +1.440 |
Eisenhower | +1.233 |
selves | +1.216 |
Chavez | +1.193 |
ances | +1.176 |
Neg logit contributions | |
theorem | -1.595 |
yss | -1.582 |
isoft | -1.540 |
ramid | -1.523 |
�� | -1.501 |
Token | Her |
Token ID | 2332 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
>>>>>>>> | +1.255 |
Eisenhower | +1.066 |
selves | +1.028 |
Chavez | +1.013 |
ances | +0.976 |
Neg logit contributions | |
theorem | -1.750 |
yss | -1.734 |
isoft | -1.706 |
ramid | -1.689 |
�� | -1.669 |
Token | very |
Token ID | 845 |
Feature activation | +8.70e+00 |
Pos logit contributions | |
>>>>>>>> | +1.046 |
Eisenhower | +0.892 |
selves | +0.888 |
Chavez | +0.858 |
ances | +0.844 |
Neg logit contributions | |
yss | -1.203 |
theorem | -1.200 |
isoft | -1.171 |
ramid | -1.166 |
�� | -1.158 |
Token | existence |
Token ID | 6224 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
>>>>>>>> | +6.027 |
selves | +5.198 |
Eisenhower | +5.100 |
Chavez | +4.932 |
ances | +4.906 |
Neg logit contributions | |
yss | -7.231 |
ramid | -7.082 |
theorem | -6.972 |
�� | -6.926 |
isoft | -6.886 |
Token | is |
Token ID | 318 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
>>>>>>>> | +0.944 |
Eisenhower | +0.793 |
selves | +0.776 |
Chavez | +0.765 |
ances | +0.752 |
Neg logit contributions | |
theorem | -1.285 |
yss | -1.280 |
isoft | -1.252 |
ramid | -1.238 |
�� | -1.219 |
Token | confusing |
Token ID | 15337 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
>>>>>>>> | +1.401 |
Eisenhower | +1.209 |
selves | +1.178 |
Chavez | +1.166 |
agers | +1.139 |
Neg logit contributions | |
theorem | -1.582 |
yss | -1.575 |
isoft | -1.532 |
ramid | -1.520 |
�� | -1.504 |
Token | – |
Token ID | 1906 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
>>>>>>>> | +0.541 |
Eisenhower | +0.467 |
selves | +0.457 |
Chavez | +0.450 |
ances | +0.444 |
Neg logit contributions | |
theorem | -0.598 |
yss | -0.594 |
isoft | -0.582 |
ramid | -0.574 |
�� | -0.566 |
Token | f |
Token ID | 69 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
>>>>>>>> | +0.611 |
Eisenhower | +0.523 |
selves | +0.516 |
Chavez | +0.502 |
agers | +0.496 |
Neg logit contributions | |
theorem | -0.723 |
yss | -0.714 |
isoft | -0.696 |
ramid | -0.688 |
�� | -0.679 |
Token | chi |
Token ID | 11072 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
theorem | +0.654 |
yss | +0.651 |
isoft | +0.628 |
ramid | +0.616 |
�� | +0.608 |
Neg logit contributions | |
>>>>>>>> | -0.678 |
Eisenhower | -0.592 |
selves | -0.574 |
Chavez | -0.573 |
agers | -0.562 |
Token | Sea |
Token ID | 6896 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
theorem | +1.332 |
yss | +1.322 |
isoft | +1.281 |
ramid | +1.256 |
�� | +1.240 |
Neg logit contributions | |
>>>>>>>> | -1.315 |
Eisenhower | -1.140 |
selves | -1.116 |
Chavez | -1.103 |
agers | -1.084 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
yss | +0.314 |
theorem | +0.314 |
isoft | +0.305 |
�� | +0.298 |
ramid | +0.298 |
Neg logit contributions | |
>>>>>>>> | -0.286 |
Eisenhower | -0.247 |
selves | -0.241 |
Chavez | -0.238 |
ances | -0.233 |
Token | Alaska |
Token ID | 12926 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
>>>>>>>> | +0.953 |
Eisenhower | +0.827 |
selves | +0.801 |
Chavez | +0.797 |
ances | +0.757 |
Neg logit contributions | |
theorem | -1.215 |
yss | -1.206 |
isoft | -1.170 |
�� | -1.166 |
ramid | -1.163 |
Token | is |
Token ID | 318 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
>>>>>>>> | +2.284 |
Eisenhower | +1.906 |
selves | +1.876 |
Chavez | +1.842 |
ances | +1.814 |
Neg logit contributions | |
theorem | -3.109 |
yss | -3.107 |
�� | -3.022 |
ramid | -2.993 |
isoft | -2.967 |
Token | far |
Token ID | 1290 |
Feature activation | +7.77e+00 |
Pos logit contributions | |
>>>>>>>> | +3.958 |
Eisenhower | +3.497 |
Chavez | +3.393 |
selves | +3.336 |
agers | +3.210 |
Neg logit contributions | |
theorem | -4.674 |
�� | -4.657 |
yss | -4.653 |
isoft | -4.543 |
ramid | -4.504 |
Token | more |
Token ID | 517 |
Feature activation | +8.90e+00 |
Pos logit contributions | |
>>>>>>>> | +4.907 |
Eisenhower | +4.272 |
selves | +4.132 |
Chavez | +4.114 |
ances | +4.069 |
Neg logit contributions | |
theorem | -6.938 |
yss | -6.933 |
�� | -6.808 |
ramid | -6.803 |
isoft | -6.725 |
Token | remote |
Token ID | 6569 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
>>>>>>>> | +5.496 |
Eisenhower | +4.805 |
Chavez | +4.668 |
deserving | +4.461 |
selves | +4.382 |
Neg logit contributions | |
�� | -8.046 |
yss | -7.983 |
ramid | -7.962 |
theorem | -7.880 |
isoft | -7.834 |
Token | than |
Token ID | 621 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
>>>>>>>> | +2.994 |
Eisenhower | +2.497 |
selves | +2.456 |
Chavez | +2.417 |
ances | +2.368 |
Neg logit contributions | |
theorem | -4.412 |
yss | -4.408 |
isoft | -4.316 |
ramid | -4.308 |
�� | -4.302 |
Token | the |
Token ID | 262 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
>>>>>>>> | +1.081 |
Eisenhower | +0.939 |
Chavez | +0.906 |
selves | +0.894 |
agers | +0.867 |
Neg logit contributions | |
yss | -1.343 |
theorem | -1.335 |
isoft | -1.305 |
ramid | -1.288 |
�� | -1.282 |
Token | Gulf |
Token ID | 12108 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
>>>>>>>> | +1.239 |
Eisenhower | +1.067 |
Chavez | +1.023 |
selves | +1.005 |
agers | +0.971 |
Neg logit contributions | |
yss | -1.831 |
theorem | -1.817 |
isoft | -1.792 |
ramid | -1.766 |
�� | -1.752 |
Token | - |
Token ID | 532 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
>>>>>>>> | +4.106 |
Eisenhower | +3.533 |
Chavez | +3.457 |
selves | +3.412 |
agers | +3.279 |
Neg logit contributions | |
yss | -5.021 |
theorem | -4.857 |
�� | -4.845 |
isoft | -4.820 |
ramid | -4.778 |
Token | TT |
Token ID | 26653 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
>>>>>>>> | +1.515 |
Eisenhower | +1.317 |
Chavez | +1.288 |
selves | +1.277 |
agers | +1.238 |
Neg logit contributions | |
theorem | -1.677 |
yss | -1.671 |
isoft | -1.608 |
�� | -1.597 |
ramid | -1.592 |
Token | IP |
Token ID | 4061 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
>>>>>>>> | +3.483 |
Eisenhower | +2.849 |
Chavez | +2.739 |
agers | +2.664 |
ances | +2.657 |
Neg logit contributions | |
�� | -5.399 |
yss | -5.289 |
theorem | -5.274 |
isoft | -5.138 |
ramid | -5.114 |
Token | - |
Token ID | 532 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
>>>>>>>> | +1.595 |
Eisenhower | +1.361 |
Chavez | +1.323 |
selves | +1.319 |
agers | +1.299 |
Neg logit contributions | |
theorem | -1.807 |
yss | -1.801 |
isoft | -1.751 |
�� | -1.730 |
ramid | -1.702 |
Token | sound |
Token ID | 2128 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
>>>>>>>> | +0.285 |
Eisenhower | +0.243 |
selves | +0.237 |
Chavez | +0.235 |
agers | +0.229 |
Neg logit contributions | |
theorem | -0.367 |
yss | -0.365 |
isoft | -0.355 |
ramid | -0.349 |
�� | -0.347 |
Token | dull |
Token ID | 19222 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
>>>>>>>> | +3.028 |
Eisenhower | +2.632 |
selves | +2.552 |
Chavez | +2.530 |
ances | +2.508 |
Neg logit contributions | |
yss | -4.039 |
theorem | -4.022 |
�� | -3.886 |
isoft | -3.878 |
ramid | -3.774 |
Token | . |
Token ID | 13 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
>>>>>>>> | +0.910 |
Eisenhower | +0.788 |
selves | +0.775 |
Chavez | +0.764 |
ances | +0.758 |
Neg logit contributions | |
theorem | -1.035 |
yss | -1.023 |
isoft | -0.999 |
�� | -0.984 |
ramid | -0.982 |
Token | It |
Token ID | 632 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
>>>>>>>> | +0.247 |
Eisenhower | +0.212 |
selves | +0.206 |
Chavez | +0.204 |
agers | +0.197 |
Neg logit contributions | |
theorem | -0.318 |
yss | -0.316 |
isoft | -0.307 |
ramid | -0.302 |
�� | -0.301 |
Token | combines |
Token ID | 21001 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
>>>>>>>> | +1.312 |
Eisenhower | +1.115 |
selves | +1.086 |
Chavez | +1.076 |
agers | +1.053 |
Neg logit contributions | |
theorem | -1.861 |
yss | -1.858 |
isoft | -1.819 |
�� | -1.793 |
ramid | -1.776 |
Token | the |
Token ID | 262 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
>>>>>>>> | +2.160 |
Eisenhower | +1.881 |
Chavez | +1.817 |
selves | +1.782 |
agers | +1.767 |
Neg logit contributions | |
yss | -2.467 |
theorem | -2.461 |
isoft | -2.427 |
�� | -2.393 |
ramid | -2.377 |
Token | US |
Token ID | 1294 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
theorem | +0.336 |
yss | +0.335 |
isoft | +0.327 |
ramid | +0.320 |
�� | +0.318 |
Neg logit contributions | |
>>>>>>>> | -0.286 |
Eisenhower | -0.246 |
selves | -0.239 |
Chavez | -0.237 |
agers | -0.232 |
Token | more |
Token ID | 517 |
Feature activation | +7.93e+00 |
Pos logit contributions | |
>>>>>>>> | +0.865 |
Eisenhower | +0.761 |
Chavez | +0.738 |
selves | +0.738 |
agers | +0.714 |
Neg logit contributions | |
theorem | -0.954 |
yss | -0.947 |
isoft | -0.921 |
ramid | -0.907 |
�� | -0.906 |
Token | than |
Token ID | 621 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
>>>>>>>> | +4.217 |
Eisenhower | +3.528 |
Chavez | +3.459 |
deserving | +3.188 |
ager | +3.177 |
Neg logit contributions | |
yss | -7.890 |
theorem | -7.774 |
isoft | -7.765 |
ramid | -7.724 |
�� | -7.678 |
Token | two |
Token ID | 734 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
>>>>>>>> | +1.157 |
Eisenhower | +1.038 |
Chavez | +0.995 |
selves | +0.981 |
agers | +0.951 |
Neg logit contributions | |
yss | -1.394 |
theorem | -1.392 |
isoft | -1.370 |
ramid | -1.345 |
�� | -1.331 |
Token | decades |
Token ID | 4647 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
>>>>>>>> | +0.571 |
Eisenhower | +0.490 |
selves | +0.471 |
Chavez | +0.469 |
agers | +0.457 |
Neg logit contributions | |
theorem | -0.793 |
yss | -0.791 |
isoft | -0.772 |
ramid | -0.760 |
�� | -0.753 |
Token | ago |
Token ID | 2084 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
theorem | +0.275 |
yss | +0.272 |
isoft | +0.261 |
ramid | +0.255 |
�� | +0.250 |
Neg logit contributions | |
>>>>>>>> | -0.454 |
Eisenhower | -0.407 |
selves | -0.401 |
Chavez | -0.397 |
agers | -0.391 |
Token | . |
Token ID | 13 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
theorem | +2.009 |
yss | +1.985 |
isoft | +1.918 |
ramid | +1.884 |
rons | +1.868 |
Neg logit contributions | |
>>>>>>>> | -2.093 |
Eisenhower | -1.813 |
selves | -1.787 |
Chavez | -1.750 |
agers | -1.736 |
Token | The |
Token ID | 464 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
>>>>>>>> | +1.700 |
Eisenhower | +1.466 |
selves | +1.418 |
Chavez | +1.396 |
א | +1.354 |
Neg logit contributions | |
theorem | -2.276 |
yss | -2.254 |
isoft | -2.173 |
ramid | -2.149 |
�� | -2.131 |
Token | company |
Token ID | 1664 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
theorem | +0.600 |
yss | +0.594 |
isoft | +0.579 |
ramid | +0.569 |
�� | +0.563 |
Neg logit contributions | |
>>>>>>>> | -0.480 |
Eisenhower | -0.412 |
selves | -0.400 |
Chavez | -0.395 |
agers | -0.388 |
Token | released |
Token ID | 2716 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
>>>>>>>> | +1.276 |
Eisenhower | +1.117 |
Chavez | +1.074 |
selves | +1.071 |
agers | +1.047 |
Neg logit contributions | |
theorem | -1.601 |
yss | -1.585 |
isoft | -1.554 |
�� | -1.536 |
ramid | -1.526 |
Token | an |
Token ID | 281 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
>>>>>>>> | +1.887 |
Eisenhower | +1.672 |
Chavez | +1.594 |
selves | +1.588 |
agers | +1.549 |
Neg logit contributions | |
theorem | -2.355 |
yss | -2.332 |
isoft | -2.296 |
ramid | -2.266 |
rons | -2.225 |
Token | independent |
Token ID | 4795 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
>>>>>>>> | +0.523 |
Eisenhower | +0.472 |
Chavez | +0.447 |
selves | +0.445 |
agers | +0.444 |
Neg logit contributions | |
theorem | -0.563 |
yss | -0.560 |
isoft | -0.543 |
ramid | -0.543 |
�� | -0.530 |
Token | linebacker |
Token ID | 18961 |
Feature activation | +5.80e+00 |
Pos logit contributions | |
>>>>>>>> | +1.693 |
Eisenhower | +1.445 |
selves | +1.362 |
Chavez | +1.338 |
agers | +1.301 |
Neg logit contributions | |
yss | -3.481 |
theorem | -3.412 |
isoft | -3.377 |
ramid | -3.349 |
�� | -3.277 |
Token | Lam |
Token ID | 10923 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
>>>>>>>> | +3.645 |
Eisenhower | +3.323 |
Chavez | +3.156 |
selves | +3.105 |
agers | +3.025 |
Neg logit contributions | |
yss | -5.251 |
isoft | -5.138 |
theorem | -5.083 |
ramid | -5.026 |
�� | -4.895 |
Token | arr |
Token ID | 3258 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
>>>>>>>> | +0.941 |
Eisenhower | +0.821 |
Chavez | +0.794 |
selves | +0.794 |
agers | +0.778 |
Neg logit contributions | |
theorem | -1.026 |
yss | -0.996 |
isoft | -0.981 |
ramid | -0.963 |
�� | -0.955 |
Token | Houston |
Token ID | 6995 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
>>>>>>>> | +1.723 |
Eisenhower | +1.417 |
Chavez | +1.324 |
selves | +1.301 |
ances | +1.288 |
Neg logit contributions | |
theorem | -4.411 |
�� | -4.216 |
yss | -4.203 |
isoft | -4.165 |
ramid | -4.139 |
Token | , |
Token ID | 11 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
theorem | +0.029 |
yss | +0.029 |
isoft | +0.029 |
ramid | +0.028 |
�� | +0.028 |
Neg logit contributions | |
>>>>>>>> | -0.027 |
Eisenhower | -0.024 |
selves | -0.023 |
Chavez | -0.023 |
agers | -0.023 |
Token | who |
Token ID | 508 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
>>>>>>>> | +0.527 |
Eisenhower | +0.456 |
Chavez | +0.435 |
selves | +0.432 |
agers | +0.417 |
Neg logit contributions | |
yss | -0.804 |
theorem | -0.799 |
isoft | -0.783 |
ramid | -0.773 |
rons | -0.760 |
Token | had |
Token ID | 550 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
>>>>>>>> | +0.460 |
Eisenhower | +0.404 |
Chavez | +0.389 |
selves | +0.387 |
ances | +0.376 |
Neg logit contributions | |
theorem | -0.538 |
yss | -0.537 |
isoft | -0.526 |
ramid | -0.514 |
�� | -0.512 |
Token | a |
Token ID | 257 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
theorem | +3.238 |
yss | +3.199 |
isoft | +3.095 |
ramid | +3.043 |
rons | +3.005 |
Neg logit contributions | |
>>>>>>>> | -3.271 |
Eisenhower | -2.838 |
selves | -2.797 |
Chavez | -2.747 |
agers | -2.708 |
Token | team |
Token ID | 1074 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
theorem | +2.911 |
yss | +2.874 |
isoft | +2.785 |
ramid | +2.743 |
rons | +2.708 |
Neg logit contributions | |
>>>>>>>> | -2.474 |
Eisenhower | -2.120 |
selves | -2.086 |
Chavez | -2.041 |
agers | -2.017 |
Token | - |
Token ID | 12 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
theorem | +1.609 |
yss | +1.594 |
isoft | +1.548 |
ramid | +1.527 |
rons | +1.508 |
Neg logit contributions | |
>>>>>>>> | -1.231 |
Eisenhower | -1.042 |
selves | -1.022 |
Chavez | -1.003 |
agers | -0.984 |
Token | and |
Token ID | 290 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
>>>>>>>> | +0.874 |
Eisenhower | +0.742 |
selves | +0.730 |
Chavez | +0.709 |
agers | +0.699 |
Neg logit contributions | |
theorem | -1.273 |
yss | -1.259 |
isoft | -1.215 |
�� | -1.209 |
ramid | -1.195 |
Token | entering |
Token ID | 8218 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
>>>>>>>> | +0.020 |
Eisenhower | +0.017 |
selves | +0.017 |
Chavez | +0.017 |
agers | +0.016 |
Neg logit contributions | |
theorem | -0.019 |
yss | -0.019 |
isoft | -0.019 |
�� | -0.018 |
ramid | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
>>>>>>>> | +2.172 |
Eisenhower | +1.882 |
selves | +1.840 |
Chavez | +1.839 |
agers | +1.786 |
Neg logit contributions | |
theorem | -2.395 |
yss | -2.367 |
isoft | -2.309 |
ramid | -2.261 |
�� | -2.239 |
Token | Hall |
Token ID | 4789 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
>>>>>>>> | +2.669 |
Eisenhower | +2.359 |
Chavez | +2.284 |
selves | +2.232 |
agers | +2.183 |
Neg logit contributions | |
yss | -3.474 |
theorem | -3.433 |
isoft | -3.371 |
ramid | -3.310 |
�� | -3.276 |
Token | are |
Token ID | 389 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
>>>>>>>> | +3.425 |
selves | +2.955 |
Eisenhower | +2.947 |
Chavez | +2.911 |
agers | +2.877 |
Neg logit contributions | |
yss | -3.922 |
theorem | -3.891 |
isoft | -3.857 |
�� | -3.719 |
ramid | -3.700 |
Token | George |
Token ID | 4502 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
>>>>>>>> | +2.174 |
Eisenhower | +1.904 |
Chavez | +1.846 |
selves | +1.839 |
agers | +1.780 |
Neg logit contributions | |
yss | -2.824 |
theorem | -2.817 |
isoft | -2.764 |
ramid | -2.723 |
�� | -2.667 |
Token | Anderson |
Token ID | 9918 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
theorem | +4.011 |
yss | +3.998 |
isoft | +3.841 |
rons | +3.783 |
ramid | +3.762 |
Neg logit contributions | |
>>>>>>>> | -3.348 |
selves | -2.770 |
Eisenhower | -2.762 |
agers | -2.679 |
ances | -2.662 |
Token | , |
Token ID | 11 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
>>>>>>>> | +1.926 |
Eisenhower | +1.681 |
Chavez | +1.641 |
selves | +1.629 |
agers | +1.598 |
Neg logit contributions | |
theorem | -2.195 |
yss | -2.183 |
isoft | -2.124 |
ramid | -2.084 |
�� | -2.049 |
Token | in |
Token ID | 287 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
theorem | +0.632 |
yss | +0.629 |
isoft | +0.613 |
ramid | +0.604 |
rons | +0.594 |
Neg logit contributions | |
>>>>>>>> | -0.467 |
Eisenhower | -0.399 |
selves | -0.387 |
Chavez | -0.384 |
agers | -0.374 |
Token | the |
Token ID | 262 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
>>>>>>>> | +1.590 |
Eisenhower | +1.399 |
Chavez | +1.359 |
selves | +1.336 |
agers | +1.322 |
Neg logit contributions | |
yss | -1.976 |
theorem | -1.976 |
isoft | -1.911 |
ramid | -1.879 |
�� | -1.853 |
Token | pioneer |
Token ID | 29570 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
>>>>>>>> | +2.571 |
Eisenhower | +2.316 |
selves | +2.201 |
Chavez | +2.195 |
agers | +2.126 |
Neg logit contributions | |
yss | -3.272 |
theorem | -3.248 |
isoft | -3.180 |
ramid | -3.147 |
�� | -3.086 |
Token | category |
Token ID | 6536 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
>>>>>>>> | +0.580 |
Eisenhower | +0.521 |
selves | +0.508 |
Chavez | +0.505 |
agers | +0.497 |
Neg logit contributions | |
yss | -0.484 |
theorem | -0.484 |
isoft | -0.467 |
ramid | -0.460 |
�� | -0.453 |
Token | which |
Token ID | 543 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
>>>>>>>> | +0.370 |
Eisenhower | +0.320 |
Chavez | +0.312 |
selves | +0.311 |
agers | +0.305 |
Neg logit contributions | |
yss | -0.421 |
theorem | -0.406 |
isoft | -0.406 |
ramid | -0.398 |
�� | -0.395 |
Token | could |
Token ID | 714 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
theorem | +1.086 |
yss | +1.085 |
isoft | +1.056 |
ramid | +1.039 |
�� | +1.029 |
Neg logit contributions | |
>>>>>>>> | -0.859 |
Eisenhower | -0.737 |
selves | -0.714 |
Chavez | -0.711 |
agers | -0.693 |
Token | capture |
Token ID | 8006 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
>>>>>>>> | +1.744 |
Eisenhower | +1.476 |
selves | +1.460 |
agers | +1.426 |
Chavez | +1.425 |
Neg logit contributions | |
yss | -2.347 |
theorem | -2.295 |
isoft | -2.254 |
ramid | -2.210 |
�� | -2.209 |
Token | the |
Token ID | 262 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
>>>>>>>> | +3.201 |
Eisenhower | +2.837 |
Chavez | +2.715 |
selves | +2.702 |
ances | +2.693 |
Neg logit contributions | |
yss | -3.850 |
isoft | -3.785 |
theorem | -3.743 |
�� | -3.721 |
ramid | -3.704 |
Token | economic |
Token ID | 3034 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
>>>>>>>> | +0.645 |
Eisenhower | +0.563 |
selves | +0.548 |
Chavez | +0.543 |
agers | +0.532 |
Neg logit contributions | |
yss | -0.706 |
theorem | -0.700 |
isoft | -0.692 |
ramid | -0.677 |
�� | -0.672 |
Token | middle |
Token ID | 3504 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
theorem | +2.261 |
yss | +2.224 |
isoft | +2.151 |
ramid | +2.116 |
rons | +2.093 |
Neg logit contributions | |
>>>>>>>> | -2.283 |
Eisenhower | -1.983 |
selves | -1.945 |
Chavez | -1.919 |
agers | -1.889 |
Token | in |
Token ID | 287 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
>>>>>>>> | +0.357 |
Eisenhower | +0.322 |
selves | +0.317 |
Chavez | +0.316 |
ances | +0.312 |
Neg logit contributions | |
yss | -0.189 |
theorem | -0.185 |
isoft | -0.180 |
�� | -0.175 |
ramid | -0.174 |
Token | India |
Token ID | 3794 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
>>>>>>>> | +2.709 |
Eisenhower | +2.414 |
Chavez | +2.309 |
selves | +2.301 |
agers | +2.287 |
Neg logit contributions | |
yss | -3.358 |
theorem | -3.251 |
isoft | -3.234 |
ramid | -3.201 |
�� | -3.179 |
Token | . |
Token ID | 13 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
>>>>>>>> | +1.156 |
Eisenhower | +0.991 |
selves | +0.990 |
Chavez | +0.966 |
ances | +0.945 |
Neg logit contributions | |
yss | -1.346 |
theorem | -1.328 |
isoft | -1.294 |
ramid | -1.282 |
�� | -1.279 |
Token | While |
Token ID | 2893 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
>>>>>>>> | +0.522 |
Eisenhower | +0.454 |
selves | +0.440 |
Chavez | +0.438 |
א | +0.418 |
Neg logit contributions | |
yss | -0.654 |
theorem | -0.652 |
isoft | -0.632 |
ramid | -0.626 |
�� | -0.622 |
Token | there |
Token ID | 612 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
theorem | +3.506 |
yss | +3.443 |
isoft | +3.339 |
ramid | +3.277 |
rons | +3.252 |
Neg logit contributions | |
>>>>>>>> | -3.251 |
Eisenhower | -2.800 |
selves | -2.760 |
Chavez | -2.702 |
agers | -2.666 |
Token | not |
Token ID | 407 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
>>>>>>>> | +2.263 |
Eisenhower | +1.996 |
Chavez | +1.913 |
selves | +1.902 |
agers | +1.848 |
Neg logit contributions | |
theorem | -2.700 |
yss | -2.694 |
isoft | -2.638 |
�� | -2.610 |
ramid | -2.602 |
Token | an |
Token ID | 281 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
>>>>>>>> | +0.302 |
Eisenhower | +0.261 |
Chavez | +0.251 |
selves | +0.251 |
agers | +0.242 |
Neg logit contributions | |
theorem | -0.387 |
yss | -0.386 |
isoft | -0.377 |
ramid | -0.371 |
�� | -0.369 |
Token | isolated |
Token ID | 11557 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
>>>>>>>> | +0.088 |
Eisenhower | +0.076 |
selves | +0.073 |
Chavez | +0.073 |
agers | +0.071 |
Neg logit contributions | |
theorem | -0.114 |
yss | -0.114 |
isoft | -0.111 |
ramid | -0.109 |
�� | -0.108 |
Token | case |
Token ID | 1339 |
Feature activation | +8.18e+00 |
Pos logit contributions | |
>>>>>>>> | +1.837 |
Eisenhower | +1.561 |
Chavez | +1.496 |
selves | +1.466 |
ances | +1.445 |
Neg logit contributions | |
yss | -2.826 |
isoft | -2.773 |
theorem | -2.764 |
ramid | -2.742 |
�� | -2.723 |
Token | . |
Token ID | 13 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
>>>>>>>> | +5.222 |
Eisenhower | +4.475 |
Chavez | +4.335 |
selves | +4.287 |
ager | +4.247 |
Neg logit contributions | |
yss | -7.263 |
isoft | -7.056 |
ramid | -7.033 |
theorem | -6.879 |
�� | -6.868 |
Token | Across |
Token ID | 27497 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
>>>>>>>> | +0.602 |
Eisenhower | +0.526 |
Chavez | +0.510 |
selves | +0.508 |
ances | +0.483 |
Neg logit contributions | |
theorem | -0.720 |
yss | -0.715 |
isoft | -0.692 |
ramid | -0.687 |
�� | -0.683 |
Token | the |
Token ID | 262 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
theorem | +0.714 |
yss | +0.707 |
isoft | +0.686 |
ramid | +0.674 |
rons | +0.665 |
Neg logit contributions | |
>>>>>>>> | -0.664 |
Eisenhower | -0.574 |
selves | -0.562 |
Chavez | -0.555 |
agers | -0.545 |
Token | country |
Token ID | 1499 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
>>>>>>>> | +1.859 |
Eisenhower | +1.578 |
Chavez | +1.467 |
selves | +1.462 |
agers | +1.423 |
Neg logit contributions | |
yss | -3.217 |
theorem | -3.188 |
isoft | -3.143 |
ramid | -3.099 |
�� | -3.089 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
>>>>>>>> | +0.449 |
Eisenhower | +0.384 |
selves | +0.374 |
Chavez | +0.371 |
agers | +0.362 |
Neg logit contributions | |
theorem | -0.536 |
yss | -0.533 |
isoft | -0.519 |
ramid | -0.510 |
�� | -0.504 |
Token | and |
Token ID | 290 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
>>>>>>>> | +1.108 |
Eisenhower | +0.952 |
Chavez | +0.921 |
selves | +0.909 |
ances | +0.885 |
Neg logit contributions | |
yss | -1.358 |
theorem | -1.351 |
isoft | -1.324 |
ramid | -1.306 |
�� | -1.300 |
Token | particularly |
Token ID | 3573 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
>>>>>>>> | +1.161 |
Eisenhower | +1.009 |
selves | +0.978 |
Chavez | +0.977 |
ances | +0.939 |
Neg logit contributions | |
yss | -1.399 |
theorem | -1.396 |
isoft | -1.368 |
ramid | -1.362 |
�� | -1.342 |
Token | the |
Token ID | 262 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
theorem | +2.346 |
yss | +2.323 |
isoft | +2.252 |
ramid | +2.210 |
rons | +2.180 |
Neg logit contributions | |
>>>>>>>> | -2.353 |
Eisenhower | -2.045 |
selves | -2.006 |
Chavez | -1.980 |
agers | -1.946 |
Token | reefs |
Token ID | 43190 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
theorem | +0.439 |
yss | +0.439 |
isoft | +0.427 |
ramid | +0.416 |
�� | +0.414 |
Neg logit contributions | |
>>>>>>>> | -0.470 |
Eisenhower | -0.416 |
selves | -0.403 |
Chavez | -0.400 |
agers | -0.393 |
Token | and |
Token ID | 290 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
yss | +0.394 |
theorem | +0.394 |
isoft | +0.387 |
ramid | +0.379 |
�� | +0.377 |
Neg logit contributions | |
>>>>>>>> | -0.349 |
Eisenhower | -0.306 |
selves | -0.296 |
Chavez | -0.294 |
agers | -0.289 |
Token | the |
Token ID | 262 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
theorem | +0.942 |
yss | +0.934 |
isoft | +0.912 |
ramid | +0.892 |
�� | +0.892 |
Neg logit contributions | |
>>>>>>>> | -0.897 |
Eisenhower | -0.779 |
selves | -0.760 |
Chavez | -0.753 |
agers | -0.739 |
Token | opening |
Token ID | 4756 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
>>>>>>>> | +0.274 |
Eisenhower | +0.241 |
selves | +0.232 |
Chavez | +0.231 |
agers | +0.228 |
Neg logit contributions | |
yss | -0.265 |
theorem | -0.265 |
isoft | -0.258 |
ramid | -0.251 |
�� | -0.251 |
Token | of |
Token ID | 286 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
theorem | +0.759 |
yss | +0.755 |
isoft | +0.732 |
ramid | +0.717 |
�� | +0.708 |
Neg logit contributions | |
>>>>>>>> | -0.810 |
Eisenhower | -0.708 |
selves | -0.693 |
Chavez | -0.686 |
agers | -0.675 |
Token | a |
Token ID | 257 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
theorem | +0.938 |
yss | +0.931 |
isoft | +0.904 |
ramid | +0.888 |
�� | +0.880 |
Neg logit contributions | |
>>>>>>>> | -0.821 |
Eisenhower | -0.709 |
selves | -0.691 |
Chavez | -0.684 |
agers | -0.669 |
Token | deep |
Token ID | 2769 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
theorem | +0.618 |
yss | +0.615 |
isoft | +0.600 |
ramid | +0.586 |
�� | +0.583 |
Neg logit contributions | |
>>>>>>>> | -0.497 |
Eisenhower | -0.424 |
selves | -0.413 |
Chavez | -0.410 |
agers | -0.398 |
Token | channel |
Token ID | 6518 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
>>>>>>>> | +1.741 |
Eisenhower | +1.506 |
Chavez | +1.455 |
selves | +1.446 |
agers | +1.413 |
Neg logit contributions | |
yss | -2.111 |
theorem | -2.091 |
isoft | -2.067 |
�� | -2.016 |
rons | -1.985 |
Token | through |
Token ID | 832 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
theorem | +1.438 |
yss | +1.437 |
isoft | +1.401 |
ramid | +1.364 |
�� | +1.356 |
Neg logit contributions | |
>>>>>>>> | -1.397 |
Eisenhower | -1.219 |
selves | -1.194 |
Chavez | -1.181 |
agers | -1.161 |
Token | the |
Token ID | 262 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
>>>>>>>> | +1.597 |
Eisenhower | +1.392 |
Chavez | +1.343 |
selves | +1.326 |
agers | +1.308 |
Neg logit contributions | |
theorem | -2.046 |
yss | -2.024 |
isoft | -1.986 |
�� | -1.938 |
ramid | -1.934 |
Token | with |
Token ID | 351 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
>>>>>>>> | +0.408 |
Eisenhower | +0.356 |
selves | +0.347 |
Chavez | +0.341 |
agers | +0.336 |
Neg logit contributions | |
theorem | -0.434 |
yss | -0.431 |
isoft | -0.424 |
ramid | -0.419 |
�� | -0.417 |
Token | the |
Token ID | 262 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
>>>>>>>> | +0.935 |
Eisenhower | +0.810 |
selves | +0.780 |
Chavez | +0.776 |
agers | +0.760 |
Neg logit contributions | |
theorem | -1.233 |
yss | -1.230 |
isoft | -1.210 |
ramid | -1.191 |
�� | -1.188 |
Token | bears |
Token ID | 13062 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
>>>>>>>> | +0.371 |
Eisenhower | +0.324 |
selves | +0.313 |
Chavez | +0.309 |
agers | +0.305 |
Neg logit contributions | |
theorem | -0.443 |
yss | -0.443 |
isoft | -0.435 |
ramid | -0.427 |
�� | -0.424 |
Token | and |
Token ID | 290 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
>>>>>>>> | +0.583 |
Eisenhower | +0.509 |
selves | +0.496 |
Chavez | +0.488 |
agers | +0.485 |
Neg logit contributions | |
yss | -0.627 |
theorem | -0.622 |
isoft | -0.612 |
ramid | -0.603 |
�� | -0.599 |
Token | me |
Token ID | 502 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
theorem | +0.759 |
yss | +0.757 |
isoft | +0.741 |
ramid | +0.729 |
�� | +0.724 |
Neg logit contributions | |
>>>>>>>> | -0.724 |
Eisenhower | -0.630 |
selves | -0.612 |
Chavez | -0.607 |
agers | -0.597 |
Token | when |
Token ID | 618 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
theorem | +0.328 |
yss | +0.322 |
isoft | +0.317 |
�� | +0.311 |
ramid | +0.310 |
Neg logit contributions | |
>>>>>>>> | -0.318 |
Eisenhower | -0.277 |
selves | -0.275 |
Chavez | -0.268 |
agers | -0.267 |
Token | I |
Token ID | 314 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
theorem | +0.954 |
yss | +0.947 |
isoft | +0.924 |
ramid | +0.908 |
�� | +0.902 |
Neg logit contributions | |
>>>>>>>> | -0.916 |
Eisenhower | -0.802 |
selves | -0.778 |
Chavez | -0.772 |
agers | -0.759 |
Token | was |
Token ID | 373 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
theorem | +1.598 |
yss | +1.589 |
isoft | +1.543 |
ramid | +1.513 |
�� | +1.505 |
Neg logit contributions | |
>>>>>>>> | -1.537 |
Eisenhower | -1.336 |
selves | -1.306 |
Chavez | -1.293 |
agers | -1.268 |
Token | struggling |
Token ID | 9648 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
theorem | +3.530 |
yss | +3.498 |
isoft | +3.360 |
ramid | +3.288 |
rons | +3.268 |
Neg logit contributions | |
>>>>>>>> | -3.713 |
Eisenhower | -3.212 |
selves | -3.177 |
Chavez | -3.126 |
agers | -3.067 |
Token | against |
Token ID | 1028 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
theorem | +2.991 |
yss | +2.967 |
isoft | +2.831 |
ramid | +2.778 |
rons | +2.753 |
Neg logit contributions | |
>>>>>>>> | -3.273 |
Eisenhower | -2.856 |
selves | -2.806 |
Chavez | -2.771 |
agers | -2.719 |
Token | D |
Token ID | 360 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
>>>>>>>> | +0.354 |
Eisenhower | +0.310 |
selves | +0.296 |
Chavez | +0.296 |
agers | +0.291 |
Neg logit contributions | |
yss | -0.429 |
theorem | -0.426 |
isoft | -0.419 |
�� | -0.414 |
ramid | -0.412 |
Token | evolution |
Token ID | 6954 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
>>>>>>>> | +0.194 |
Eisenhower | +0.169 |
Chavez | +0.163 |
selves | +0.163 |
ances | +0.159 |
Neg logit contributions | |
yss | -0.200 |
theorem | -0.200 |
isoft | -0.196 |
ramid | -0.192 |
�� | -0.192 |
Token | in |
Token ID | 287 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
theorem | +0.952 |
yss | +0.951 |
isoft | +0.923 |
ramid | +0.908 |
�� | +0.898 |
Neg logit contributions | |
>>>>>>>> | -0.980 |
Eisenhower | -0.860 |
selves | -0.842 |
Chavez | -0.836 |
agers | -0.817 |
Token | the |
Token ID | 262 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
>>>>>>>> | +0.475 |
Eisenhower | +0.419 |
selves | +0.404 |
Chavez | +0.404 |
agers | +0.399 |
Neg logit contributions | |
theorem | -0.488 |
yss | -0.488 |
isoft | -0.473 |
�� | -0.463 |
ramid | -0.460 |
Token | [ |
Token ID | 685 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
>>>>>>>> | +1.002 |
Eisenhower | +0.885 |
selves | +0.857 |
Chavez | +0.851 |
agers | +0.838 |
Neg logit contributions | |
yss | -0.989 |
theorem | -0.985 |
isoft | -0.959 |
�� | -0.939 |
ramid | -0.932 |
Token | F |
Token ID | 37 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
>>>>>>>> | +0.215 |
Eisenhower | +0.185 |
selves | +0.183 |
Chavez | +0.179 |
agers | +0.178 |
Neg logit contributions | |
theorem | -0.223 |
yss | -0.219 |
isoft | -0.213 |
�� | -0.209 |
ramid | -0.208 |
Token | DA |
Token ID | 5631 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
>>>>>>>> | +0.126 |
Eisenhower | +0.103 |
selves | +0.100 |
Chavez | +0.099 |
agers | +0.097 |
Neg logit contributions | |
theorem | -0.207 |
yss | -0.204 |
isoft | -0.200 |
�� | -0.196 |
ramid | -0.195 |
Token | 's |
Token ID | 338 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
theorem | +1.073 |
yss | +1.062 |
isoft | +1.040 |
ramid | +1.023 |
rons | +1.011 |
Neg logit contributions | |
>>>>>>>> | -0.788 |
Eisenhower | -0.664 |
selves | -0.648 |
Chavez | -0.641 |
agers | -0.626 |
Token | ] |
Token ID | 60 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
>>>>>>>> | +0.158 |
Eisenhower | +0.128 |
selves | +0.125 |
Chavez | +0.121 |
agers | +0.118 |
Neg logit contributions | |
theorem | -0.310 |
yss | -0.308 |
isoft | -0.300 |
ramid | -0.296 |
�� | -0.294 |
Token | approach |
Token ID | 3164 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
theorem | +1.125 |
yss | +1.119 |
isoft | +1.082 |
ramid | +1.062 |
�� | +1.053 |
Neg logit contributions | |
>>>>>>>> | -1.147 |
Eisenhower | -1.003 |
selves | -0.985 |
Chavez | -0.971 |
agers | -0.954 |
Token | to |
Token ID | 284 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
>>>>>>>> | +0.930 |
Eisenhower | +0.816 |
selves | +0.799 |
Chavez | +0.796 |
ances | +0.781 |
Neg logit contributions | |
yss | -0.902 |
theorem | -0.901 |
isoft | -0.883 |
�� | -0.862 |
ramid | -0.859 |
Token | regulating |
Token ID | 26379 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
theorem | +1.276 |
yss | +1.267 |
isoft | +1.229 |
ramid | +1.205 |
�� | +1.193 |
Neg logit contributions | |
>>>>>>>> | -1.183 |
Eisenhower | -1.023 |
selves | -1.001 |
Chavez | -0.988 |
agers | -0.972 |
Token | every |
Token ID | 790 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
theorem | +1.075 |
yss | +1.075 |
isoft | +1.041 |
ramid | +1.021 |
�� | +1.009 |
Neg logit contributions | |
>>>>>>>> | -0.948 |
Eisenhower | -0.821 |
selves | -0.792 |
Chavez | -0.792 |
agers | -0.774 |
Token | boot |
Token ID | 6297 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
theorem | +2.588 |
yss | +2.575 |
isoft | +2.489 |
ramid | +2.443 |
�� | +2.411 |
Neg logit contributions | |
>>>>>>>> | -2.994 |
Eisenhower | -2.629 |
selves | -2.579 |
Chavez | -2.557 |
agers | -2.502 |
Token | , |
Token ID | 11 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
theorem | +4.456 |
yss | +4.409 |
isoft | +4.283 |
ramid | +4.194 |
rons | +4.139 |
Neg logit contributions | |
>>>>>>>> | -4.274 |
Eisenhower | -3.699 |
selves | -3.643 |
Chavez | -3.576 |
agers | -3.516 |
Token | the |
Token ID | 262 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
>>>>>>>> | +0.276 |
Eisenhower | +0.239 |
Chavez | +0.230 |
selves | +0.230 |
ances | +0.227 |
Neg logit contributions | |
theorem | -0.293 |
yss | -0.292 |
isoft | -0.280 |
�� | -0.279 |
ramid | -0.278 |
Token | fan |
Token ID | 4336 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
>>>>>>>> | +1.148 |
Eisenhower | +1.009 |
selves | +0.978 |
Chavez | +0.978 |
ances | +0.956 |
Neg logit contributions | |
yss | -1.109 |
theorem | -1.095 |
�� | -1.060 |
isoft | -1.054 |
ramid | -1.031 |
Token | will |
Token ID | 481 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
theorem | +4.348 |
yss | +4.265 |
isoft | +4.150 |
rons | +4.076 |
ramid | +4.063 |
Neg logit contributions | |
>>>>>>>> | -3.522 |
Eisenhower | -2.987 |
selves | -2.942 |
Chavez | -2.861 |
agers | -2.822 |
Token | reverse |
Token ID | 9575 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
theorem | +2.218 |
yss | +2.187 |
isoft | +2.127 |
ramid | +2.086 |
rons | +2.068 |
Neg logit contributions | |
>>>>>>>> | -2.098 |
Eisenhower | -1.818 |
selves | -1.780 |
Chavez | -1.754 |
agers | -1.727 |
Token | for |
Token ID | 329 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
theorem | +1.133 |
yss | +1.133 |
isoft | +1.096 |
ramid | +1.083 |
�� | +1.077 |
Neg logit contributions | |
>>>>>>>> | -1.020 |
Eisenhower | -0.885 |
selves | -0.867 |
Chavez | -0.857 |
ances | -0.845 |
Token | 30 |
Token ID | 1542 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
>>>>>>>> | +1.665 |
Eisenhower | +1.435 |
selves | +1.415 |
Chavez | +1.398 |
agers | +1.387 |
Neg logit contributions | |
yss | -1.900 |
theorem | -1.896 |
isoft | -1.807 |
�� | -1.799 |
ramid | -1.793 |
Token | seconds |
Token ID | 4201 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
>>>>>>>> | +1.655 |
Eisenhower | +1.353 |
selves | +1.335 |
Chavez | +1.315 |
ances | +1.303 |
Neg logit contributions | |
theorem | -2.487 |
yss | -2.449 |
isoft | -2.419 |
ramid | -2.390 |
�� | -2.376 |
Token | when |
Token ID | 618 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
theorem | +0.810 |
yss | +0.810 |
isoft | +0.782 |
ramid | +0.776 |
�� | +0.774 |
Neg logit contributions | |
>>>>>>>> | -0.789 |
Eisenhower | -0.682 |
selves | -0.667 |
Chavez | -0.664 |
ances | -0.650 |
Token | filled |
Token ID | 5901 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
>>>>>>>> | +2.534 |
Eisenhower | +2.162 |
selves | +2.150 |
agers | +2.050 |
ances | +2.049 |
Neg logit contributions | |
theorem | -3.192 |
yss | -3.160 |
isoft | -3.112 |
�� | -3.073 |
ramid | -3.068 |
Token | the |
Token ID | 262 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
>>>>>>>> | +3.483 |
Eisenhower | +3.004 |
selves | +3.004 |
Chavez | +2.885 |
ances | +2.873 |
Neg logit contributions | |
theorem | -4.489 |
isoft | -4.461 |
�� | -4.458 |
ramid | -4.418 |
yss | -4.396 |
Token | roles |
Token ID | 9176 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
>>>>>>>> | +2.246 |
Eisenhower | +1.932 |
selves | +1.918 |
Chavez | +1.883 |
ances | +1.834 |
Neg logit contributions | |
yss | -2.405 |
theorem | -2.394 |
isoft | -2.383 |
�� | -2.363 |
ramid | -2.331 |
Token | we |
Token ID | 356 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
theorem | +0.511 |
yss | +0.507 |
isoft | +0.499 |
ramid | +0.492 |
�� | +0.489 |
Neg logit contributions | |
>>>>>>>> | -0.465 |
Eisenhower | -0.405 |
selves | -0.396 |
Chavez | -0.390 |
ances | -0.383 |
Token | were |
Token ID | 547 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
theorem | +2.388 |
yss | +2.363 |
isoft | +2.294 |
ramid | +2.256 |
rons | +2.232 |
Neg logit contributions | |
>>>>>>>> | -2.293 |
Eisenhower | -1.981 |
selves | -1.936 |
Chavez | -1.921 |
agers | -1.884 |
Token | going |
Token ID | 1016 |
Feature activation | -8.70e+00 |
Pos logit contributions | |
theorem | +4.083 |
yss | +4.030 |
isoft | +3.888 |
ramid | +3.814 |
rons | +3.812 |
Neg logit contributions | |
>>>>>>>> | -4.994 |
Eisenhower | -4.353 |
selves | -4.249 |
Chavez | -4.234 |
agers | -4.169 |
Token | for |
Token ID | 329 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
theorem | +5.438 |
yss | +5.257 |
isoft | +5.006 |
ramid | +4.988 |
�� | +4.907 |
Neg logit contributions | |
>>>>>>>> | -8.009 |
Eisenhower | -6.972 |
Chavez | -6.870 |
selves | -6.773 |
agers | -6.698 |
Token | . |
Token ID | 13 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
theorem | +1.474 |
yss | +1.457 |
isoft | +1.430 |
ramid | +1.402 |
�� | +1.386 |
Neg logit contributions | |
>>>>>>>> | -1.391 |
Eisenhower | -1.203 |
selves | -1.187 |
Chavez | -1.163 |
agers | -1.146 |
Token | Did |
Token ID | 7731 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
>>>>>>>> | +0.029 |
Eisenhower | +0.025 |
selves | +0.025 |
Chavez | +0.024 |
ances | +0.023 |
Neg logit contributions | |
theorem | -0.038 |
yss | -0.037 |
isoft | -0.036 |
ramid | -0.036 |
�� | -0.036 |
Token | you |
Token ID | 345 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
theorem | +0.985 |
yss | +0.972 |
isoft | +0.949 |
ramid | +0.931 |
�� | +0.920 |
Neg logit contributions | |
>>>>>>>> | -0.915 |
Eisenhower | -0.792 |
selves | -0.778 |
Chavez | -0.764 |
agers | -0.754 |
Token | have |
Token ID | 423 |
Feature activation | -6.82e+00 |
Pos logit contributions | |
yss | +1.197 |
theorem | +1.196 |
isoft | +1.156 |
�� | +1.143 |
ramid | +1.140 |
Neg logit contributions | |
>>>>>>>> | -0.986 |
Eisenhower | -0.844 |
selves | -0.829 |
Chavez | -0.811 |
agers | -0.803 |
Token | this |
Token ID | 428 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
theorem | +2.352 |
yss | +2.329 |
isoft | +2.260 |
ramid | +2.219 |
rons | +2.190 |
Neg logit contributions | |
>>>>>>>> | -2.210 |
Eisenhower | -1.911 |
selves | -1.874 |
Chavez | -1.848 |
agers | -1.815 |
Token | is |
Token ID | 318 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
theorem | +1.122 |
yss | +1.113 |
isoft | +1.080 |
ramid | +1.061 |
rons | +1.047 |
Neg logit contributions | |
>>>>>>>> | -1.013 |
Eisenhower | -0.873 |
selves | -0.856 |
Chavez | -0.844 |
agers | -0.828 |
Token | He |
Token ID | 679 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
>>>>>>>> | +0.530 |
Eisenhower | +0.464 |
selves | +0.448 |
Chavez | +0.446 |
agers | +0.435 |
Neg logit contributions | |
yss | -0.583 |
theorem | -0.573 |
isoft | -0.566 |
ramid | -0.559 |
�� | -0.550 |
Token | ikes |
Token ID | 7938 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
yss | +1.845 |
theorem | +1.836 |
isoft | +1.775 |
ramid | +1.736 |
rons | +1.723 |
Neg logit contributions | |
>>>>>>>> | -1.754 |
Eisenhower | -1.500 |
Chavez | -1.469 |
selves | -1.467 |
א | -1.418 |
Token | ' |
Token ID | 6 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
theorem | +0.330 |
yss | +0.328 |
isoft | +0.319 |
ramid | +0.314 |
rons | +0.311 |
Neg logit contributions | |
>>>>>>>> | -0.224 |
Eisenhower | -0.188 |
selves | -0.184 |
Chavez | -0.181 |
agers | -0.177 |
Token | intention |
Token ID | 6778 |
Feature activation | -8.52e+00 |
Pos logit contributions | |
theorem | +1.780 |
yss | +1.758 |
isoft | +1.699 |
ramid | +1.664 |
rons | +1.640 |
Neg logit contributions | |
>>>>>>>> | -2.097 |
Eisenhower | -1.843 |
selves | -1.811 |
Chavez | -1.790 |
agers | -1.762 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
theorem | +6.238 |
yss | +5.960 |
isoft | +5.714 |
rons | +5.604 |
ramid | +5.525 |
Neg logit contributions | |
>>>>>>>> | -7.095 |
Eisenhower | -6.130 |
selves | -6.069 |
Chavez | -5.998 |
agers | -5.939 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
theorem | +0.928 |
yss | +0.925 |
isoft | +0.899 |
ramid | +0.890 |
�� | +0.878 |
Neg logit contributions | |
>>>>>>>> | -0.778 |
Eisenhower | -0.676 |
selves | -0.655 |
Chavez | -0.650 |
ances | -0.627 |
Token |
|
Token ID | 198 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
theorem | +1.144 |
yss | +1.131 |
isoft | +1.099 |
ramid | +1.083 |
rons | +1.072 |
Neg logit contributions | |
>>>>>>>> | -0.930 |
Eisenhower | -0.792 |
selves | -0.776 |
Chavez | -0.766 |
agers | -0.753 |
Token | He |
Token ID | 1544 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
theorem | +1.719 |
yss | +1.703 |
isoft | +1.652 |
ramid | +1.623 |
�� | +1.604 |
Neg logit contributions | |
>>>>>>>> | -1.644 |
Eisenhower | -1.421 |
selves | -1.393 |
Chavez | -1.373 |
agers | -1.350 |
Token | ikes |
Token ID | 7938 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
theorem | +3.643 |
yss | +3.627 |
isoft | +3.502 |
ramid | +3.411 |
rons | +3.403 |
Neg logit contributions | |
>>>>>>>> | -3.344 |
Eisenhower | -2.849 |
selves | -2.809 |
Chavez | -2.764 |
agers | -2.695 |
Token | f |
Token ID | 69 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
theorem | +1.192 |
yss | +1.172 |
isoft | +1.139 |
ramid | +1.124 |
�� | +1.115 |
Neg logit contributions | |
>>>>>>>> | -1.056 |
Eisenhower | -0.903 |
selves | -0.891 |
Chavez | -0.873 |
agers | -0.863 |
Token | () |
Token ID | 3419 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
>>>>>>>> | +0.527 |
Eisenhower | +0.459 |
selves | +0.451 |
Chavez | +0.443 |
ances | +0.442 |
Neg logit contributions | |
theorem | -0.492 |
yss | -0.487 |
isoft | -0.468 |
ramid | -0.459 |
�� | -0.458 |
Token | == |
Token ID | 6624 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
theorem | +1.326 |
yss | +1.314 |
isoft | +1.270 |
ramid | +1.244 |
rons | +1.229 |
Neg logit contributions | |
>>>>>>>> | -1.511 |
Eisenhower | -1.322 |
selves | -1.297 |
Chavez | -1.282 |
agers | -1.261 |
Token | float |
Token ID | 12178 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
>>>>>>>> | +1.942 |
Eisenhower | +1.657 |
Chavez | +1.590 |
selves | +1.575 |
ances | +1.538 |
Neg logit contributions | |
theorem | -2.268 |
yss | -2.251 |
isoft | -2.186 |
ramid | -2.180 |
rons | -2.155 |
Token | ( |
Token ID | 7 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
theorem | +2.881 |
yss | +2.851 |
isoft | +2.764 |
ramid | +2.710 |
rons | +2.672 |
Neg logit contributions | |
>>>>>>>> | -2.988 |
Eisenhower | -2.607 |
selves | -2.560 |
Chavez | -2.526 |
agers | -2.482 |
Token | count |
Token ID | 9127 |
Feature activation | -7.72e+00 |
Pos logit contributions | |
theorem | +2.835 |
yss | +2.814 |
isoft | +2.725 |
ramid | +2.663 |
rons | +2.626 |
Neg logit contributions | |
>>>>>>>> | -3.149 |
Eisenhower | -2.765 |
selves | -2.715 |
Chavez | -2.687 |
agers | -2.636 |
Token | )); |
Token ID | 18125 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
theorem | +5.569 |
yss | +5.512 |
isoft | +5.308 |
ramid | +5.188 |
rons | +5.166 |
Neg logit contributions | |
>>>>>>>> | -6.366 |
Eisenhower | -5.643 |
Chavez | -5.556 |
selves | -5.545 |
א | -5.367 |
Token | RAW |
Token ID | 33782 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
theorem | +2.395 |
yss | +2.366 |
isoft | +2.302 |
ramid | +2.252 |
rons | +2.225 |
Neg logit contributions | |
>>>>>>>> | -2.120 |
Eisenhower | -1.835 |
selves | -1.803 |
Chavez | -1.772 |
agers | -1.746 |
Token | _ |
Token ID | 62 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
theorem | +0.598 |
yss | +0.590 |
isoft | +0.567 |
ramid | +0.553 |
�� | +0.544 |
Neg logit contributions | |
>>>>>>>> | -0.958 |
Eisenhower | -0.856 |
selves | -0.843 |
Chavez | -0.834 |
agers | -0.823 |
Token | ASS |
Token ID | 10705 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
theorem | +0.953 |
yss | +0.945 |
isoft | +0.913 |
ramid | +0.893 |
rons | +0.879 |
Neg logit contributions | |
>>>>>>>> | -1.139 |
Eisenhower | -1.007 |
selves | -0.990 |
Chavez | -0.979 |
agers | -0.962 |
Token | ERT |
Token ID | 17395 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
>>>>>>>> | +1.718 |
Eisenhower | +1.467 |
selves | +1.427 |
Chavez | +1.401 |
agers | +1.389 |
Neg logit contributions | |
theorem | -1.831 |
yss | -1.817 |
isoft | -1.773 |
�� | -1.751 |
ramid | -1.737 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
>>>>>>>> | +3.431 |
Eisenhower | +2.980 |
Chavez | +2.934 |
selves | +2.929 |
ances | +2.859 |
Neg logit contributions | |
yss | -3.703 |
isoft | -3.683 |
theorem | -3.659 |
ramid | -3.575 |
�� | -3.573 |
Token | Brook |
Token ID | 7590 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
theorem | +0.796 |
yss | +0.790 |
isoft | +0.769 |
ramid | +0.759 |
�� | +0.745 |
Neg logit contributions | |
>>>>>>>> | -0.867 |
Eisenhower | -0.764 |
Chavez | -0.745 |
selves | -0.742 |
agers | -0.721 |
Token | had |
Token ID | 550 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
theorem | +1.315 |
yss | +1.303 |
isoft | +1.267 |
ramid | +1.247 |
�� | +1.230 |
Neg logit contributions | |
>>>>>>>> | -1.062 |
Eisenhower | -0.907 |
selves | -0.887 |
Chavez | -0.875 |
agers | -0.857 |
Token | taken |
Token ID | 2077 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
theorem | +3.676 |
yss | +3.618 |
isoft | +3.487 |
ramid | +3.424 |
rons | +3.414 |
Neg logit contributions | |
>>>>>>>> | -3.855 |
Eisenhower | -3.349 |
selves | -3.305 |
Chavez | -3.230 |
agers | -3.206 |
Token | a |
Token ID | 257 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
theorem | +2.032 |
yss | +2.012 |
isoft | +1.951 |
ramid | +1.916 |
rons | +1.893 |
Neg logit contributions | |
>>>>>>>> | -1.873 |
Eisenhower | -1.617 |
selves | -1.586 |
Chavez | -1.562 |
agers | -1.535 |
Token | knee |
Token ID | 10329 |
Feature activation | -7.75e+00 |
Pos logit contributions | |
theorem | +3.173 |
yss | +3.127 |
isoft | +3.031 |
ramid | +2.976 |
rons | +2.944 |
Neg logit contributions | |
>>>>>>>> | -2.929 |
Eisenhower | -2.528 |
selves | -2.486 |
Chavez | -2.437 |
agers | -2.410 |
Token | when |
Token ID | 618 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
theorem | +5.613 |
yss | +5.475 |
isoft | +5.222 |
rons | +5.176 |
ramid | +5.091 |
Neg logit contributions | |
>>>>>>>> | -6.501 |
Eisenhower | -5.685 |
selves | -5.590 |
agers | -5.466 |
Chavez | -5.462 |
Token | he |
Token ID | 339 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
theorem | +2.093 |
yss | +2.073 |
isoft | +2.010 |
ramid | +1.974 |
rons | +1.947 |
Neg logit contributions | |
>>>>>>>> | -2.022 |
Eisenhower | -1.753 |
selves | -1.718 |
Chavez | -1.696 |
agers | -1.666 |
Token | wasn |
Token ID | 2492 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
theorem | +0.097 |
yss | +0.096 |
isoft | +0.094 |
�� | +0.093 |
ramid | +0.092 |
Neg logit contributions | |
>>>>>>>> | -0.094 |
Eisenhower | -0.082 |
Chavez | -0.081 |
selves | -0.080 |
agers | -0.078 |
Token | � |
Token ID | 447 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
theorem | +0.950 |
yss | +0.942 |
isoft | +0.916 |
ramid | +0.902 |
�� | +0.891 |
Neg logit contributions | |
>>>>>>>> | -0.727 |
Eisenhower | -0.617 |
selves | -0.603 |
Chavez | -0.593 |
agers | -0.581 |
Token | � |
Token ID | 247 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
theorem | +2.239 |
yss | +2.219 |
isoft | +2.143 |
ramid | +2.096 |
�� | +2.074 |
Neg logit contributions | |
>>>>>>>> | -2.639 |
Eisenhower | -2.322 |
selves | -2.282 |
Chavez | -2.261 |
agers | -2.222 |
Token | Summers |
Token ID | 36776 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
>>>>>>>> | +0.919 |
Eisenhower | +0.797 |
Chavez | +0.771 |
selves | +0.765 |
agers | +0.753 |
Neg logit contributions | |
yss | -0.978 |
theorem | -0.976 |
isoft | -0.945 |
ramid | -0.941 |
�� | -0.921 |
Token | and |
Token ID | 290 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
>>>>>>>> | +1.580 |
Eisenhower | +1.356 |
selves | +1.323 |
Chavez | +1.311 |
agers | +1.280 |
Neg logit contributions | |
theorem | -1.811 |
yss | -1.804 |
isoft | -1.757 |
ramid | -1.756 |
rons | -1.698 |
Token | A |
Token ID | 317 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
theorem | +2.170 |
yss | +2.147 |
isoft | +2.087 |
ramid | +2.048 |
rons | +2.032 |
Neg logit contributions | |
>>>>>>>> | -1.733 |
Eisenhower | -1.474 |
selves | -1.448 |
Chavez | -1.417 |
agers | -1.397 |
Token | ery |
Token ID | 1924 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
theorem | +1.957 |
yss | +1.936 |
isoft | +1.881 |
ramid | +1.845 |
�� | +1.827 |
Neg logit contributions | |
>>>>>>>> | -1.793 |
Eisenhower | -1.547 |
selves | -1.518 |
Chavez | -1.495 |
agers | -1.469 |
Token | n |
Token ID | 77 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
>>>>>>>> | +1.219 |
Eisenhower | +1.053 |
Chavez | +1.021 |
selves | +1.018 |
agers | +0.997 |
Neg logit contributions | |
theorem | -1.301 |
yss | -1.271 |
isoft | -1.250 |
ramid | -1.225 |
�� | -1.225 |
Token | Sun |
Token ID | 3825 |
Feature activation | -8.69e+00 |
Pos logit contributions | |
theorem | +0.795 |
yss | +0.783 |
isoft | +0.766 |
ramid | +0.757 |
�� | +0.744 |
Neg logit contributions | |
>>>>>>>> | -0.743 |
Eisenhower | -0.646 |
selves | -0.630 |
Chavez | -0.622 |
agers | -0.609 |
Token | . |
Token ID | 13 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
theorem | +7.055 |
yss | +7.029 |
isoft | +6.624 |
omi | +6.522 |
ramid | +6.352 |
Neg logit contributions | |
>>>>>>>> | -6.352 |
selves | -5.399 |
Eisenhower | -5.295 |
WithNo | -5.193 |
Chavez | -5.184 |
Token | Though |
Token ID | 7486 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
theorem | +0.510 |
yss | +0.506 |
isoft | +0.492 |
ramid | +0.485 |
�� | +0.479 |
Neg logit contributions | |
>>>>>>>> | -0.421 |
Eisenhower | -0.362 |
selves | -0.353 |
Chavez | -0.350 |
agers | -0.338 |
Token | shows |
Token ID | 2523 |
Feature activation | +8.06e+00 |
Pos logit contributions | |
theorem | +2.720 |
yss | +2.689 |
isoft | +2.600 |
ramid | +2.549 |
rons | +2.533 |
Neg logit contributions | |
>>>>>>>> | -2.548 |
Eisenhower | -2.202 |
selves | -2.163 |
Chavez | -2.123 |
agers | -2.092 |
Token | like |
Token ID | 588 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
>>>>>>>> | +4.650 |
Eisenhower | +4.002 |
Chavez | +3.846 |
selves | +3.827 |
agers | +3.709 |
Neg logit contributions | |
yss | -7.629 |
theorem | -7.534 |
isoft | -7.371 |
ramid | -7.347 |
�� | -7.236 |
Token | Or |
Token ID | 1471 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
>>>>>>>> | +3.803 |
Eisenhower | +3.294 |
selves | +3.205 |
Chavez | +3.202 |
ances | +3.100 |
Neg logit contributions | |
theorem | -4.436 |
yss | -4.386 |
isoft | -4.278 |
ramid | -4.270 |
�� | -4.248 |