Token | er |
Token ID | 263 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
GOODMAN | +0.620 |
cast | +0.617 |
CAST | +0.600 |
fisher | +0.595 |
#$ | +0.582 |
Neg logit contributions | |
ificate | -1.054 |
ills | -0.999 |
riet | -0.989 |
Downloadha | -0.978 |
reme | -0.976 |
Token | - |
Token ID | 12 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ificate | +0.433 |
ills | +0.406 |
riet | +0.399 |
Downloadha | +0.394 |
reme | +0.393 |
Neg logit contributions | |
GOODMAN | -0.419 |
cast | -0.417 |
CAST | -0.408 |
fisher | -0.405 |
#$ | -0.399 |
Token | blocks |
Token ID | 27372 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
GOODMAN | +0.345 |
cast | +0.342 |
CAST | +0.335 |
fisher | +0.334 |
#$ | +0.327 |
Neg logit contributions | |
ificate | -0.379 |
ills | -0.356 |
riet | -0.351 |
Downloadha | -0.347 |
reme | -0.346 |
Token | / |
Token ID | 14 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
ificate | +0.429 |
ills | +0.403 |
riet | +0.395 |
Downloadha | +0.390 |
reme | +0.390 |
Neg logit contributions | |
GOODMAN | -0.424 |
cast | -0.421 |
CAST | -0.414 |
fisher | -0.410 |
#$ | -0.403 |
Token | ) |
Token ID | 1267 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
ificate | +0.966 |
ills | +0.908 |
riet | +0.890 |
reme | +0.879 |
Downloadha | +0.878 |
Neg logit contributions | |
GOODMAN | -0.975 |
cast | -0.960 |
CAST | -0.946 |
fisher | -0.940 |
#$ | -0.926 |
Token | Finally |
Token ID | 9461 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
GOODMAN | +0.518 |
cast | +0.517 |
CAST | +0.506 |
fisher | +0.502 |
#$ | +0.494 |
Neg logit contributions | |
ificate | -0.522 |
ills | -0.489 |
riet | -0.480 |
Downloadha | -0.474 |
reme | -0.474 |
Token | -- |
Token ID | 438 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
cast | +4.738 |
GOODMAN | +4.685 |
fisher | +4.604 |
CAST | +4.553 |
Zimmer | +4.511 |
Neg logit contributions | |
ificate | -6.364 |
riet | -6.197 |
Downloadha | -6.059 |
ills | -6.059 |
reme | -5.910 |
Token | at |
Token ID | 265 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
cast | +1.741 |
GOODMAN | +1.732 |
CAST | +1.701 |
fisher | +1.688 |
#$ | +1.661 |
Neg logit contributions | |
ificate | -1.566 |
ills | -1.458 |
riet | -1.442 |
Downloadha | -1.428 |
reme | -1.412 |
Token | some |
Token ID | 617 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
ificate | +0.638 |
ills | +0.598 |
riet | +0.588 |
reme | +0.585 |
iously | +0.581 |
Neg logit contributions | |
GOODMAN | -0.503 |
cast | -0.499 |
CAST | -0.489 |
fisher | -0.483 |
#$ | -0.472 |
Token | point |
Token ID | 966 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
GOODMAN | +0.748 |
cast | +0.747 |
CAST | +0.725 |
fisher | +0.719 |
#$ | +0.703 |
Neg logit contributions | |
ificate | -1.229 |
ills | -1.165 |
riet | -1.153 |
Downloadha | -1.142 |
reme | -1.138 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
ificate | +0.954 |
ills | +0.898 |
riet | +0.880 |
iously | +0.872 |
reme | +0.871 |
Neg logit contributions | |
GOODMAN | -0.850 |
cast | -0.849 |
CAST | -0.833 |
fisher | -0.819 |
#$ | -0.811 |
Token | thereof |
Token ID | 15370 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
cast | +1.378 |
GOODMAN | +1.366 |
CAST | +1.341 |
fisher | +1.336 |
#$ | +1.318 |
Neg logit contributions | |
ificate | -1.314 |
ills | -1.217 |
riet | -1.209 |
Downloadha | -1.187 |
reme | -1.185 |
Token | . |
Token ID | 13 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ificate | +0.728 |
ills | +0.680 |
riet | +0.669 |
Downloadha | +0.661 |
reme | +0.659 |
Neg logit contributions | |
GOODMAN | -0.774 |
cast | -0.771 |
CAST | -0.756 |
fisher | -0.751 |
#$ | -0.740 |
Token |
|
Token ID | 198 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
ificate | +0.659 |
ills | +0.618 |
riet | +0.607 |
reme | +0.600 |
Downloadha | +0.599 |
Neg logit contributions | |
GOODMAN | -0.633 |
cast | -0.631 |
CAST | -0.618 |
fisher | -0.615 |
#$ | -0.605 |
Token |
|
Token ID | 198 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
ificate | +1.932 |
ills | +1.779 |
iously | +1.727 |
iss | +1.714 |
riet | +1.713 |
Neg logit contributions | |
GOODMAN | -2.253 |
fisher | -2.174 |
cast | -2.160 |
CAST | -2.153 |
� | -2.151 |
Token | Article |
Token ID | 14906 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
ificate | +1.657 |
ills | +1.545 |
riet | +1.493 |
iously | +1.486 |
iss | +1.484 |
Neg logit contributions | |
GOODMAN | -2.293 |
fisher | -2.248 |
cast | -2.215 |
autos | -2.199 |
Zimmer | -2.174 |
Token | IV |
Token ID | 8363 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ificate | +2.146 |
ills | +2.000 |
riet | +1.976 |
iously | +1.947 |
reme | +1.946 |
Neg logit contributions | |
GOODMAN | -2.099 |
cast | -2.091 |
CAST | -2.068 |
fisher | -2.039 |
#$ | -2.012 |
Token | , |
Token ID | 11 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
cast | +5.074 |
GOODMAN | +5.059 |
fisher | +4.914 |
CAST | +4.875 |
Zimmer | +4.817 |
Neg logit contributions | |
ificate | -5.603 |
Downloadha | -5.259 |
riet | -5.238 |
ills | -5.180 |
reme | -5.055 |
Token | Section |
Token ID | 7275 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
GOODMAN | +1.223 |
cast | +1.219 |
CAST | +1.194 |
fisher | +1.188 |
#$ | +1.169 |
Neg logit contributions | |
ificate | -1.005 |
ills | -0.932 |
riet | -0.919 |
Downloadha | -0.911 |
reme | -0.900 |
Token | 2 |
Token ID | 362 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
ificate | +0.858 |
ills | +0.806 |
riet | +0.792 |
reme | +0.781 |
iously | +0.780 |
Neg logit contributions | |
GOODMAN | -0.813 |
cast | -0.811 |
CAST | -0.800 |
fisher | -0.787 |
#$ | -0.781 |
Token | begins |
Token ID | 6140 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
GOODMAN | +1.321 |
cast | +1.320 |
CAST | +1.291 |
fisher | +1.283 |
#$ | +1.261 |
Neg logit contributions | |
ificate | -1.291 |
ills | -1.207 |
riet | -1.190 |
Downloadha | -1.177 |
reme | -1.170 |
Token | with |
Token ID | 351 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
GOODMAN | +0.704 |
cast | +0.701 |
CAST | +0.688 |
fisher | +0.682 |
#$ | +0.673 |
Neg logit contributions | |
ificate | -0.675 |
ills | -0.631 |
riet | -0.620 |
Downloadha | -0.612 |
reme | -0.610 |
Token | p |
Token ID | 79 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
GOODMAN | +0.852 |
cast | +0.848 |
CAST | +0.831 |
fisher | +0.828 |
#$ | +0.811 |
Neg logit contributions | |
ificate | -0.837 |
ills | -0.784 |
riet | -0.773 |
Downloadha | -0.762 |
reme | -0.760 |
Token | DM |
Token ID | 23127 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
GOODMAN | +0.369 |
cast | +0.365 |
fisher | +0.358 |
CAST | +0.358 |
Zimmer | +0.350 |
Neg logit contributions | |
ificate | -0.380 |
ills | -0.358 |
riet | -0.353 |
reme | -0.347 |
Downloadha | -0.347 |
Token | 2 |
Token ID | 17 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
GOODMAN | +0.066 |
cast | +0.066 |
CAST | +0.064 |
fisher | +0.064 |
Zimmer | +0.063 |
Neg logit contributions | |
ificate | -0.066 |
ills | -0.062 |
riet | -0.061 |
reme | -0.060 |
Downloadha | -0.060 |
Token | — |
Token ID | 851 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
GOODMAN | +0.656 |
cast | +0.652 |
CAST | +0.639 |
fisher | +0.635 |
#$ | +0.621 |
Neg logit contributions | |
ificate | -0.741 |
ills | -0.698 |
riet | -0.687 |
reme | -0.678 |
Downloadha | -0.676 |
Token | V |
Token ID | 569 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
GOODMAN | +0.758 |
cast | +0.756 |
CAST | +0.740 |
fisher | +0.735 |
#$ | +0.722 |
Neg logit contributions | |
ificate | -0.809 |
ills | -0.757 |
riet | -0.748 |
Downloadha | -0.740 |
reme | -0.735 |
Token | INE |
Token ID | 8881 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ificate | +0.294 |
ills | +0.277 |
riet | +0.270 |
reme | +0.268 |
iss | +0.265 |
Neg logit contributions | |
GOODMAN | -0.334 |
cast | -0.331 |
CAST | -0.325 |
fisher | -0.324 |
#$ | -0.318 |
Token | : |
Token ID | 25 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
GOODMAN | +5.058 |
cast | +5.048 |
CAST | +4.994 |
fisher | +4.870 |
#$ | +4.820 |
Neg logit contributions | |
ificate | -5.384 |
Downloadha | -5.046 |
ills | -5.006 |
riet | -5.002 |
iously | -4.857 |
Token | Im |
Token ID | 1846 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
ificate | +0.617 |
ills | +0.582 |
riet | +0.571 |
reme | +0.567 |
iously | +0.562 |
Neg logit contributions | |
GOODMAN | -0.538 |
cast | -0.536 |
fisher | -0.524 |
CAST | -0.521 |
#$ | -0.509 |
Token | Justin |
Token ID | 33229 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ificate | +0.055 |
ills | +0.052 |
riet | +0.051 |
reme | +0.050 |
Downloadha | +0.050 |
Neg logit contributions | |
GOODMAN | -0.053 |
cast | -0.053 |
CAST | -0.052 |
fisher | -0.051 |
#$ | -0.050 |
Token | Ray |
Token ID | 19591 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
GOODMAN | +0.546 |
cast | +0.545 |
CAST | +0.534 |
fisher | +0.532 |
#$ | +0.522 |
Neg logit contributions | |
ificate | -0.462 |
ills | -0.430 |
riet | -0.423 |
Downloadha | -0.416 |
reme | -0.416 |
Token | (@ |
Token ID | 4275 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
cast | +1.721 |
GOODMAN | +1.716 |
CAST | +1.686 |
fisher | +1.669 |
#$ | +1.647 |
Neg logit contributions | |
ificate | -1.326 |
ills | -1.227 |
riet | -1.209 |
Downloadha | -1.198 |
reme | -1.186 |
Token | far |
Token ID | 1290 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
ificate | +0.744 |
ills | +0.699 |
iously | +0.676 |
riet | +0.676 |
iss | +0.673 |
Neg logit contributions | |
GOODMAN | -0.811 |
cast | -0.803 |
CAST | -0.796 |
fisher | -0.780 |
#$ | -0.773 |
Token | . |
Token ID | 13 |
Feature activation | -5.99e-02 |
Pos logit contributions | |
ificate | +1.745 |
ills | +1.635 |
riet | +1.589 |
Downloadha | +1.577 |
reme | +1.577 |
Neg logit contributions | |
GOODMAN | -1.808 |
cast | -1.803 |
CAST | -1.770 |
fisher | -1.757 |
#$ | -1.731 |
Token |
|
Token ID | 198 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
ificate | +0.183 |
ills | +0.171 |
riet | +0.167 |
Downloadha | +0.165 |
iously | +0.165 |
Neg logit contributions | |
GOODMAN | -0.189 |
cast | -0.188 |
CAST | -0.184 |
fisher | -0.184 |
#$ | -0.181 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
GOODMAN | +0.213 |
cast | +0.211 |
CAST | +0.207 |
fisher | +0.207 |
#$ | +0.202 |
Neg logit contributions | |
ificate | -0.220 |
ills | -0.206 |
riet | -0.202 |
reme | -0.199 |
Downloadha | -0.199 |
Token | And |
Token ID | 1870 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
GOODMAN | +0.080 |
cast | +0.079 |
fisher | +0.078 |
CAST | +0.078 |
#$ | +0.077 |
Neg logit contributions | |
ificate | -0.064 |
ills | -0.060 |
riet | -0.059 |
Downloadha | -0.058 |
reme | -0.058 |
Token | finally |
Token ID | 3443 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
GOODMAN | +0.761 |
cast | +0.760 |
CAST | +0.743 |
fisher | +0.738 |
#$ | +0.725 |
Neg logit contributions | |
ificate | -0.825 |
ills | -0.774 |
riet | -0.763 |
Downloadha | -0.754 |
reme | -0.751 |
Token | , |
Token ID | 11 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
GOODMAN | +4.497 |
cast | +4.477 |
CAST | +4.362 |
fisher | +4.325 |
Zimmer | +4.264 |
Neg logit contributions | |
ificate | -5.720 |
riet | -5.435 |
ills | -5.360 |
Downloadha | -5.310 |
reme | -5.250 |
Token | please |
Token ID | 3387 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
GOODMAN | +1.582 |
cast | +1.581 |
CAST | +1.543 |
fisher | +1.534 |
#$ | +1.504 |
Neg logit contributions | |
ificate | -1.782 |
ills | -1.674 |
riet | -1.655 |
Downloadha | -1.636 |
reme | -1.628 |
Token | have |
Token ID | 423 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
ificate | +0.600 |
ills | +0.561 |
riet | +0.551 |
reme | +0.546 |
iously | +0.545 |
Neg logit contributions | |
GOODMAN | -0.563 |
cast | -0.560 |
CAST | -0.551 |
fisher | -0.541 |
#$ | -0.538 |
Token | a |
Token ID | 257 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
GOODMAN | +0.052 |
cast | +0.052 |
CAST | +0.051 |
fisher | +0.050 |
#$ | +0.050 |
Neg logit contributions | |
ificate | -0.063 |
ills | -0.059 |
riet | -0.059 |
iously | -0.058 |
Downloadha | -0.057 |
Token | look |
Token ID | 804 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
GOODMAN | +0.301 |
cast | +0.299 |
CAST | +0.289 |
fisher | +0.284 |
#$ | +0.279 |
Neg logit contributions | |
ificate | -0.673 |
ills | -0.639 |
riet | -0.636 |
reme | -0.627 |
Downloadha | -0.626 |
Token | it |
Token ID | 340 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
cast | +1.898 |
GOODMAN | +1.896 |
CAST | +1.853 |
fisher | +1.842 |
#$ | +1.808 |
Neg logit contributions | |
ificate | -1.932 |
ills | -1.800 |
riet | -1.785 |
Downloadha | -1.759 |
reme | -1.756 |
Token | is |
Token ID | 318 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
GOODMAN | +0.960 |
cast | +0.957 |
CAST | +0.938 |
fisher | +0.930 |
#$ | +0.916 |
Neg logit contributions | |
ificate | -0.970 |
ills | -0.910 |
riet | -0.895 |
Downloadha | -0.884 |
reme | -0.880 |
Token | , |
Token ID | 11 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
GOODMAN | +1.167 |
cast | +1.166 |
CAST | +1.140 |
fisher | +1.132 |
#$ | +1.113 |
Neg logit contributions | |
ificate | -1.235 |
ills | -1.158 |
riet | -1.142 |
Downloadha | -1.129 |
reme | -1.124 |
Token | without |
Token ID | 1231 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
ificate | +0.174 |
ills | +0.163 |
riet | +0.161 |
Downloadha | +0.159 |
reme | +0.158 |
Neg logit contributions | |
GOODMAN | -0.156 |
cast | -0.155 |
CAST | -0.152 |
fisher | -0.149 |
#$ | -0.148 |
Token | further |
Token ID | 2252 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
ificate | +0.886 |
ills | +0.833 |
riet | +0.821 |
Downloadha | +0.811 |
reme | +0.805 |
Neg logit contributions | |
cast | -0.799 |
GOODMAN | -0.798 |
CAST | -0.783 |
fisher | -0.773 |
#$ | -0.763 |
Token | ado |
Token ID | 50129 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
GOODMAN | +1.010 |
cast | +1.009 |
CAST | +0.977 |
fisher | +0.969 |
#$ | +0.943 |
Neg logit contributions | |
ificate | -1.782 |
ills | -1.689 |
riet | -1.674 |
Downloadha | -1.660 |
reme | -1.655 |
Token | : |
Token ID | 25 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
cast | +4.441 |
GOODMAN | +4.350 |
CAST | +4.315 |
fisher | +4.215 |
·· | +4.162 |
Neg logit contributions | |
ificate | -5.669 |
riet | -5.453 |
ills | -5.381 |
Downloadha | -5.328 |
reme | -5.257 |
Token | one |
Token ID | 530 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
cast | +2.130 |
GOODMAN | +2.119 |
CAST | +2.077 |
fisher | +2.067 |
#$ | +2.029 |
Neg logit contributions | |
ificate | -2.452 |
ills | -2.305 |
riet | -2.277 |
Downloadha | -2.254 |
reme | -2.244 |
Token | man |
Token ID | 582 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
cast | +1.155 |
GOODMAN | +1.152 |
CAST | +1.129 |
fisher | +1.125 |
#$ | +1.106 |
Neg logit contributions | |
ificate | -1.047 |
ills | -0.975 |
riet | -0.960 |
Downloadha | -0.952 |
reme | -0.944 |
Token | � |
Token ID | 447 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ificate | +0.045 |
ills | +0.042 |
riet | +0.042 |
Downloadha | +0.041 |
reme | +0.041 |
Neg logit contributions | |
GOODMAN | -0.043 |
cast | -0.042 |
CAST | -0.042 |
fisher | -0.041 |
#$ | -0.041 |
Token | � |
Token ID | 247 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
GOODMAN | +0.387 |
cast | +0.383 |
CAST | +0.375 |
fisher | +0.371 |
#$ | +0.362 |
Neg logit contributions | |
ificate | -0.496 |
ills | -0.470 |
riet | -0.463 |
reme | -0.456 |
Downloadha | -0.454 |
Token | sticks |
Token ID | 16461 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
GOODMAN | +1.090 |
cast | +1.088 |
CAST | +1.061 |
fisher | +1.055 |
#$ | +1.035 |
Neg logit contributions | |
ificate | -1.281 |
ills | -1.206 |
riet | -1.189 |
Downloadha | -1.176 |
reme | -1.171 |
Token | . |
Token ID | 13 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
ificate | +0.405 |
ills | +0.381 |
riet | +0.371 |
Downloadha | +0.367 |
iously | +0.367 |
Neg logit contributions | |
GOODMAN | -0.430 |
cast | -0.426 |
CAST | -0.420 |
fisher | -0.416 |
#$ | -0.409 |
Token |
|
Token ID | 198 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
GOODMAN | +0.205 |
cast | +0.205 |
CAST | +0.201 |
fisher | +0.200 |
#$ | +0.196 |
Neg logit contributions | |
ificate | -0.202 |
ills | -0.190 |
riet | -0.185 |
Downloadha | -0.183 |
reme | -0.183 |
Token |
|
Token ID | 198 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
GOODMAN | +0.749 |
cast | +0.747 |
CAST | +0.731 |
fisher | +0.726 |
#$ | +0.713 |
Neg logit contributions | |
ificate | -0.802 |
ills | -0.752 |
riet | -0.742 |
Downloadha | -0.733 |
reme | -0.730 |
Token | And |
Token ID | 1870 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
GOODMAN | +0.674 |
cast | +0.669 |
fisher | +0.656 |
CAST | +0.655 |
Zimmer | +0.644 |
Neg logit contributions | |
ificate | -0.553 |
ills | -0.515 |
riet | -0.505 |
Downloadha | -0.499 |
reme | -0.496 |
Token | finally |
Token ID | 3443 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
GOODMAN | +0.457 |
cast | +0.456 |
CAST | +0.446 |
fisher | +0.442 |
#$ | +0.436 |
Neg logit contributions | |
ificate | -0.508 |
ills | -0.478 |
riet | -0.470 |
Downloadha | -0.465 |
reme | -0.463 |
Token | , |
Token ID | 11 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
cast | +4.252 |
GOODMAN | +4.224 |
CAST | +4.122 |
fisher | +4.093 |
cks | +3.967 |
Neg logit contributions | |
ificate | -5.716 |
riet | -5.423 |
ills | -5.352 |
iously | -5.263 |
reme | -5.232 |
Token | as |
Token ID | 355 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
GOODMAN | +1.545 |
cast | +1.545 |
CAST | +1.507 |
fisher | +1.500 |
#$ | +1.470 |
Neg logit contributions | |
ificate | -1.744 |
ills | -1.637 |
riet | -1.618 |
Downloadha | -1.599 |
reme | -1.593 |
Token | for |
Token ID | 329 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
GOODMAN | +0.356 |
cast | +0.353 |
CAST | +0.348 |
fisher | +0.344 |
#$ | +0.339 |
Neg logit contributions | |
ificate | -0.369 |
ills | -0.347 |
riet | -0.340 |
Downloadha | -0.337 |
reme | -0.335 |
Token | admins |
Token ID | 44563 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
GOODMAN | +0.890 |
cast | +0.889 |
CAST | +0.872 |
fisher | +0.862 |
#$ | +0.850 |
Neg logit contributions | |
ificate | -0.932 |
ills | -0.876 |
riet | -0.861 |
Downloadha | -0.851 |
reme | -0.847 |
Token | , |
Token ID | 11 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
GOODMAN | +0.046 |
cast | +0.046 |
CAST | +0.045 |
fisher | +0.045 |
#$ | +0.044 |
Neg logit contributions | |
ificate | -0.048 |
ills | -0.045 |
riet | -0.044 |
Downloadha | -0.044 |
reme | -0.044 |
Token | United |
Token ID | 1578 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
GOODMAN | +1.280 |
cast | +1.279 |
CAST | +1.247 |
fisher | +1.241 |
Zimmer | +1.217 |
Neg logit contributions | |
ificate | -1.458 |
ills | -1.367 |
riet | -1.351 |
Downloadha | -1.340 |
reme | -1.328 |
Token | States |
Token ID | 1829 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
GOODMAN | +1.060 |
cast | +1.058 |
CAST | +1.036 |
fisher | +1.029 |
#$ | +1.013 |
Neg logit contributions | |
ificate | -0.999 |
ills | -0.932 |
riet | -0.918 |
Downloadha | -0.906 |
reme | -0.903 |
Token | Constitution |
Token ID | 7965 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
GOODMAN | +0.047 |
cast | +0.047 |
CAST | +0.046 |
fisher | +0.046 |
#$ | +0.045 |
Neg logit contributions | |
ificate | -0.042 |
ills | -0.039 |
riet | -0.038 |
reme | -0.038 |
iously | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
GOODMAN | +0.281 |
cast | +0.279 |
CAST | +0.275 |
fisher | +0.272 |
#$ | +0.268 |
Neg logit contributions | |
ificate | -0.305 |
ills | -0.287 |
riet | -0.281 |
reme | -0.279 |
iously | -0.277 |
Token | Article |
Token ID | 10172 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
GOODMAN | +0.580 |
cast | +0.578 |
CAST | +0.569 |
fisher | +0.566 |
#$ | +0.556 |
Neg logit contributions | |
ificate | -0.586 |
ills | -0.548 |
riet | -0.537 |
reme | -0.531 |
iously | -0.528 |
Token | IV |
Token ID | 8363 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ificate | +1.480 |
ills | +1.391 |
riet | +1.351 |
iously | +1.343 |
reme | +1.327 |
Neg logit contributions | |
GOODMAN | -1.579 |
cast | -1.571 |
CAST | -1.566 |
fisher | -1.532 |
cks | -1.513 |
Token | , |
Token ID | 11 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
cast | +4.604 |
GOODMAN | +4.584 |
fisher | +4.444 |
CAST | +4.368 |
Zimmer | +4.335 |
Neg logit contributions | |
ificate | -5.386 |
Downloadha | -5.087 |
riet | -5.054 |
ills | -4.992 |
reme | -4.882 |
Token | Section |
Token ID | 7275 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
cast | +1.149 |
GOODMAN | +1.147 |
CAST | +1.127 |
fisher | +1.118 |
#$ | +1.103 |
Neg logit contributions | |
ificate | -0.942 |
ills | -0.875 |
riet | -0.860 |
reme | -0.846 |
Downloadha | -0.844 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
ificate | +0.439 |
ills | +0.411 |
riet | +0.405 |
reme | +0.402 |
iss | +0.397 |
Neg logit contributions | |
GOODMAN | -0.423 |
cast | -0.421 |
CAST | -0.416 |
fisher | -0.410 |
#$ | -0.404 |
Token | reads |
Token ID | 9743 |
Feature activation | +3.54e-03 |
Pos logit contributions | |
GOODMAN | +0.785 |
cast | +0.783 |
CAST | +0.768 |
fisher | +0.762 |
#$ | +0.750 |
Neg logit contributions | |
ificate | -0.758 |
ills | -0.710 |
riet | -0.698 |
Downloadha | -0.688 |
reme | -0.688 |
Token | , |
Token ID | 11 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
GOODMAN | +0.010 |
cast | +0.010 |
CAST | +0.010 |
fisher | +0.010 |
#$ | +0.010 |
Neg logit contributions | |
ificate | -0.012 |
ills | -0.011 |
riet | -0.011 |
Downloadha | -0.011 |
reme | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ificate | +0.114 |
ills | +0.107 |
riet | +0.104 |
reme | +0.103 |
iously | +0.103 |
Neg logit contributions | |
cast | -0.114 |
GOODMAN | -0.114 |
fisher | -0.112 |
CAST | -0.111 |
#$ | -0.110 |
Token |
|
Token ID | 198 |
Feature activation | +9.58e-02 |
Pos logit contributions | |
GOODMAN | +0.377 |
cast | +0.372 |
fisher | +0.367 |
CAST | +0.365 |
Zimmer | +0.358 |
Neg logit contributions | |
ificate | -0.382 |
ills | -0.356 |
riet | -0.350 |
reme | -0.345 |
iously | -0.344 |
Token | COM |
Token ID | 9858 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
GOODMAN | +0.314 |
cast | +0.309 |
fisher | +0.306 |
CAST | +0.301 |
Zimmer | +0.298 |
Neg logit contributions | |
ificate | -0.283 |
ills | -0.265 |
riet | -0.260 |
Downloadha | -0.255 |
reme | -0.255 |
Token | IC |
Token ID | 2149 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
GOODMAN | +0.905 |
cast | +0.903 |
CAST | +0.883 |
fisher | +0.879 |
#$ | +0.865 |
Neg logit contributions | |
ificate | -0.858 |
ills | -0.801 |
riet | -0.788 |
Downloadha | -0.777 |
reme | -0.776 |
Token | V |
Token ID | 569 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
GOODMAN | +0.736 |
cast | +0.736 |
CAST | +0.716 |
fisher | +0.715 |
#$ | +0.703 |
Neg logit contributions | |
ificate | -0.862 |
ills | -0.808 |
riet | -0.800 |
reme | -0.788 |
Downloadha | -0.786 |
Token | INE |
Token ID | 8881 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
GOODMAN | +1.388 |
cast | +1.386 |
CAST | +1.353 |
fisher | +1.346 |
#$ | +1.323 |
Neg logit contributions | |
ificate | -1.528 |
ills | -1.438 |
riet | -1.414 |
Downloadha | -1.396 |
reme | -1.395 |
Token | : |
Token ID | 25 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
cast | +4.400 |
GOODMAN | +4.387 |
CAST | +4.299 |
fisher | +4.190 |
Zimmer | +4.136 |
Neg logit contributions | |
ificate | -5.589 |
Downloadha | -5.278 |
ills | -5.272 |
riet | -5.250 |
reme | -5.146 |
Token | When |
Token ID | 1649 |
Feature activation | -6.90e-03 |
Pos logit contributions | |
GOODMAN | +1.213 |
cast | +1.211 |
CAST | +1.187 |
fisher | +1.179 |
#$ | +1.159 |
Neg logit contributions | |
ificate | -1.182 |
ills | -1.105 |
riet | -1.087 |
Downloadha | -1.070 |
reme | -1.069 |
Token | you |
Token ID | 345 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
ificate | +0.022 |
ills | +0.021 |
riet | +0.020 |
iously | +0.020 |
iss | +0.020 |
Neg logit contributions | |
GOODMAN | -0.021 |
cast | -0.021 |
CAST | -0.020 |
fisher | -0.020 |
#$ | -0.020 |
Token | think |
Token ID | 892 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
GOODMAN | +1.073 |
cast | +1.059 |
CAST | +1.045 |
fisher | +1.032 |
#$ | +1.025 |
Neg logit contributions | |
ificate | -1.019 |
ills | -0.949 |
riet | -0.934 |
iously | -0.918 |
reme | -0.917 |
Token | of |
Token ID | 286 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ificate | +1.146 |
ills | +1.078 |
riet | +1.045 |
reme | +1.037 |
iously | +1.032 |
Neg logit contributions | |
GOODMAN | -1.256 |
cast | -1.243 |
CAST | -1.237 |
fisher | -1.209 |
#$ | -1.199 |
Token | the |
Token ID | 262 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
GOODMAN | +0.376 |
cast | +0.374 |
CAST | +0.365 |
fisher | +0.360 |
#$ | +0.356 |
Neg logit contributions | |
ificate | -0.473 |
ills | -0.447 |
riet | -0.437 |
iously | -0.435 |
reme | -0.433 |
Token | Def |
Token ID | 2896 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
ificate | +0.196 |
ills | +0.184 |
riet | +0.181 |
reme | +0.179 |
iously | +0.178 |
Neg logit contributions | |
GOODMAN | -0.170 |
cast | -0.169 |
CAST | -0.166 |
fisher | -0.162 |
#$ | -0.162 |
Token | erred |
Token ID | 17436 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
GOODMAN | +0.136 |
cast | +0.135 |
CAST | +0.132 |
fisher | +0.131 |
#$ | +0.129 |
Neg logit contributions | |
ificate | -0.186 |
ills | -0.176 |
riet | -0.174 |
Downloadha | -0.172 |
reme | -0.171 |
Token | Action |
Token ID | 7561 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
GOODMAN | +1.246 |
cast | +1.238 |
CAST | +1.218 |
fisher | +1.208 |
#$ | +1.194 |
Neg logit contributions | |
ificate | -1.214 |
ills | -1.136 |
riet | -1.117 |
Downloadha | -1.101 |
reme | -1.101 |
Token | for |
Token ID | 329 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
cast | +1.715 |
GOODMAN | +1.709 |
CAST | +1.667 |
fisher | +1.666 |
Zimmer | +1.638 |
Neg logit contributions | |
ificate | -1.336 |
ills | -1.245 |
riet | -1.226 |
Downloadha | -1.215 |
reme | -1.199 |
Token | Childhood |
Token ID | 40992 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ificate | +0.130 |
ills | +0.121 |
reme | +0.116 |
iously | +0.116 |
riet | +0.116 |
Neg logit contributions | |
GOODMAN | -0.189 |
cast | -0.187 |
CAST | -0.185 |
#$ | -0.182 |
fisher | -0.181 |
Token | Arri |
Token ID | 27350 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
cast | +3.694 |
GOODMAN | +3.585 |
fisher | +3.522 |
CAST | +3.471 |
cks | +3.366 |
Neg logit contributions | |
ificate | -6.264 |
riet | -5.995 |
Downloadha | -5.989 |
ills | -5.955 |
reme | -5.807 |
Token | vals |
Token ID | 12786 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
GOODMAN | +2.184 |
cast | +2.151 |
CAST | +2.146 |
fisher | +2.130 |
#$ | +2.111 |
Neg logit contributions | |
ificate | -1.091 |
ills | -0.998 |
riet | -0.967 |
reme | -0.950 |
iously | -0.936 |
Token | ( |
Token ID | 357 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
GOODMAN | +0.263 |
cast | +0.263 |
CAST | +0.256 |
fisher | +0.254 |
#$ | +0.249 |
Neg logit contributions | |
ificate | -0.368 |
ills | -0.347 |
riet | -0.344 |
Downloadha | -0.340 |
reme | -0.339 |
Token | D |
Token ID | 35 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
cast | +1.960 |
GOODMAN | +1.940 |
CAST | +1.923 |
fisher | +1.892 |
#$ | +1.861 |
Neg logit contributions | |
ificate | -1.620 |
ills | -1.510 |
riet | -1.492 |
Downloadha | -1.458 |
reme | -1.452 |
Token | ACA |
Token ID | 26576 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
GOODMAN | +0.334 |
cast | +0.330 |
CAST | +0.325 |
fisher | +0.324 |
Zimmer | +0.318 |
Neg logit contributions | |
ificate | -0.323 |
ills | -0.305 |
riet | -0.296 |
reme | -0.294 |
Downloadha | -0.294 |
Token | isn |
Token ID | 2125 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
GOODMAN | +0.995 |
cast | +0.992 |
CAST | +0.968 |
fisher | +0.959 |
#$ | +0.944 |
Neg logit contributions | |
ificate | -1.179 |
ills | -1.109 |
riet | -1.093 |
Downloadha | -1.081 |
reme | -1.078 |
Token | 't |
Token ID | 470 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ificate | +1.024 |
ills | +0.963 |
riet | +0.958 |
reme | +0.940 |
iss | +0.939 |
Neg logit contributions | |
GOODMAN | -0.851 |
cast | -0.823 |
CAST | -0.818 |
fisher | -0.816 |
Zimmer | -0.796 |
Token | it |
Token ID | 340 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ificate | +1.067 |
ills | +1.002 |
riet | +0.990 |
reme | +0.980 |
iss | +0.980 |
Neg logit contributions | |
GOODMAN | -0.862 |
cast | -0.840 |
CAST | -0.836 |
fisher | -0.820 |
cks | -0.815 |
Token | way |
Token ID | 835 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
GOODMAN | +0.596 |
cast | +0.591 |
CAST | +0.583 |
fisher | +0.573 |
#$ | +0.571 |
Neg logit contributions | |
ificate | -0.696 |
ills | -0.654 |
riet | -0.645 |
iously | -0.637 |
reme | -0.635 |
Token | too |
Token ID | 1165 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
GOODMAN | +0.440 |
cast | +0.435 |
CAST | +0.429 |
fisher | +0.424 |
#$ | +0.420 |
Neg logit contributions | |
ificate | -0.370 |
ills | -0.348 |
riet | -0.341 |
reme | -0.334 |
iously | -0.334 |
Token | late |
Token ID | 2739 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ificate | +0.528 |
ills | +0.499 |
riet | +0.487 |
iously | +0.479 |
iss | +0.478 |
Neg logit contributions | |
GOODMAN | -0.561 |
cast | -0.557 |
CAST | -0.550 |
fisher | -0.538 |
#$ | -0.537 |
Token | for |
Token ID | 329 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
cast | +4.881 |
GOODMAN | +4.823 |
CAST | +4.677 |
fisher | +4.672 |
#$ | +4.595 |
Neg logit contributions | |
ificate | -4.797 |
riet | -4.511 |
ills | -4.479 |
Downloadha | -4.471 |
reme | -4.416 |
Token | the |
Token ID | 262 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
GOODMAN | +1.249 |
cast | +1.245 |
CAST | +1.216 |
fisher | +1.204 |
#$ | +1.183 |
Neg logit contributions | |
ificate | -1.622 |
ills | -1.531 |
riet | -1.509 |
Downloadha | -1.492 |
reme | -1.490 |
Token | players |
Token ID | 1938 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
GOODMAN | +0.806 |
cast | +0.803 |
CAST | +0.782 |
fisher | +0.772 |
#$ | +0.761 |
Neg logit contributions | |
ificate | -1.261 |
ills | -1.197 |
riet | -1.179 |
reme | -1.168 |
Downloadha | -1.166 |
Token | to |
Token ID | 284 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
GOODMAN | +1.127 |
cast | +1.127 |
CAST | +1.104 |
fisher | +1.095 |
#$ | +1.079 |
Neg logit contributions | |
ificate | -1.055 |
ills | -0.985 |
riet | -0.969 |
Downloadha | -0.956 |
reme | -0.953 |
Token | be |
Token ID | 307 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
GOODMAN | +1.896 |
cast | +1.894 |
CAST | +1.853 |
fisher | +1.836 |
#$ | +1.810 |
Neg logit contributions | |
ificate | -2.162 |
ills | -2.032 |
riet | -2.001 |
reme | -1.975 |
Downloadha | -1.974 |
Token | figured |
Token ID | 11638 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
GOODMAN | +0.159 |
cast | +0.157 |
CAST | +0.156 |
fisher | +0.152 |
#$ | +0.152 |
Neg logit contributions | |
ificate | -0.147 |
ills | -0.138 |
riet | -0.136 |
reme | -0.133 |
iss | -0.132 |
Token | it |
Token ID | 340 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
GOODMAN | +0.546 |
cast | +0.543 |
CAST | +0.533 |
fisher | +0.527 |
#$ | +0.519 |
Neg logit contributions | |
ificate | -0.606 |
ills | -0.570 |
riet | -0.560 |
Downloadha | -0.553 |
reme | -0.552 |
Token | was |
Token ID | 373 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
ificate | +0.544 |
ills | +0.510 |
riet | +0.495 |
iously | +0.493 |
iss | +0.488 |
Neg logit contributions | |
GOODMAN | -0.649 |
CAST | -0.639 |
cast | -0.637 |
fisher | -0.623 |
#$ | -0.619 |
Token | just |
Token ID | 655 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
GOODMAN | +0.534 |
cast | +0.528 |
CAST | +0.521 |
fisher | +0.512 |
#$ | +0.508 |
Neg logit contributions | |
ificate | -0.599 |
ills | -0.563 |
riet | -0.555 |
Downloadha | -0.546 |
reme | -0.546 |
Token | too |
Token ID | 1165 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ificate | +0.325 |
ills | +0.305 |
riet | +0.300 |
iously | +0.296 |
reme | +0.295 |
Neg logit contributions | |
GOODMAN | -0.306 |
cast | -0.300 |
CAST | -0.298 |
fisher | -0.291 |
#$ | -0.290 |
Token | late |
Token ID | 2739 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ificate | +0.328 |
ills | +0.308 |
riet | +0.300 |
iously | +0.295 |
reme | +0.294 |
Neg logit contributions | |
GOODMAN | -0.403 |
cast | -0.399 |
CAST | -0.395 |
fisher | -0.388 |
#$ | -0.386 |
Token | for |
Token ID | 329 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
cast | +4.678 |
GOODMAN | +4.565 |
fisher | +4.435 |
CAST | +4.392 |
·· | +4.390 |
Neg logit contributions | |
ificate | -5.007 |
riet | -4.736 |
Downloadha | -4.711 |
ills | -4.666 |
reme | -4.632 |
Token | me |
Token ID | 502 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
GOODMAN | +1.254 |
cast | +1.254 |
CAST | +1.224 |
fisher | +1.217 |
#$ | +1.195 |
Neg logit contributions | |
ificate | -1.354 |
ills | -1.269 |
riet | -1.253 |
Downloadha | -1.239 |
reme | -1.233 |
Token | . |
Token ID | 13 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ificate | +0.772 |
ills | +0.721 |
riet | +0.703 |
reme | +0.693 |
iously | +0.693 |
Neg logit contributions | |
GOODMAN | -0.873 |
cast | -0.870 |
CAST | -0.860 |
fisher | -0.849 |
#$ | -0.837 |
Token | However |
Token ID | 2102 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
ificate | +0.841 |
ills | +0.791 |
riet | +0.766 |
iss | +0.758 |
reme | +0.757 |
Neg logit contributions | |
GOODMAN | -0.904 |
cast | -0.895 |
CAST | -0.883 |
fisher | -0.880 |
cks | -0.858 |
Token | , |
Token ID | 11 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
ificate | +0.700 |
ills | +0.657 |
riet | +0.647 |
Downloadha | +0.639 |
reme | +0.637 |
Neg logit contributions | |
GOODMAN | -0.667 |
cast | -0.664 |
CAST | -0.651 |
fisher | -0.646 |
#$ | -0.635 |
Token | a |
Token ID | 257 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
GOODMAN | +0.187 |
cast | +0.187 |
CAST | +0.183 |
fisher | +0.181 |
#$ | +0.178 |
Neg logit contributions | |
ificate | -0.211 |
ills | -0.198 |
riet | -0.195 |
reme | -0.193 |
Downloadha | -0.192 |
Token | major |
Token ID | 1688 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ificate | +0.487 |
ills | +0.455 |
riet | +0.450 |
reme | +0.443 |
iously | +0.441 |
Neg logit contributions | |
GOODMAN | -0.439 |
cast | -0.435 |
CAST | -0.427 |
fisher | -0.421 |
#$ | -0.415 |
Token | role |
Token ID | 2597 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
GOODMAN | +0.989 |
cast | +0.986 |
CAST | +0.968 |
fisher | +0.959 |
#$ | +0.947 |
Neg logit contributions | |
ificate | -0.906 |
ills | -0.841 |
riet | -0.829 |
reme | -0.817 |
Downloadha | -0.816 |
Token | in |
Token ID | 287 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ificate | +1.151 |
ills | +1.080 |
riet | +1.053 |
Downloadha | +1.041 |
iously | +1.041 |
Neg logit contributions | |
GOODMAN | -1.161 |
cast | -1.154 |
CAST | -1.137 |
fisher | -1.129 |
cks | -1.110 |
Token | sp |
Token ID | 599 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
GOODMAN | +0.418 |
cast | +0.418 |
CAST | +0.409 |
fisher | +0.406 |
#$ | +0.399 |
Neg logit contributions | |
ificate | -0.410 |
ills | -0.384 |
riet | -0.377 |
reme | -0.372 |
Downloadha | -0.371 |
Token | ru |
Token ID | 622 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ificate | +0.598 |
ills | +0.563 |
riet | +0.554 |
reme | +0.542 |
iously | +0.542 |
Neg logit contributions | |
GOODMAN | -0.684 |
cast | -0.676 |
CAST | -0.666 |
fisher | -0.661 |
#$ | -0.651 |
Token | cing |
Token ID | 2259 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
cast | +4.812 |
GOODMAN | +4.760 |
CAST | +4.701 |
cks | +4.636 |
fisher | +4.570 |
Neg logit contributions | |
ificate | -4.758 |
Downloadha | -4.389 |
riet | -4.359 |
ills | -4.323 |
reme | -4.285 |
Token | up |
Token ID | 510 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
ificate | +0.322 |
ills | +0.301 |
riet | +0.295 |
reme | +0.292 |
iously | +0.292 |
Neg logit contributions | |
GOODMAN | -0.321 |
cast | -0.319 |
CAST | -0.313 |
fisher | -0.310 |
#$ | -0.307 |
Token | Sam |
Token ID | 3409 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
ificate | +0.118 |
ills | +0.112 |
riet | +0.110 |
reme | +0.109 |
Downloadha | +0.108 |
Neg logit contributions | |
GOODMAN | -0.096 |
cast | -0.096 |
CAST | -0.094 |
fisher | -0.093 |
#$ | -0.091 |
Token | � |
Token ID | 447 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
GOODMAN | +0.195 |
cast | +0.195 |
CAST | +0.192 |
fisher | +0.190 |
#$ | +0.187 |
Neg logit contributions | |
ificate | -0.222 |
ills | -0.209 |
riet | -0.205 |
reme | -0.203 |
iss | -0.202 |
Token | � |
Token ID | 247 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
GOODMAN | +0.129 |
cast | +0.129 |
CAST | +0.126 |
fisher | +0.124 |
#$ | +0.121 |
Neg logit contributions | |
ificate | -0.193 |
ills | -0.184 |
riet | -0.181 |
reme | -0.179 |
Downloadha | -0.178 |
Token | mm |
Token ID | 3020 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
cast | +0.228 |
GOODMAN | +0.227 |
CAST | +0.222 |
fisher | +0.221 |
#$ | +0.218 |
Neg logit contributions | |
ificate | -0.187 |
ills | -0.172 |
riet | -0.171 |
Downloadha | -0.168 |
iously | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
ificate | +1.007 |
ills | +0.945 |
riet | +0.922 |
Downloadha | +0.912 |
reme | +0.911 |
Neg logit contributions | |
GOODMAN | -1.077 |
cast | -1.075 |
CAST | -1.057 |
fisher | -1.046 |
Zimmer | -1.027 |
Token |
|
Token ID | 198 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
ificate | +0.824 |
ills | +0.774 |
riet | +0.759 |
Downloadha | +0.752 |
reme | +0.749 |
Neg logit contributions | |
GOODMAN | -0.797 |
cast | -0.795 |
CAST | -0.781 |
fisher | -0.774 |
#$ | -0.759 |
Token |
|
Token ID | 198 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
ificate | +0.230 |
ills | +0.214 |
riet | +0.209 |
iously | +0.207 |
reme | +0.206 |
Neg logit contributions | |
GOODMAN | -0.234 |
cast | -0.229 |
CAST | -0.226 |
fisher | -0.226 |
� | -0.221 |
Token | and |
Token ID | 392 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
ificate | +0.102 |
ills | +0.095 |
riet | +0.093 |
Downloadha | +0.091 |
reme | +0.091 |
Neg logit contributions | |
GOODMAN | -0.127 |
cast | -0.125 |
fisher | -0.124 |
CAST | -0.123 |
Zimmer | -0.121 |
Token | finally |
Token ID | 3443 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ificate | +2.387 |
ills | +2.250 |
riet | +2.180 |
iously | +2.174 |
iss | +2.150 |
Neg logit contributions | |
GOODMAN | -2.321 |
cast | -2.315 |
CAST | -2.291 |
fisher | -2.247 |
#$ | -2.239 |
Token | the |
Token ID | 262 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
cast | +4.135 |
GOODMAN | +4.110 |
fisher | +4.005 |
CAST | +3.960 |
Zimmer | +3.923 |
Neg logit contributions | |
ificate | -5.245 |
riet | -4.931 |
ills | -4.922 |
Downloadha | -4.873 |
reme | -4.820 |
Token | 16 |
Token ID | 1467 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
GOODMAN | +0.476 |
cast | +0.475 |
CAST | +0.467 |
fisher | +0.460 |
#$ | +0.454 |
Neg logit contributions | |
ificate | -0.503 |
ills | -0.474 |
riet | -0.465 |
reme | -0.460 |
Downloadha | -0.458 |
Token | - |
Token ID | 12 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
ificate | +0.469 |
ills | +0.440 |
riet | +0.434 |
Downloadha | +0.429 |
reme | +0.426 |
Neg logit contributions | |
GOODMAN | -0.442 |
cast | -0.441 |
CAST | -0.431 |
fisher | -0.428 |
#$ | -0.421 |
Token | 35 |
Token ID | 2327 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
ificate | +1.224 |
ills | +1.170 |
riet | +1.138 |
reme | +1.127 |
iss | +1.119 |
Neg logit contributions | |
GOODMAN | -1.339 |
cast | -1.291 |
fisher | -1.277 |
CAST | -1.274 |
Zimmer | -1.263 |
Token | f |
Token ID | 277 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
cast | +0.105 |
GOODMAN | +0.105 |
CAST | +0.102 |
fisher | +0.101 |
#$ | +0.099 |
Neg logit contributions | |
ificate | -0.163 |
ills | -0.155 |
riet | -0.153 |
Downloadha | -0.152 |
reme | -0.151 |
Token | more |
Token ID | 517 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
GOODMAN | +1.819 |
cast | +1.812 |
CAST | +1.771 |
fisher | +1.754 |
#$ | +1.727 |
Neg logit contributions | |
ificate | -2.107 |
ills | -1.984 |
riet | -1.956 |
Downloadha | -1.933 |
reme | -1.927 |
Token | straightforward |
Token ID | 15836 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
GOODMAN | +0.129 |
cast | +0.127 |
CAST | +0.125 |
#$ | +0.122 |
fisher | +0.122 |
Neg logit contributions | |
ificate | -0.119 |
ills | -0.113 |
riet | -0.110 |
iously | -0.109 |
iss | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
GOODMAN | +1.600 |
cast | +1.600 |
CAST | +1.565 |
fisher | +1.557 |
#$ | +1.531 |
Neg logit contributions | |
ificate | -1.435 |
ills | -1.336 |
riet | -1.318 |
Downloadha | -1.303 |
reme | -1.294 |
Token |
|
Token ID | 198 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
GOODMAN | +0.257 |
cast | +0.255 |
CAST | +0.251 |
fisher | +0.249 |
#$ | +0.245 |
Neg logit contributions | |
ificate | -0.251 |
ills | -0.237 |
riet | -0.230 |
reme | -0.228 |
iously | -0.227 |
Token |
|
Token ID | 198 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
cast | +1.691 |
GOODMAN | +1.668 |
CAST | +1.640 |
fisher | +1.622 |
#$ | +1.600 |
Neg logit contributions | |
ificate | -1.922 |
ills | -1.809 |
riet | -1.794 |
Downloadha | -1.789 |
reme | -1.765 |
Token | Finally |
Token ID | 11158 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
GOODMAN | +1.271 |
cast | +1.268 |
CAST | +1.243 |
fisher | +1.237 |
#$ | +1.217 |
Neg logit contributions | |
ificate | -1.026 |
ills | -0.953 |
riet | -0.937 |
Downloadha | -0.924 |
reme | -0.920 |
Token | , |
Token ID | 11 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
cast | +3.966 |
GOODMAN | +3.927 |
fisher | +3.794 |
CAST | +3.788 |
Zimmer | +3.736 |
Neg logit contributions | |
ificate | -5.309 |
riet | -5.031 |
ills | -4.960 |
Downloadha | -4.934 |
iously | -4.856 |
Token | our |
Token ID | 674 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
cast | +1.517 |
GOODMAN | +1.515 |
CAST | +1.479 |
fisher | +1.472 |
Zimmer | +1.443 |
Neg logit contributions | |
ificate | -1.671 |
ills | -1.567 |
riet | -1.550 |
Downloadha | -1.535 |
reme | -1.525 |
Token | understanding |
Token ID | 4547 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
GOODMAN | +0.336 |
cast | +0.335 |
CAST | +0.328 |
fisher | +0.326 |
#$ | +0.321 |
Neg logit contributions | |
ificate | -0.318 |
ills | -0.298 |
riet | -0.293 |
reme | -0.288 |
Downloadha | -0.288 |
Token | of |
Token ID | 286 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
ificate | +0.479 |
ills | +0.446 |
riet | +0.439 |
Downloadha | +0.433 |
reme | +0.431 |
Neg logit contributions | |
GOODMAN | -0.556 |
cast | -0.555 |
CAST | -0.544 |
fisher | -0.540 |
#$ | -0.532 |
Token | puls |
Token ID | 22271 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
GOODMAN | +0.130 |
cast | +0.129 |
CAST | +0.127 |
fisher | +0.125 |
#$ | +0.123 |
Neg logit contributions | |
ificate | -0.147 |
ills | -0.139 |
riet | -0.136 |
Downloadha | -0.134 |
reme | -0.134 |
Token | - |
Token ID | 532 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
ificate | +1.460 |
ills | +1.386 |
riet | +1.343 |
iously | +1.331 |
reme | +1.322 |
Neg logit contributions | |
GOODMAN | -1.475 |
cast | -1.450 |
CAST | -1.438 |
fisher | -1.413 |
#$ | -1.397 |
Token | thank |
Token ID | 5875 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
ificate | +0.911 |
ills | +0.859 |
riet | +0.840 |
reme | +0.825 |
iss | +0.822 |
Neg logit contributions | |
GOODMAN | -0.913 |
cast | -0.909 |
CAST | -0.894 |
fisher | -0.875 |
#$ | -0.872 |
Token | you |
Token ID | 345 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
GOODMAN | +0.624 |
cast | +0.621 |
CAST | +0.606 |
fisher | +0.600 |
#$ | +0.587 |
Neg logit contributions | |
ificate | -0.977 |
ills | -0.926 |
riet | -0.914 |
Downloadha | -0.903 |
reme | -0.903 |
Token | ! |
Token ID | 0 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
GOODMAN | +2.221 |
cast | +2.217 |
CAST | +2.162 |
fisher | +2.150 |
Zimmer | +2.116 |
Neg logit contributions | |
ificate | -2.331 |
ills | -2.175 |
riet | -2.153 |
Downloadha | -2.145 |
reme | -2.117 |
Token | And |
Token ID | 843 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ificate | +0.136 |
ills | +0.128 |
riet | +0.125 |
Downloadha | +0.124 |
reme | +0.124 |
Neg logit contributions | |
cast | -0.133 |
GOODMAN | -0.132 |
CAST | -0.130 |
fisher | -0.129 |
#$ | -0.127 |
Token | finally |
Token ID | 3443 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
GOODMAN | +0.785 |
cast | +0.783 |
CAST | +0.767 |
fisher | +0.761 |
#$ | +0.751 |
Neg logit contributions | |
ificate | -0.810 |
ills | -0.759 |
riet | -0.748 |
Downloadha | -0.737 |
reme | -0.736 |
Token | , |
Token ID | 11 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
cast | +4.189 |
GOODMAN | +4.154 |
fisher | +4.082 |
CAST | +4.051 |
Zimmer | +4.035 |
Neg logit contributions | |
ificate | -5.158 |
ills | -4.817 |
riet | -4.805 |
Downloadha | -4.783 |
iously | -4.719 |
Token | I |
Token ID | 314 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
cast | +1.650 |
GOODMAN | +1.650 |
CAST | +1.610 |
fisher | +1.604 |
Zimmer | +1.572 |
Neg logit contributions | |
ificate | -1.775 |
ills | -1.665 |
riet | -1.643 |
Downloadha | -1.628 |
reme | -1.617 |
Token | would |
Token ID | 561 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
GOODMAN | +0.088 |
cast | +0.088 |
CAST | +0.086 |
fisher | +0.085 |
#$ | +0.085 |
Neg logit contributions | |
ificate | -0.084 |
ills | -0.078 |
riet | -0.077 |
reme | -0.076 |
iss | -0.076 |
Token | like |
Token ID | 588 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
ificate | +0.391 |
ills | +0.367 |
riet | +0.362 |
reme | +0.357 |
iously | +0.355 |
Neg logit contributions | |
GOODMAN | -0.336 |
cast | -0.334 |
CAST | -0.328 |
fisher | -0.323 |
#$ | -0.322 |
Token | to |
Token ID | 284 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ificate | +0.135 |
ills | +0.125 |
riet | +0.122 |
reme | +0.121 |
Downloadha | +0.120 |
Neg logit contributions | |
GOODMAN | -0.164 |
cast | -0.163 |
CAST | -0.161 |
fisher | -0.159 |
#$ | -0.157 |
Token | he |
Token ID | 339 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
GOODMAN | +1.081 |
cast | +1.078 |
CAST | +1.056 |
fisher | +1.044 |
#$ | +1.025 |
Neg logit contributions | |
ificate | -1.297 |
ills | -1.221 |
riet | -1.204 |
Downloadha | -1.189 |
reme | -1.187 |
Token | is |
Token ID | 318 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
ificate | +0.995 |
ills | +0.933 |
iously | +0.910 |
riet | +0.910 |
reme | +0.899 |
Neg logit contributions | |
GOODMAN | -1.064 |
CAST | -1.049 |
cast | -1.046 |
fisher | -1.016 |
#$ | -1.012 |
Token | committed |
Token ID | 5364 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ificate | +0.805 |
ills | +0.749 |
riet | +0.735 |
reme | +0.723 |
iously | +0.722 |
Neg logit contributions | |
GOODMAN | -0.902 |
cast | -0.888 |
CAST | -0.883 |
fisher | -0.861 |
#$ | -0.860 |
Token | to |
Token ID | 284 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
ificate | +1.000 |
ills | +0.929 |
riet | +0.911 |
iously | +0.899 |
reme | +0.897 |
Neg logit contributions | |
GOODMAN | -1.193 |
cast | -1.188 |
CAST | -1.171 |
fisher | -1.156 |
#$ | -1.137 |
Token | say |
Token ID | 910 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ificate | +1.411 |
ills | +1.334 |
riet | +1.308 |
iously | +1.292 |
iss | +1.280 |
Neg logit contributions | |
GOODMAN | -1.512 |
cast | -1.494 |
CAST | -1.489 |
#$ | -1.447 |
fisher | -1.444 |
Token | whatever |
Token ID | 4232 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
GOODMAN | +0.809 |
cast | +0.802 |
CAST | +0.789 |
fisher | +0.781 |
#$ | +0.765 |
Neg logit contributions | |
ificate | -0.927 |
ills | -0.874 |
riet | -0.861 |
Downloadha | -0.847 |
reme | -0.847 |
Token | he |
Token ID | 339 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
cast | +4.033 |
GOODMAN | +3.932 |
fisher | +3.866 |
Zimmer | +3.852 |
#$ | +3.802 |
Neg logit contributions | |
ificate | -5.279 |
Downloadha | -4.993 |
ills | -4.949 |
riet | -4.938 |
reme | -4.859 |
Token | has |
Token ID | 468 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ificate | +0.484 |
ills | +0.454 |
riet | +0.443 |
iously | +0.437 |
reme | +0.436 |
Neg logit contributions | |
GOODMAN | -0.566 |
cast | -0.561 |
CAST | -0.557 |
fisher | -0.548 |
#$ | -0.539 |
Token | to |
Token ID | 284 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
ificate | +0.860 |
ills | +0.795 |
riet | +0.775 |
iously | +0.772 |
iss | +0.761 |
Neg logit contributions | |
GOODMAN | -1.124 |
CAST | -1.113 |
cast | -1.109 |
fisher | -1.094 |
#$ | -1.079 |
Token | in |
Token ID | 287 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ificate | +1.699 |
ills | +1.593 |
iss | +1.550 |
riet | +1.549 |
iously | +1.544 |
Neg logit contributions | |
GOODMAN | -1.454 |
CAST | -1.444 |
cast | -1.429 |
fisher | -1.412 |
#$ | -1.387 |
Token | order |
Token ID | 1502 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
ificate | +0.481 |
ills | +0.461 |
riet | +0.451 |
iously | +0.446 |
reme | +0.446 |
Neg logit contributions | |
GOODMAN | -0.365 |
cast | -0.357 |
CAST | -0.356 |
fisher | -0.353 |
#$ | -0.346 |
Token | communities |
Token ID | 5348 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ificate | +0.565 |
ills | +0.533 |
riet | +0.519 |
reme | +0.514 |
iously | +0.513 |
Neg logit contributions | |
GOODMAN | -0.509 |
cast | -0.507 |
CAST | -0.500 |
#$ | -0.485 |
cks | -0.479 |
Token | of |
Token ID | 286 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
cast | +2.037 |
GOODMAN | +2.036 |
fisher | +1.991 |
CAST | +1.991 |
Zimmer | +1.948 |
Neg logit contributions | |
ificate | -1.867 |
ills | -1.730 |
riet | -1.715 |
Downloadha | -1.695 |
reme | -1.685 |
Token | color |
Token ID | 3124 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
ificate | +0.115 |
ills | +0.108 |
riet | +0.105 |
iss | +0.103 |
reme | +0.103 |
Neg logit contributions | |
GOODMAN | -0.109 |
cast | -0.107 |
CAST | -0.105 |
#$ | -0.104 |
� | -0.102 |
Token | under |
Token ID | 739 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
cast | +2.519 |
GOODMAN | +2.512 |
fisher | +2.467 |
CAST | +2.459 |
cks | +2.402 |
Neg logit contributions | |
ificate | -2.581 |
ills | -2.399 |
riet | -2.393 |
Downloadha | -2.359 |
reme | -2.339 |
Token | Title |
Token ID | 11851 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
ificate | +1.438 |
ills | +1.360 |
riet | +1.317 |
iss | +1.312 |
reme | +1.310 |
Neg logit contributions | |
GOODMAN | -1.300 |
cast | -1.284 |
CAST | -1.264 |
#$ | -1.242 |
fisher | -1.236 |
Token | VI |
Token ID | 13889 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
GOODMAN | +0.725 |
cast | +0.724 |
CAST | +0.709 |
fisher | +0.704 |
#$ | +0.693 |
Neg logit contributions | |
ificate | -0.670 |
ills | -0.625 |
riet | -0.615 |
Downloadha | -0.607 |
reme | -0.605 |
Token | of |
Token ID | 286 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
cast | +4.536 |
GOODMAN | +4.504 |
fisher | +4.472 |
CAST | +4.378 |
cks | +4.338 |
Neg logit contributions | |
ificate | -4.714 |
riet | -4.417 |
Downloadha | -4.361 |
ills | -4.353 |
reme | -4.262 |
Token | the |
Token ID | 262 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
cast | +0.296 |
GOODMAN | +0.296 |
CAST | +0.289 |
fisher | +0.285 |
#$ | +0.280 |
Neg logit contributions | |
ificate | -0.387 |
ills | -0.366 |
riet | -0.360 |
reme | -0.357 |
iously | -0.355 |
Token | Civil |
Token ID | 7511 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
ificate | +0.155 |
ills | +0.147 |
riet | +0.143 |
reme | +0.143 |
iss | +0.141 |
Neg logit contributions | |
GOODMAN | -0.152 |
cast | -0.151 |
CAST | -0.149 |
#$ | -0.145 |
fisher | -0.145 |
Token | Rights |
Token ID | 6923 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
GOODMAN | +1.694 |
cast | +1.685 |
CAST | +1.658 |
fisher | +1.647 |
#$ | +1.625 |
Neg logit contributions | |
ificate | -1.377 |
ills | -1.275 |
riet | -1.250 |
reme | -1.234 |
iously | -1.230 |
Token | Act |
Token ID | 2191 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
cast | +2.081 |
GOODMAN | +2.080 |
CAST | +2.022 |
fisher | +2.010 |
#$ | +1.979 |
Neg logit contributions | |
ificate | -2.476 |
ills | -2.315 |
riet | -2.307 |
Downloadha | -2.304 |
reme | -2.257 |
Token | talk |
Token ID | 1561 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
GOODMAN | +0.750 |
cast | +0.744 |
CAST | +0.729 |
fisher | +0.720 |
#$ | +0.709 |
Neg logit contributions | |
ificate | -0.900 |
ills | -0.846 |
riet | -0.835 |
Downloadha | -0.824 |
reme | -0.822 |
Token | about |
Token ID | 546 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
GOODMAN | +0.559 |
cast | +0.559 |
CAST | +0.546 |
fisher | +0.542 |
#$ | +0.533 |
Neg logit contributions | |
ificate | -0.612 |
ills | -0.574 |
riet | -0.567 |
Downloadha | -0.560 |
reme | -0.558 |
Token | the |
Token ID | 262 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
GOODMAN | +0.529 |
cast | +0.527 |
CAST | +0.515 |
fisher | +0.511 |
#$ | +0.503 |
Neg logit contributions | |
ificate | -0.608 |
ills | -0.572 |
riet | -0.564 |
Downloadha | -0.558 |
reme | -0.556 |
Token | upcoming |
Token ID | 7865 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
GOODMAN | +0.329 |
cast | +0.328 |
CAST | +0.321 |
fisher | +0.319 |
#$ | +0.314 |
Neg logit contributions | |
ificate | -0.338 |
ills | -0.316 |
riet | -0.312 |
Downloadha | -0.308 |
reme | -0.307 |
Token | Fifty |
Token ID | 35351 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
cast | +1.031 |
GOODMAN | +1.029 |
CAST | +1.005 |
fisher | +1.000 |
Zimmer | +0.981 |
Neg logit contributions | |
ificate | -1.110 |
ills | -1.038 |
riet | -1.025 |
Downloadha | -1.015 |
reme | -1.009 |
Token | Shades |
Token ID | 47260 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
cast | +1.837 |
GOODMAN | +1.831 |
CAST | +1.786 |
fisher | +1.779 |
#$ | +1.752 |
Neg logit contributions | |
ificate | -2.285 |
ills | -2.147 |
riet | -2.123 |
Downloadha | -2.110 |
reme | -2.082 |
Token | of |
Token ID | 286 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
cast | +4.499 |
GOODMAN | +4.272 |
CAST | +4.216 |
fisher | +4.201 |
Zimmer | +4.149 |
Neg logit contributions | |
ificate | -4.879 |
Downloadha | -4.514 |
riet | -4.503 |
ills | -4.476 |
iously | -4.416 |
Token | Grey |
Token ID | 13980 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
ificate | +0.297 |
ills | +0.277 |
riet | +0.272 |
reme | +0.271 |
Downloadha | +0.267 |
Neg logit contributions | |
GOODMAN | -0.351 |
cast | -0.348 |
CAST | -0.343 |
fisher | -0.340 |
#$ | -0.335 |
Token | film |
Token ID | 2646 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
GOODMAN | +1.172 |
cast | +1.172 |
CAST | +1.142 |
fisher | +1.134 |
#$ | +1.111 |
Neg logit contributions | |
ificate | -1.494 |
ills | -1.407 |
riet | -1.389 |
Downloadha | -1.376 |
reme | -1.369 |
Token | it |
Token ID | 340 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
GOODMAN | +0.922 |
cast | +0.917 |
CAST | +0.899 |
fisher | +0.892 |
#$ | +0.878 |
Neg logit contributions | |
ificate | -0.961 |
ills | -0.901 |
riet | -0.888 |
Downloadha | -0.875 |
reme | -0.875 |
Token | looks |
Token ID | 3073 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
GOODMAN | +0.155 |
CAST | +0.152 |
cast | +0.152 |
fisher | +0.149 |
#$ | +0.148 |
Neg logit contributions | |
ificate | -0.159 |
ills | -0.150 |
iously | -0.147 |
riet | -0.146 |
reme | -0.145 |
Token | This |
Token ID | 770 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
GOODMAN | +0.836 |
cast | +0.833 |
CAST | +0.816 |
fisher | +0.813 |
#$ | +0.798 |
Neg logit contributions | |
ificate | -0.859 |
ills | -0.805 |
riet | -0.791 |
Downloadha | -0.781 |
reme | -0.779 |
Token | shows |
Token ID | 2523 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
GOODMAN | +0.814 |
cast | +0.807 |
CAST | +0.795 |
fisher | +0.780 |
#$ | +0.773 |
Neg logit contributions | |
ificate | -0.837 |
ills | -0.783 |
riet | -0.773 |
reme | -0.760 |
iously | -0.758 |
Token | that |
Token ID | 326 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
GOODMAN | +0.416 |
cast | +0.411 |
CAST | +0.405 |
fisher | +0.397 |
#$ | +0.395 |
Neg logit contributions | |
ificate | -0.573 |
ills | -0.542 |
riet | -0.536 |
reme | -0.527 |
iously | -0.526 |
Token | the |
Token ID | 262 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
GOODMAN | +0.547 |
cast | +0.543 |
CAST | +0.534 |
fisher | +0.525 |
#$ | +0.520 |
Neg logit contributions | |
ificate | -0.653 |
ills | -0.615 |
riet | -0.607 |
Downloadha | -0.598 |
reme | -0.597 |
Token | ex |
Token ID | 409 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
GOODMAN | +0.296 |
cast | +0.293 |
CAST | +0.288 |
fisher | +0.283 |
#$ | +0.282 |
Neg logit contributions | |
ificate | -0.328 |
ills | -0.308 |
riet | -0.304 |
reme | -0.300 |
iously | -0.299 |
Token | oplan |
Token ID | 46853 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
cast | +0.805 |
GOODMAN | +0.803 |
CAST | +0.790 |
fisher | +0.787 |
#$ | +0.775 |
Neg logit contributions | |
ificate | -0.448 |
ills | -0.408 |
riet | -0.401 |
Downloadha | -0.397 |
reme | -0.388 |
Token | et |
Token ID | 316 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
cast | +5.018 |
GOODMAN | +4.841 |
fisher | +4.812 |
CAST | +4.768 |
cks | +4.751 |
Neg logit contributions | |
ificate | -4.123 |
Downloadha | -3.946 |
ills | -3.874 |
riet | -3.836 |
iffe | -3.761 |
Token | must |
Token ID | 1276 |
Feature activation | -1.19e-03 |
Pos logit contributions | |
GOODMAN | +1.630 |
cast | +1.625 |
CAST | +1.592 |
fisher | +1.577 |
#$ | +1.554 |
Neg logit contributions | |
ificate | -1.693 |
ills | -1.584 |
riet | -1.563 |
Downloadha | -1.541 |
reme | -1.537 |
Token | have |
Token ID | 423 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ificate | +0.004 |
ills | +0.003 |
riet | +0.003 |
iously | +0.003 |
reme | +0.003 |
Neg logit contributions | |
GOODMAN | -0.004 |
cast | -0.004 |
CAST | -0.004 |
fisher | -0.004 |
#$ | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ificate | +0.307 |
ills | +0.287 |
riet | +0.282 |
iously | +0.278 |
reme | +0.277 |
Neg logit contributions | |
GOODMAN | -0.330 |
cast | -0.327 |
CAST | -0.323 |
#$ | -0.317 |
fisher | -0.316 |
Token | dense |
Token ID | 15715 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
GOODMAN | +0.453 |
cast | +0.451 |
CAST | +0.443 |
fisher | +0.435 |
#$ | +0.431 |
Neg logit contributions | |
ificate | -0.459 |
ills | -0.428 |
riet | -0.422 |
reme | -0.417 |
Downloadha | -0.414 |
Token | day |
Token ID | 1110 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
ificate | +0.359 |
ills | +0.337 |
riet | +0.329 |
reme | +0.325 |
iously | +0.325 |
Neg logit contributions | |
GOODMAN | -0.379 |
cast | -0.377 |
CAST | -0.372 |
fisher | -0.367 |
#$ | -0.362 |
Token | long |
Token ID | 890 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
ificate | +0.056 |
ills | +0.052 |
riet | +0.051 |
Downloadha | +0.050 |
reme | +0.050 |
Neg logit contributions | |
GOODMAN | -0.067 |
cast | -0.066 |
CAST | -0.065 |
fisher | -0.065 |
#$ | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
ificate | +1.683 |
ills | +1.576 |
riet | +1.524 |
reme | +1.513 |
iously | +1.513 |
Neg logit contributions | |
GOODMAN | -1.893 |
cast | -1.874 |
CAST | -1.856 |
fisher | -1.831 |
#$ | -1.808 |
Token |
|
Token ID | 198 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
ificate | +0.131 |
ills | +0.122 |
riet | +0.120 |
Downloadha | +0.118 |
iously | +0.118 |
Neg logit contributions | |
GOODMAN | -0.133 |
cast | -0.133 |
CAST | -0.130 |
fisher | -0.129 |
#$ | -0.127 |
Token |
|
Token ID | 198 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
ificate | +0.130 |
ills | +0.121 |
riet | +0.119 |
iously | +0.117 |
reme | +0.117 |
Neg logit contributions | |
GOODMAN | -0.129 |
cast | -0.128 |
CAST | -0.126 |
fisher | -0.125 |
Zimmer | -0.123 |
Token | Finally |
Token ID | 11158 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ificate | +0.095 |
ills | +0.089 |
riet | +0.087 |
Downloadha | +0.085 |
reme | +0.085 |
Neg logit contributions | |
GOODMAN | -0.118 |
cast | -0.117 |
fisher | -0.115 |
CAST | -0.114 |
Zimmer | -0.112 |
Token | , |
Token ID | 11 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
GOODMAN | +3.817 |
cast | +3.799 |
fisher | +3.655 |
CAST | +3.631 |
cks | +3.587 |
Neg logit contributions | |
ificate | -5.217 |
riet | -4.988 |
ills | -4.900 |
Downloadha | -4.841 |
reme | -4.833 |
Token | bring |
Token ID | 2222 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
cast | +1.504 |
GOODMAN | +1.503 |
CAST | +1.464 |
fisher | +1.458 |
#$ | +1.427 |
Neg logit contributions | |
ificate | -1.753 |
ills | -1.648 |
riet | -1.630 |
Downloadha | -1.612 |
reme | -1.605 |
Token | cash |
Token ID | 5003 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
cast | +1.487 |
GOODMAN | +1.487 |
CAST | +1.447 |
fisher | +1.440 |
#$ | +1.409 |
Neg logit contributions | |
ificate | -1.885 |
ills | -1.774 |
riet | -1.756 |
Downloadha | -1.737 |
reme | -1.730 |
Token | . |
Token ID | 13 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
ificate | +0.152 |
ills | +0.144 |
riet | +0.139 |
iously | +0.137 |
reme | +0.137 |
Neg logit contributions | |
GOODMAN | -0.167 |
cast | -0.166 |
CAST | -0.164 |
fisher | -0.163 |
#$ | -0.160 |
Token | Sometimes |
Token ID | 8975 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
GOODMAN | +0.195 |
cast | +0.194 |
CAST | +0.191 |
fisher | +0.189 |
#$ | +0.186 |
Neg logit contributions | |
ificate | -0.192 |
ills | -0.180 |
riet | -0.176 |
Downloadha | -0.173 |
reme | -0.173 |
Token | 2 |
Token ID | 362 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
GOODMAN | +0.523 |
cast | +0.522 |
CAST | +0.509 |
fisher | +0.507 |
Zimmer | +0.498 |
Neg logit contributions | |
ificate | -0.485 |
ills | -0.453 |
riet | -0.446 |
Downloadha | -0.443 |
reme | -0.438 |
Token | 18 |
Token ID | 1248 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ificate | +1.549 |
ills | +1.464 |
riet | +1.438 |
reme | +1.420 |
iously | +1.416 |
Neg logit contributions | |
GOODMAN | -1.256 |
cast | -1.252 |
CAST | -1.227 |
fisher | -1.208 |
#$ | -1.200 |
Token | K |
Token ID | 42 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
ificate | +0.717 |
ills | +0.669 |
riet | +0.658 |
reme | +0.648 |
Downloadha | +0.648 |
Neg logit contributions | |
GOODMAN | -0.760 |
cast | -0.759 |
CAST | -0.744 |
fisher | -0.738 |
#$ | -0.729 |
Token | Shares |
Token ID | 23997 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
cast | +1.638 |
GOODMAN | +1.629 |
fisher | +1.580 |
CAST | +1.576 |
Zimmer | +1.558 |
Neg logit contributions | |
ificate | -1.197 |
Downloadha | -1.100 |
riet | -1.099 |
ills | -1.099 |
iously | -1.077 |
Token |
|
Token ID | 198 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ificate | +4.264 |
ills | +3.896 |
riet | +3.808 |
iously | +3.794 |
iss | +3.787 |
Neg logit contributions | |
GOODMAN | -4.715 |
CAST | -4.677 |
cast | -4.617 |
fisher | -4.580 |
#$ | -4.492 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ificate | +4.293 |
ills | +3.919 |
iss | +3.807 |
iously | +3.792 |
riet | +3.716 |
Neg logit contributions | |
�醒 | -6.026 |
GOODMAN | -5.982 |
� | -5.820 |
fisher | -5.780 |
CAST | -5.654 |
Token | Act |
Token ID | 6398 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
ificate | +4.861 |
ills | +4.732 |
iss | +4.578 |
riet | +4.575 |
reme | +4.479 |
Neg logit contributions | |
GOODMAN | -5.713 |
fisher | -5.524 |
autos | -5.413 |
Zimmer | -5.397 |
cast | -5.312 |
Token | ress |
Token ID | 601 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
GOODMAN | +0.207 |
cast | +0.206 |
CAST | +0.202 |
fisher | +0.201 |
#$ | +0.198 |
Neg logit contributions | |
ificate | -0.163 |
ills | -0.151 |
riet | -0.149 |
Downloadha | -0.147 |
reme | -0.146 |
Token | Amy |
Token ID | 14235 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
ificate | +1.935 |
ills | +1.810 |
riet | +1.792 |
reme | +1.757 |
iously | +1.755 |
Neg logit contributions | |
GOODMAN | -2.096 |
cast | -2.075 |
CAST | -2.059 |
fisher | -2.019 |
#$ | -2.010 |
Token | Schumer |
Token ID | 26107 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
GOODMAN | +1.495 |
cast | +1.492 |
CAST | +1.455 |
fisher | +1.444 |
#$ | +1.415 |
Neg logit contributions | |
ificate | -1.935 |
ills | -1.823 |
riet | -1.800 |
Downloadha | -1.783 |
reme | -1.774 |
Token | became |
Token ID | 2627 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
cast | +2.321 |
GOODMAN | +2.304 |
CAST | +2.246 |
fisher | +2.236 |
Zimmer | +2.203 |
Neg logit contributions | |
ificate | -2.453 |
ills | -2.282 |
riet | -2.257 |
Downloadha | -2.253 |
reme | -2.217 |
Token | < |
Token ID | 1279 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
cast | +1.064 |
CAST | +1.042 |
GOODMAN | +1.039 |
fisher | +1.015 |
#$ | +1.008 |
Neg logit contributions | |
ificate | -1.217 |
ills | -1.152 |
riet | -1.141 |
Downloadha | -1.140 |
reme | -1.127 |
Token | T |
Token ID | 309 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
ificate | +2.542 |
ills | +2.354 |
riet | +2.338 |
reme | +2.291 |
iss | +2.288 |
Neg logit contributions | |
GOODMAN | -1.734 |
cast | -1.681 |
CAST | -1.663 |
fisher | -1.654 |
� | -1.628 |
Token | > |
Token ID | 1875 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
ificate | +1.468 |
ills | +1.397 |
riet | +1.377 |
reme | +1.365 |
Downloadha | +1.361 |
Neg logit contributions | |
GOODMAN | -0.679 |
cast | -0.661 |
fisher | -0.642 |
CAST | -0.641 |
#$ | -0.624 |
Token | { |
Token ID | 1391 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
ificate | +0.233 |
ills | +0.217 |
riet | +0.214 |
Downloadha | +0.212 |
reme | +0.210 |
Neg logit contributions | |
cast | -0.260 |
GOODMAN | -0.260 |
CAST | -0.255 |
fisher | -0.253 |
#$ | -0.249 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
GOODMAN | +0.044 |
cast | +0.043 |
CAST | +0.042 |
fisher | +0.042 |
#$ | +0.041 |
Neg logit contributions | |
ificate | -0.053 |
ills | -0.050 |
riet | -0.049 |
reme | -0.048 |
Downloadha | -0.048 |
Token | fn |
Token ID | 24714 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ificate | +3.454 |
ills | +3.206 |
riet | +3.145 |
iss | +3.092 |
iously | +3.081 |
Neg logit contributions | |
GOODMAN | -3.649 |
cast | -3.547 |
CAST | -3.512 |
fisher | -3.451 |
Zimmer | -3.432 |
Token | new |
Token ID | 649 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
ificate | +5.479 |
ills | +5.107 |
iss | +4.998 |
iously | +4.981 |
riet | +4.922 |
Neg logit contributions | |
GOODMAN | -5.063 |
CAST | -4.855 |
cast | -4.815 |
Zimmer | -4.770 |
� | -4.746 |
Token | ( |
Token ID | 357 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ificate | +1.406 |
ills | +1.320 |
riet | +1.294 |
reme | +1.278 |
Downloadha | +1.273 |
Neg logit contributions | |
GOODMAN | -1.343 |
cast | -1.313 |
fisher | -1.291 |
CAST | -1.286 |
Zimmer | -1.267 |
Token | t |
Token ID | 256 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
ificate | +0.766 |
ills | +0.709 |
riet | +0.693 |
reme | +0.686 |
iss | +0.684 |
Neg logit contributions | |
GOODMAN | -0.963 |
cast | -0.928 |
CAST | -0.924 |
fisher | -0.921 |
Zimmer | -0.908 |
Token | : |
Token ID | 1058 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
ificate | +1.157 |
ills | +1.087 |
riet | +1.064 |
reme | +1.055 |
iss | +1.044 |
Neg logit contributions | |
GOODMAN | -1.035 |
cast | -1.006 |
CAST | -0.997 |
fisher | -0.985 |
#$ | -0.978 |
Token | T |
Token ID | 309 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ificate | +1.598 |
ills | +1.488 |
riet | +1.461 |
reme | +1.450 |
iously | +1.445 |
Neg logit contributions | |
GOODMAN | -1.278 |
cast | -1.251 |
CAST | -1.238 |
fisher | -1.217 |
#$ | -1.202 |
Token | Red |
Token ID | 2297 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
GOODMAN | +0.162 |
cast | +0.162 |
CAST | +0.159 |
fisher | +0.157 |
#$ | +0.154 |
Neg logit contributions | |
ificate | -0.175 |
ills | -0.165 |
riet | -0.162 |
Downloadha | -0.160 |
reme | -0.160 |
Token | Christmas |
Token ID | 6786 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
GOODMAN | +0.418 |
cast | +0.414 |
CAST | +0.406 |
fisher | +0.404 |
#$ | +0.397 |
Neg logit contributions | |
ificate | -0.532 |
ills | -0.499 |
riet | -0.492 |
reme | -0.488 |
Downloadha | -0.485 |
Token | album |
Token ID | 5062 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
GOODMAN | +0.649 |
cast | +0.646 |
CAST | +0.631 |
fisher | +0.627 |
#$ | +0.617 |
Neg logit contributions | |
ificate | -0.791 |
ills | -0.744 |
riet | -0.733 |
Downloadha | -0.724 |
reme | -0.724 |
Token | .[ |
Token ID | 3693 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
ificate | +0.257 |
ills | +0.241 |
riet | +0.235 |
reme | +0.232 |
Downloadha | +0.232 |
Neg logit contributions | |
GOODMAN | -0.272 |
cast | -0.270 |
CAST | -0.266 |
fisher | -0.264 |
#$ | -0.261 |
Token | c |
Token ID | 66 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
ificate | +1.625 |
ills | +1.522 |
riet | +1.476 |
iously | +1.466 |
Downloadha | +1.465 |
Neg logit contributions | |
GOODMAN | -1.920 |
cast | -1.878 |
fisher | -1.870 |
CAST | -1.847 |
Zimmer | -1.818 |
Token | itation |
Token ID | 3780 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ificate | +0.416 |
ills | +0.336 |
riet | +0.319 |
Downloadha | +0.305 |
reme | +0.300 |
Neg logit contributions | |
GOODMAN | -2.082 |
cast | -2.080 |
CAST | -2.054 |
fisher | -2.045 |
#$ | -2.025 |
Token | needed |
Token ID | 2622 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
ificate | +3.485 |
ills | +3.008 |
riet | +2.840 |
iously | +2.817 |
iss | +2.803 |
Neg logit contributions | |
GOODMAN | -7.005 |
cast | -6.811 |
cks | -6.778 |
#$ | -6.761 |
sbm | -6.698 |
Token | ] |
Token ID | 60 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
cast | +0.102 |
GOODMAN | +0.101 |
CAST | +0.098 |
fisher | +0.098 |
#$ | +0.096 |
Neg logit contributions | |
ificate | -0.150 |
ills | -0.143 |
riet | -0.142 |
Downloadha | -0.141 |
reme | -0.139 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
GOODMAN | +0.260 |
cast | +0.259 |
CAST | +0.254 |
fisher | +0.253 |
#$ | +0.248 |
Neg logit contributions | |
ificate | -0.266 |
ills | -0.248 |
riet | -0.244 |
Downloadha | -0.241 |
reme | -0.241 |
Token |
|
Token ID | 198 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
ificate | +0.572 |
ills | +0.532 |
riet | +0.520 |
iously | +0.516 |
reme | +0.513 |
Neg logit contributions | |
GOODMAN | -0.588 |
cast | -0.575 |
CAST | -0.568 |
fisher | -0.567 |
� | -0.557 |
Token | As |
Token ID | 1722 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
ificate | +0.557 |
ills | +0.520 |
riet | +0.509 |
Downloadha | +0.502 |
reme | +0.501 |
Neg logit contributions | |
GOODMAN | -0.639 |
cast | -0.619 |
fisher | -0.619 |
Zimmer | -0.605 |
CAST | -0.605 |
Token | . |
Token ID | 13 |
Feature activation | +9.58e-02 |
Pos logit contributions | |
GOODMAN | +0.782 |
cast | +0.781 |
CAST | +0.764 |
fisher | +0.759 |
#$ | +0.747 |
Neg logit contributions | |
ificate | -0.771 |
ills | -0.721 |
riet | -0.711 |
Downloadha | -0.702 |
reme | -0.699 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
GOODMAN | +0.304 |
cast | +0.302 |
fisher | +0.298 |
CAST | +0.296 |
#$ | +0.290 |
Neg logit contributions | |
ificate | -0.291 |
ills | -0.271 |
riet | -0.264 |
reme | -0.262 |
Downloadha | -0.261 |
Token |
|
Token ID | 198 |
Feature activation | -7.61e-03 |
Pos logit contributions | |
ificate | +0.036 |
ills | +0.033 |
riet | +0.033 |
reme | +0.032 |
iously | +0.032 |
Neg logit contributions | |
GOODMAN | -0.036 |
cast | -0.036 |
fisher | -0.036 |
CAST | -0.035 |
Zimmer | -0.035 |
Token | " |
Token ID | 1 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ificate | +0.021 |
ills | +0.019 |
riet | +0.019 |
reme | +0.019 |
Downloadha | +0.019 |
Neg logit contributions | |
GOODMAN | -0.027 |
cast | -0.026 |
fisher | -0.026 |
CAST | -0.025 |
Zimmer | -0.025 |
Token | An |
Token ID | 2025 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
ificate | +0.656 |
ills | +0.607 |
riet | +0.592 |
reme | +0.586 |
Downloadha | +0.583 |
Neg logit contributions | |
GOODMAN | -0.813 |
cast | -0.794 |
fisher | -0.792 |
CAST | -0.780 |
cks | -0.771 |
Token | ub |
Token ID | 549 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
GOODMAN | +1.935 |
cast | +1.925 |
CAST | +1.887 |
fisher | +1.873 |
#$ | +1.840 |
Neg logit contributions | |
ificate | -2.103 |
ills | -1.975 |
riet | -1.945 |
Downloadha | -1.921 |
reme | -1.919 |
Token | h |
Token ID | 71 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
ificate | +4.937 |
ills | +4.811 |
riet | +4.776 |
iss | +4.646 |
reme | +4.635 |
Neg logit contributions | |
GOODMAN | -5.315 |
#$ | -5.039 |
CAST | -5.019 |
fisher | -4.965 |
cast | -4.929 |
Token | av |
Token ID | 615 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
GOODMAN | +0.079 |
CAST | +0.077 |
cast | +0.077 |
fisher | +0.076 |
#$ | +0.075 |
Neg logit contributions | |
ificate | -0.071 |
ills | -0.068 |
riet | -0.066 |
reme | -0.065 |
iss | -0.065 |
Token | Sin |
Token ID | 10884 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
ificate | +1.181 |
ills | +1.119 |
riet | +1.093 |
reme | +1.079 |
iss | +1.079 |
Neg logit contributions | |
GOODMAN | -1.121 |
cast | -1.101 |
CAST | -1.091 |
fisher | -1.076 |
#$ | -1.067 |
Token | ha |
Token ID | 3099 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
GOODMAN | +0.761 |
cast | +0.758 |
CAST | +0.742 |
fisher | +0.736 |
#$ | +0.724 |
Neg logit contributions | |
ificate | -0.836 |
ills | -0.785 |
riet | -0.774 |
Downloadha | -0.765 |
reme | -0.763 |
Token | 's |
Token ID | 338 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
ificate | +0.643 |
ills | +0.606 |
riet | +0.592 |
reme | +0.588 |
Downloadha | +0.584 |
Neg logit contributions | |
GOODMAN | -0.623 |
cast | -0.614 |
CAST | -0.606 |
fisher | -0.599 |
#$ | -0.590 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
GOODMAN | +0.684 |
cast | +0.683 |
CAST | +0.667 |
fisher | +0.663 |
#$ | +0.652 |
Neg logit contributions | |
ificate | -0.696 |
ills | -0.653 |
riet | -0.643 |
Downloadha | -0.635 |
reme | -0.633 |
Token | 2 |
Token ID | 362 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
GOODMAN | +0.523 |
cast | +0.522 |
CAST | +0.509 |
fisher | +0.507 |
Zimmer | +0.498 |
Neg logit contributions | |
ificate | -0.485 |
ills | -0.453 |
riet | -0.446 |
Downloadha | -0.443 |
reme | -0.438 |
Token | 18 |
Token ID | 1248 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ificate | +1.549 |
ills | +1.464 |
riet | +1.438 |
reme | +1.420 |
iously | +1.416 |
Neg logit contributions | |
GOODMAN | -1.256 |
cast | -1.252 |
CAST | -1.227 |
fisher | -1.208 |
#$ | -1.200 |
Token | K |
Token ID | 42 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
ificate | +0.717 |
ills | +0.669 |
riet | +0.658 |
reme | +0.648 |
Downloadha | +0.648 |
Neg logit contributions | |
GOODMAN | -0.760 |
cast | -0.759 |
CAST | -0.744 |
fisher | -0.738 |
#$ | -0.729 |
Token | Shares |
Token ID | 23997 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
cast | +1.638 |
GOODMAN | +1.629 |
fisher | +1.580 |
CAST | +1.576 |
Zimmer | +1.558 |
Neg logit contributions | |
ificate | -1.197 |
Downloadha | -1.100 |
riet | -1.099 |
ills | -1.099 |
iously | -1.077 |
Token |
|
Token ID | 198 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ificate | +4.264 |
ills | +3.896 |
riet | +3.808 |
iously | +3.794 |
iss | +3.787 |
Neg logit contributions | |
GOODMAN | -4.715 |
CAST | -4.677 |
cast | -4.617 |
fisher | -4.580 |
#$ | -4.492 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ificate | +4.293 |
ills | +3.919 |
iss | +3.807 |
iously | +3.792 |
riet | +3.716 |
Neg logit contributions | |
�醒 | -6.026 |
GOODMAN | -5.982 |
� | -5.820 |
fisher | -5.780 |
CAST | -5.654 |
Token | Act |
Token ID | 6398 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
ificate | +4.861 |
ills | +4.732 |
iss | +4.578 |
riet | +4.575 |
reme | +4.479 |
Neg logit contributions | |
GOODMAN | -5.713 |
fisher | -5.524 |
autos | -5.413 |
Zimmer | -5.397 |
cast | -5.312 |
Token | ress |
Token ID | 601 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
GOODMAN | +0.207 |
cast | +0.206 |
CAST | +0.202 |
fisher | +0.201 |
#$ | +0.198 |
Neg logit contributions | |
ificate | -0.163 |
ills | -0.151 |
riet | -0.149 |
Downloadha | -0.147 |
reme | -0.146 |
Token | Amy |
Token ID | 14235 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
ificate | +1.935 |
ills | +1.810 |
riet | +1.792 |
reme | +1.757 |
iously | +1.755 |
Neg logit contributions | |
GOODMAN | -2.096 |
cast | -2.075 |
CAST | -2.059 |
fisher | -2.019 |
#$ | -2.010 |
Token | Schumer |
Token ID | 26107 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
GOODMAN | +1.495 |
cast | +1.492 |
CAST | +1.455 |
fisher | +1.444 |
#$ | +1.415 |
Neg logit contributions | |
ificate | -1.935 |
ills | -1.823 |
riet | -1.800 |
Downloadha | -1.783 |
reme | -1.774 |
Token | Guard |
Token ID | 4932 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ificate | +2.424 |
ills | +2.264 |
riet | +2.208 |
iss | +2.186 |
reme | +2.185 |
Neg logit contributions | |
GOODMAN | -2.071 |
cast | -2.024 |
CAST | -2.012 |
#$ | -1.967 |
fisher | -1.964 |
Token | { |
Token ID | 1391 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
ificate | +0.893 |
ills | +0.834 |
riet | +0.819 |
Downloadha | +0.809 |
reme | +0.807 |
Neg logit contributions | |
GOODMAN | -0.864 |
cast | -0.854 |
CAST | -0.837 |
fisher | -0.831 |
#$ | -0.817 |
Token | ... |
Token ID | 2644 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
GOODMAN | +0.642 |
cast | +0.630 |
CAST | +0.620 |
fisher | +0.614 |
#$ | +0.604 |
Neg logit contributions | |
ificate | -0.681 |
ills | -0.636 |
riet | -0.624 |
reme | -0.615 |
Downloadha | -0.612 |
Token | } |
Token ID | 1782 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ificate | +1.132 |
ills | +1.052 |
riet | +1.026 |
reme | +1.021 |
iss | +1.019 |
Neg logit contributions | |
GOODMAN | -0.995 |
cast | -0.970 |
CAST | -0.960 |
fisher | -0.948 |
Zimmer | -0.933 |
Token | pub |
Token ID | 2240 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
GOODMAN | +0.347 |
cast | +0.346 |
CAST | +0.338 |
fisher | +0.335 |
#$ | +0.329 |
Neg logit contributions | |
ificate | -0.382 |
ills | -0.359 |
riet | -0.354 |
Downloadha | -0.349 |
reme | -0.348 |
Token | fn |
Token ID | 24714 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ificate | +3.239 |
ills | +3.001 |
riet | +2.954 |
iss | +2.908 |
iously | +2.898 |
Neg logit contributions | |
GOODMAN | -2.987 |
cast | -2.928 |
CAST | -2.884 |
fisher | -2.834 |
Zimmer | -2.817 |
Token | pin |
Token ID | 6757 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
ificate | +5.420 |
ills | +5.066 |
iously | +4.965 |
iss | +4.952 |
riet | +4.888 |
Neg logit contributions | |
GOODMAN | -4.803 |
CAST | -4.660 |
cast | -4.595 |
Zimmer | -4.488 |
#$ | -4.478 |
Token | () |
Token ID | 7499 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
ificate | +1.274 |
ills | +1.192 |
riet | +1.175 |
Downloadha | +1.160 |
reme | +1.158 |
Neg logit contributions | |
GOODMAN | -1.175 |
cast | -1.165 |
CAST | -1.141 |
fisher | -1.134 |
#$ | -1.114 |
Token | -> |
Token ID | 4613 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
ificate | +1.628 |
ills | +1.531 |
riet | +1.506 |
reme | +1.487 |
Downloadha | +1.479 |
Neg logit contributions | |
GOODMAN | -1.336 |
cast | -1.311 |
CAST | -1.293 |
fisher | -1.275 |
Zimmer | -1.252 |
Token | Guard |
Token ID | 4932 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
ificate | +1.477 |
ills | +1.378 |
riet | +1.346 |
iously | +1.335 |
reme | +1.330 |
Neg logit contributions | |
GOODMAN | -1.397 |
cast | -1.387 |
CAST | -1.368 |
fisher | -1.346 |
#$ | -1.326 |
Token | ; |
Token ID | 2162 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
ificate | +1.009 |
ills | +0.941 |
riet | +0.925 |
Downloadha | +0.912 |
reme | +0.911 |
Neg logit contributions | |
GOODMAN | -0.971 |
cast | -0.960 |
CAST | -0.942 |
fisher | -0.935 |
#$ | -0.918 |
Token | wrap |
Token ID | 37150 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
GOODMAN | +0.719 |
cast | +0.718 |
CAST | +0.703 |
fisher | +0.698 |
#$ | +0.686 |
Neg logit contributions | |
ificate | -0.704 |
ills | -0.658 |
riet | -0.648 |
Downloadha | -0.641 |
reme | -0.638 |
Token | ()) |
Token ID | 32865 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
cast | +1.450 |
GOODMAN | +1.416 |
CAST | +1.408 |
fisher | +1.382 |
#$ | +1.363 |
Neg logit contributions | |
ificate | -1.701 |
ills | -1.596 |
riet | -1.594 |
Downloadha | -1.585 |
reme | -1.561 |
Token | } |
Token ID | 1782 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
ificate | +0.460 |
ills | +0.433 |
riet | +0.427 |
Downloadha | +0.422 |
reme | +0.421 |
Neg logit contributions | |
GOODMAN | -0.383 |
cast | -0.382 |
CAST | -0.373 |
fisher | -0.370 |
#$ | -0.363 |
Token | } |
Token ID | 1782 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
GOODMAN | +0.770 |
cast | +0.770 |
CAST | +0.750 |
fisher | +0.745 |
#$ | +0.730 |
Neg logit contributions | |
ificate | -1.028 |
ills | -0.970 |
riet | -0.959 |
Downloadha | -0.950 |
reme | -0.945 |
Token | pub |
Token ID | 2240 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
cast | +0.858 |
GOODMAN | +0.853 |
CAST | +0.836 |
fisher | +0.830 |
#$ | +0.814 |
Neg logit contributions | |
ificate | -1.043 |
ills | -0.982 |
riet | -0.973 |
Downloadha | -0.966 |
reme | -0.956 |
Token | fn |
Token ID | 24714 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ificate | +2.907 |
ills | +2.707 |
riet | +2.653 |
reme | +2.613 |
iously | +2.601 |
Neg logit contributions | |
GOODMAN | -3.179 |
cast | -3.122 |
CAST | -3.075 |
fisher | -3.043 |
Zimmer | -3.014 |
Token | apply |
Token ID | 4174 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
ificate | +4.957 |
ills | +4.698 |
iss | +4.559 |
reme | +4.510 |
iously | +4.506 |
Neg logit contributions | |
GOODMAN | -5.111 |
CAST | -5.067 |
cast | -5.003 |
� | -4.894 |
Zimmer | -4.875 |
Token | _ |
Token ID | 62 |
Feature activation | -9.70e-03 |
Pos logit contributions | |
ificate | +1.279 |
ills | +1.199 |
riet | +1.165 |
reme | +1.155 |
iously | +1.151 |
Neg logit contributions | |
GOODMAN | -1.349 |
cast | -1.307 |
fisher | -1.294 |
CAST | -1.281 |
Zimmer | -1.273 |
Token | move |
Token ID | 21084 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
ificate | +0.025 |
ills | +0.023 |
riet | +0.023 |
Downloadha | +0.023 |
reme | +0.023 |
Neg logit contributions | |
GOODMAN | -0.035 |
cast | -0.035 |
CAST | -0.034 |
fisher | -0.034 |
Zimmer | -0.034 |
Token | ( |
Token ID | 357 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
ificate | +0.065 |
ills | +0.061 |
riet | +0.060 |
Downloadha | +0.060 |
reme | +0.059 |
Neg logit contributions | |
cast | -0.059 |
GOODMAN | -0.058 |
CAST | -0.057 |
fisher | -0.056 |
#$ | -0.055 |
Token | & |
Token ID | 1222 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
ificate | +1.113 |
ills | +1.026 |
riet | +0.999 |
reme | +0.996 |
Downloadha | +0.983 |
Neg logit contributions | |
GOODMAN | -1.443 |
cast | -1.421 |
CAST | -1.402 |
fisher | -1.394 |
Zimmer | -1.378 |
Token | truly |
Token ID | 4988 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
ificate | +0.607 |
ills | +0.568 |
riet | +0.558 |
reme | +0.547 |
iously | +0.547 |
Neg logit contributions | |
GOODMAN | -0.663 |
cast | -0.645 |
CAST | -0.641 |
fisher | -0.630 |
#$ | -0.628 |
Token | afraid |
Token ID | 7787 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
GOODMAN | +1.057 |
cast | +1.049 |
CAST | +1.032 |
fisher | +1.023 |
#$ | +1.010 |
Neg logit contributions | |
ificate | -0.897 |
ills | -0.837 |
riet | -0.822 |
Downloadha | -0.808 |
reme | -0.808 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
GOODMAN | +1.273 |
cast | +1.273 |
CAST | +1.245 |
fisher | +1.237 |
#$ | +1.216 |
Neg logit contributions | |
ificate | -1.238 |
ills | -1.157 |
riet | -1.142 |
Downloadha | -1.128 |
reme | -1.123 |
Token | The |
Token ID | 383 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
ificate | +0.441 |
ills | +0.411 |
riet | +0.400 |
iously | +0.396 |
iss | +0.395 |
Neg logit contributions | |
GOODMAN | -0.451 |
cast | -0.445 |
CAST | -0.441 |
fisher | -0.438 |
#$ | -0.428 |
Token | first |
Token ID | 717 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ificate | +0.244 |
ills | +0.228 |
riet | +0.223 |
reme | +0.220 |
iously | +0.220 |
Neg logit contributions | |
GOODMAN | -0.246 |
cast | -0.243 |
CAST | -0.239 |
fisher | -0.236 |
#$ | -0.234 |
Token | time |
Token ID | 640 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ificate | +3.258 |
ills | +3.079 |
iously | +3.014 |
riet | +2.990 |
iss | +2.953 |
Neg logit contributions | |
GOODMAN | -3.432 |
CAST | -3.367 |
cast | -3.287 |
#$ | -3.278 |
fisher | -3.212 |
Token | , |
Token ID | 11 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ificate | +4.211 |
ills | +3.978 |
iss | +3.827 |
riet | +3.825 |
iously | +3.811 |
Neg logit contributions | |
GOODMAN | -5.555 |
CAST | -5.487 |
cast | -5.328 |
fisher | -5.225 |
#$ | -5.224 |
Token | he |
Token ID | 339 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
ificate | +0.920 |
ills | +0.864 |
riet | +0.847 |
Downloadha | +0.836 |
reme | +0.834 |
Neg logit contributions | |
GOODMAN | -0.890 |
CAST | -0.876 |
cast | -0.875 |
fisher | -0.853 |
#$ | -0.845 |
Token | genuinely |
Token ID | 17170 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ificate | +0.916 |
ills | +0.848 |
riet | +0.835 |
iously | +0.822 |
reme | +0.816 |
Neg logit contributions | |
GOODMAN | -1.248 |
cast | -1.218 |
CAST | -1.214 |
fisher | -1.188 |
#$ | -1.182 |
Token | believed |
Token ID | 4762 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
ificate | +0.356 |
ills | +0.331 |
riet | +0.327 |
iously | +0.319 |
reme | +0.319 |
Neg logit contributions | |
GOODMAN | -0.431 |
cast | -0.422 |
CAST | -0.421 |
fisher | -0.411 |
#$ | -0.408 |
Token | he |
Token ID | 339 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
GOODMAN | +1.008 |
cast | +1.002 |
CAST | +0.980 |
fisher | +0.969 |
#$ | +0.953 |
Neg logit contributions | |
ificate | -1.311 |
ills | -1.238 |
riet | -1.219 |
Downloadha | -1.207 |
reme | -1.203 |
Token | United |
Token ID | 1578 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
ificate | +1.093 |
ills | +1.037 |
riet | +1.021 |
reme | +1.013 |
iously | +1.008 |
Neg logit contributions | |
cast | -0.768 |
GOODMAN | -0.767 |
CAST | -0.759 |
#$ | -0.735 |
fisher | -0.728 |
Token | States |
Token ID | 1829 |
Feature activation | -6.87e-03 |
Pos logit contributions | |
GOODMAN | +0.816 |
cast | +0.815 |
CAST | +0.798 |
fisher | +0.792 |
#$ | +0.780 |
Neg logit contributions | |
ificate | -0.772 |
ills | -0.721 |
riet | -0.710 |
Downloadha | -0.701 |
reme | -0.699 |
Token | on |
Token ID | 319 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ificate | +0.020 |
ills | +0.019 |
riet | +0.019 |
Downloadha | +0.018 |
reme | +0.018 |
Neg logit contributions | |
GOODMAN | -0.022 |
cast | -0.022 |
CAST | -0.022 |
fisher | -0.022 |
#$ | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
ificate | +0.984 |
ills | +0.927 |
iously | +0.901 |
riet | +0.893 |
reme | +0.891 |
Neg logit contributions | |
cast | -0.848 |
GOODMAN | -0.847 |
CAST | -0.838 |
#$ | -0.821 |
fisher | -0.807 |
Token | very |
Token ID | 845 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
ificate | +0.194 |
ills | +0.182 |
riet | +0.178 |
reme | +0.177 |
iss | +0.176 |
Neg logit contributions | |
cast | -0.169 |
GOODMAN | -0.167 |
CAST | -0.167 |
#$ | -0.161 |
fisher | -0.161 |
Token | day |
Token ID | 1110 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ificate | +1.337 |
ills | +1.253 |
riet | +1.212 |
iously | +1.208 |
reme | +1.204 |
Neg logit contributions | |
cast | -1.495 |
CAST | -1.482 |
GOODMAN | -1.469 |
#$ | -1.451 |
fisher | -1.428 |
Token | of |
Token ID | 286 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
ificate | +5.011 |
ills | +4.749 |
iss | +4.650 |
riet | +4.543 |
reme | +4.520 |
Neg logit contributions | |
CAST | -4.839 |
cast | -4.696 |
GOODMAN | -4.648 |
#$ | -4.525 |
fisher | -4.508 |
Token | his |
Token ID | 465 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ificate | +1.967 |
ills | +1.859 |
iss | +1.815 |
riet | +1.811 |
reme | +1.801 |
Neg logit contributions | |
GOODMAN | -1.430 |
cast | -1.427 |
CAST | -1.419 |
fisher | -1.380 |
#$ | -1.371 |
Token | inauguration |
Token ID | 23166 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
ificate | +0.753 |
ills | +0.700 |
riet | +0.689 |
reme | +0.682 |
iously | +0.680 |
Neg logit contributions | |
GOODMAN | -0.728 |
cast | -0.727 |
CAST | -0.716 |
#$ | -0.700 |
fisher | -0.698 |
Token | . |
Token ID | 13 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
ificate | +0.971 |
ills | +0.905 |
riet | +0.879 |
reme | +0.870 |
iously | +0.870 |
Neg logit contributions | |
GOODMAN | -1.098 |
cast | -1.093 |
CAST | -1.081 |
fisher | -1.063 |
#$ | -1.053 |
Token | On |
Token ID | 1550 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ificate | +1.080 |
ills | +1.009 |
riet | +0.978 |
reme | +0.970 |
iss | +0.970 |
Neg logit contributions | |
cast | -1.127 |
GOODMAN | -1.127 |
CAST | -1.108 |
fisher | -1.102 |
#$ | -1.074 |
Token | < |
Token ID | 1279 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
ificate | +1.481 |
ills | +1.389 |
riet | +1.360 |
reme | +1.343 |
Downloadha | +1.341 |
Neg logit contributions | |
GOODMAN | -1.296 |
cast | -1.273 |
fisher | -1.243 |
CAST | -1.243 |
Zimmer | -1.219 |
Token | T |
Token ID | 309 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
ificate | +2.323 |
ills | +2.170 |
riet | +2.138 |
reme | +2.109 |
iss | +2.097 |
Neg logit contributions | |
GOODMAN | -1.548 |
cast | -1.516 |
CAST | -1.486 |
fisher | -1.482 |
� | -1.463 |
Token | > |
Token ID | 1875 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
ificate | +1.699 |
ills | +1.621 |
riet | +1.599 |
reme | +1.585 |
Downloadha | +1.582 |
Neg logit contributions | |
GOODMAN | -0.704 |
cast | -0.690 |
CAST | -0.667 |
fisher | -0.663 |
#$ | -0.647 |
Token | { |
Token ID | 1391 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
cast | +0.048 |
GOODMAN | +0.048 |
CAST | +0.047 |
fisher | +0.047 |
#$ | +0.046 |
Neg logit contributions | |
ificate | -0.049 |
ills | -0.045 |
riet | -0.045 |
Downloadha | -0.045 |
reme | -0.044 |
Token | pub |
Token ID | 2240 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
GOODMAN | +0.430 |
cast | +0.428 |
CAST | +0.418 |
fisher | +0.415 |
#$ | +0.407 |
Neg logit contributions | |
ificate | -0.526 |
ills | -0.495 |
riet | -0.488 |
Downloadha | -0.482 |
reme | -0.481 |
Token | fn |
Token ID | 24714 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ificate | +2.881 |
ills | +2.667 |
riet | +2.606 |
reme | +2.559 |
iss | +2.558 |
Neg logit contributions | |
GOODMAN | -3.326 |
cast | -3.261 |
CAST | -3.222 |
fisher | -3.169 |
Zimmer | -3.149 |
Token | load |
Token ID | 3440 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ificate | +5.298 |
ills | +4.972 |
iss | +4.833 |
iously | +4.816 |
riet | +4.732 |
Neg logit contributions | |
GOODMAN | -4.575 |
CAST | -4.439 |
cast | -4.379 |
� | -4.314 |
Zimmer | -4.297 |
Token | < |
Token ID | 1279 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
cast | +1.169 |
CAST | +1.142 |
GOODMAN | +1.141 |
fisher | +1.116 |
cks | +1.097 |
Neg logit contributions | |
ificate | -1.310 |
ills | -1.230 |
riet | -1.227 |
Downloadha | -1.216 |
reme | -1.197 |
Token | ' |
Token ID | 705 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
ificate | +2.408 |
ills | +2.248 |
riet | +2.196 |
iss | +2.161 |
reme | +2.157 |
Neg logit contributions | |
GOODMAN | -2.033 |
cast | -1.960 |
CAST | -1.957 |
fisher | -1.945 |
� | -1.916 |
Token | a |
Token ID | 64 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
ificate | +2.392 |
ills | +2.226 |
riet | +2.156 |
iss | +2.137 |
reme | +2.133 |
Neg logit contributions | |
GOODMAN | -2.672 |
CAST | -2.585 |
fisher | -2.574 |
cast | -2.572 |
#$ | -2.507 |
Token | > |
Token ID | 1875 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
ificate | +2.200 |
ills | +2.065 |
riet | +2.019 |
reme | +1.990 |
iss | +1.989 |
Neg logit contributions | |
GOODMAN | -1.845 |
cast | -1.816 |
CAST | -1.793 |
fisher | -1.781 |
#$ | -1.743 |
Token | null |
Token ID | 9242 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ificate | +0.887 |
ills | +0.829 |
riet | +0.808 |
iously | +0.805 |
reme | +0.800 |
Neg logit contributions | |
GOODMAN | -0.847 |
cast | -0.836 |
CAST | -0.828 |
fisher | -0.818 |
#$ | -0.805 |
Token | atomic |
Token ID | 17226 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
GOODMAN | +0.615 |
cast | +0.606 |
CAST | +0.597 |
fisher | +0.596 |
Zimmer | +0.584 |
Neg logit contributions | |
ificate | -0.634 |
ills | -0.588 |
riet | -0.580 |
iously | -0.572 |
reme | -0.572 |
Token | pointer |
Token ID | 17562 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
ificate | +1.309 |
ills | +1.203 |
riet | +1.186 |
iously | +1.179 |
reme | +1.174 |
Neg logit contributions | |
GOODMAN | -1.137 |
cast | -1.106 |
CAST | -1.099 |
fisher | -1.086 |
� | -1.072 |
Token | . |
Token ID | 13 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
ificate | +0.425 |
ills | +0.395 |
riet | +0.388 |
reme | +0.383 |
iously | +0.382 |
Neg logit contributions | |
GOODMAN | -0.415 |
cast | -0.407 |
CAST | -0.400 |
fisher | -0.398 |
Zimmer | -0.391 |
Token | pub |
Token ID | 2240 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
ificate | +0.219 |
ills | +0.206 |
riet | +0.202 |
reme | +0.199 |
Downloadha | +0.198 |
Neg logit contributions | |
GOODMAN | -0.191 |
cast | -0.188 |
CAST | -0.184 |
fisher | -0.183 |
Zimmer | -0.180 |
Token | fn |
Token ID | 24714 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ificate | +2.896 |
ills | +2.667 |
riet | +2.626 |
iously | +2.591 |
reme | +2.580 |
Neg logit contributions | |
GOODMAN | -2.989 |
cast | -2.899 |
CAST | -2.861 |
fisher | -2.818 |
Zimmer | -2.816 |
Token | null |
Token ID | 9242 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
ificate | +3.952 |
ills | +3.660 |
iss | +3.567 |
iously | +3.547 |
reme | +3.458 |
Neg logit contributions | |
GOODMAN | -5.743 |
CAST | -5.487 |
cast | -5.456 |
Zimmer | -5.420 |
� | -5.417 |
Token | () |
Token ID | 7499 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
cast | +0.255 |
GOODMAN | +0.253 |
CAST | +0.248 |
fisher | +0.246 |
#$ | +0.241 |
Neg logit contributions | |
ificate | -0.272 |
ills | -0.255 |
riet | -0.252 |
Downloadha | -0.250 |
reme | -0.248 |
Token | -> |
Token ID | 4613 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ificate | +1.043 |
ills | +0.988 |
riet | +0.973 |
Downloadha | +0.961 |
reme | +0.961 |
Neg logit contributions | |
GOODMAN | -0.720 |
cast | -0.711 |
CAST | -0.696 |
fisher | -0.689 |
#$ | -0.675 |
Token | Atomic |
Token ID | 28976 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
ificate | +1.156 |
ills | +1.087 |
riet | +1.064 |
iously | +1.062 |
reme | +1.057 |
Neg logit contributions | |
GOODMAN | -0.784 |
cast | -0.772 |
CAST | -0.762 |
fisher | -0.749 |
� | -0.735 |
Token | < |
Token ID | 1279 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
ificate | +1.773 |
ills | +1.656 |
riet | +1.618 |
reme | +1.603 |
iously | +1.601 |
Neg logit contributions | |
GOODMAN | -1.549 |
cast | -1.513 |
CAST | -1.487 |
fisher | -1.485 |
Zimmer | -1.456 |
Token | state |
Token ID | 5219 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
ificate | +0.578 |
ills | +0.541 |
riet | +0.533 |
iss | +0.528 |
reme | +0.526 |
Neg logit contributions | |
GOODMAN | -0.548 |
cast | -0.521 |
fisher | -0.519 |
CAST | -0.518 |
Zimmer | -0.515 |
Token | ); |
Token ID | 5619 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ificate | +1.371 |
ills | +1.276 |
riet | +1.241 |
reme | +1.229 |
Downloadha | +1.223 |
Neg logit contributions | |
GOODMAN | -1.501 |
cast | -1.482 |
CAST | -1.460 |
fisher | -1.453 |
#$ | -1.426 |
Token | ... |
Token ID | 2644 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
GOODMAN | +0.603 |
cast | +0.597 |
CAST | +0.585 |
fisher | +0.579 |
#$ | +0.569 |
Neg logit contributions | |
ificate | -0.768 |
ills | -0.723 |
riet | -0.711 |
reme | -0.702 |
Downloadha | -0.701 |
Token | } |
Token ID | 1782 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
ificate | +0.129 |
ills | +0.122 |
riet | +0.119 |
reme | +0.118 |
iously | +0.117 |
Neg logit contributions | |
GOODMAN | -0.104 |
cast | -0.103 |
CAST | -0.101 |
fisher | -0.100 |
Zimmer | -0.098 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
cast | +0.976 |
GOODMAN | +0.972 |
CAST | +0.952 |
fisher | +0.945 |
#$ | +0.928 |
Neg logit contributions | |
ificate | -1.161 |
ills | -1.092 |
riet | -1.081 |
Downloadha | -1.072 |
reme | -1.064 |
Token | fn |
Token ID | 24714 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ificate | +3.080 |
ills | +2.854 |
riet | +2.795 |
reme | +2.763 |
iss | +2.742 |
Neg logit contributions | |
GOODMAN | -3.465 |
cast | -3.403 |
CAST | -3.358 |
fisher | -3.320 |
Zimmer | -3.290 |
Token | undo |
Token ID | 23981 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ificate | +4.487 |
ills | +4.302 |
iss | +4.161 |
reme | +4.136 |
iously | +4.114 |
Neg logit contributions | |
GOODMAN | -4.980 |
CAST | -4.966 |
cast | -4.909 |
� | -4.764 |
Zimmer | -4.752 |
Token | _ |
Token ID | 62 |
Feature activation | +7.45e-04 |
Pos logit contributions | |
ificate | +0.363 |
ills | +0.339 |
riet | +0.330 |
iously | +0.327 |
reme | +0.327 |
Neg logit contributions | |
GOODMAN | -0.367 |
cast | -0.358 |
fisher | -0.354 |
CAST | -0.351 |
#$ | -0.346 |
Token | move |
Token ID | 21084 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
GOODMAN | +0.003 |
cast | +0.003 |
fisher | +0.003 |
CAST | +0.003 |
Zimmer | +0.003 |
Neg logit contributions | |
ificate | -0.002 |
ills | -0.002 |
riet | -0.002 |
reme | -0.002 |
iss | -0.002 |
Token | ( |
Token ID | 357 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
ificate | +0.390 |
ills | +0.366 |
riet | +0.363 |
Downloadha | +0.362 |
reme | +0.357 |
Neg logit contributions | |
cast | -0.351 |
GOODMAN | -0.347 |
CAST | -0.342 |
fisher | -0.338 |
Zimmer | -0.331 |
Token | & |
Token ID | 1222 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
ificate | +1.480 |
ills | +1.363 |
riet | +1.338 |
reme | +1.324 |
Downloadha | +1.314 |
Neg logit contributions | |
GOODMAN | -1.893 |
cast | -1.876 |
CAST | -1.846 |
fisher | -1.835 |
Zimmer | -1.810 |
Token |
|
Token ID | 198 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
GOODMAN | +0.718 |
cast | +0.710 |
CAST | +0.697 |
fisher | +0.694 |
#$ | +0.680 |
Neg logit contributions | |
ificate | -0.745 |
ills | -0.697 |
riet | -0.686 |
reme | -0.675 |
Downloadha | -0.675 |
Token | impl |
Token ID | 23928 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
GOODMAN | +0.516 |
cast | +0.506 |
fisher | +0.499 |
CAST | +0.496 |
Zimmer | +0.487 |
Neg logit contributions | |
ificate | -0.542 |
ills | -0.509 |
riet | -0.500 |
reme | -0.493 |
Downloadha | -0.492 |
Token | Board |
Token ID | 5926 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
ificate | +2.628 |
ills | +2.423 |
reme | +2.372 |
iss | +2.355 |
riet | +2.342 |
Neg logit contributions | |
GOODMAN | -2.594 |
cast | -2.521 |
fisher | -2.497 |
CAST | -2.486 |
� | -2.435 |
Token | { |
Token ID | 1391 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
ificate | +0.639 |
ills | +0.596 |
riet | +0.585 |
reme | +0.577 |
Downloadha | +0.575 |
Neg logit contributions | |
GOODMAN | -0.675 |
cast | -0.665 |
CAST | -0.652 |
fisher | -0.651 |
#$ | -0.637 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
cast | +1.466 |
GOODMAN | +1.464 |
CAST | +1.430 |
fisher | +1.419 |
#$ | +1.393 |
Neg logit contributions | |
ificate | -1.774 |
ills | -1.670 |
riet | -1.650 |
Downloadha | -1.634 |
reme | -1.624 |
Token | fn |
Token ID | 24714 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ificate | +2.981 |
ills | +2.795 |
riet | +2.714 |
iss | +2.683 |
reme | +2.669 |
Neg logit contributions | |
GOODMAN | -3.343 |
cast | -3.240 |
CAST | -3.205 |
fisher | -3.174 |
Zimmer | -3.141 |
Token | copy |
Token ID | 4866 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
ificate | +4.291 |
ills | +4.036 |
iss | +3.894 |
reme | +3.883 |
iously | +3.847 |
Neg logit contributions | |
GOODMAN | -5.239 |
CAST | -5.150 |
cast | -5.062 |
#$ | -5.024 |
fisher | -4.999 |
Token | _ |
Token ID | 62 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
cast | +0.175 |
GOODMAN | +0.171 |
CAST | +0.170 |
fisher | +0.167 |
#$ | +0.165 |
Neg logit contributions | |
ificate | -0.199 |
ills | -0.186 |
riet | -0.185 |
Downloadha | -0.184 |
reme | -0.182 |
Token | board |
Token ID | 3526 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
cast | +0.709 |
GOODMAN | +0.707 |
CAST | +0.694 |
fisher | +0.689 |
#$ | +0.679 |
Neg logit contributions | |
ificate | -0.585 |
ills | -0.543 |
riet | -0.535 |
Downloadha | -0.529 |
reme | -0.524 |
Token | ( |
Token ID | 357 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
ificate | +0.122 |
ills | +0.114 |
riet | +0.113 |
Downloadha | +0.113 |
reme | +0.111 |
Neg logit contributions | |
cast | -0.111 |
GOODMAN | -0.110 |
CAST | -0.108 |
fisher | -0.107 |
#$ | -0.105 |
Token | & |
Token ID | 1222 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
ificate | +1.298 |
ills | +1.202 |
reme | +1.171 |
riet | +1.166 |
iss | +1.160 |
Neg logit contributions | |
GOODMAN | -1.612 |
cast | -1.558 |
CAST | -1.548 |
fisher | -1.539 |
Zimmer | -1.523 |
Token | A |
Token ID | 32 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
GOODMAN | +0.603 |
cast | +0.601 |
CAST | +0.589 |
fisher | +0.586 |
#$ | +0.577 |
Neg logit contributions | |
ificate | -0.525 |
ills | -0.489 |
riet | -0.481 |
Downloadha | -0.475 |
reme | -0.473 |
Token | sixth |
Token ID | 11695 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ificate | +0.269 |
ills | +0.252 |
riet | +0.249 |
reme | +0.245 |
Downloadha | +0.242 |
Neg logit contributions | |
GOODMAN | -0.286 |
cast | -0.284 |
CAST | -0.278 |
fisher | -0.276 |
#$ | -0.272 |
Token | firm |
Token ID | 4081 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
ificate | +0.425 |
ills | +0.398 |
riet | +0.392 |
reme | +0.387 |
iously | +0.384 |
Neg logit contributions | |
GOODMAN | -0.446 |
cast | -0.443 |
CAST | -0.435 |
fisher | -0.428 |
#$ | -0.426 |
Token | was |
Token ID | 373 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
GOODMAN | +1.103 |
cast | +1.100 |
CAST | +1.077 |
fisher | +1.069 |
#$ | +1.054 |
Neg logit contributions | |
ificate | -1.112 |
ills | -1.044 |
riet | -1.028 |
Downloadha | -1.014 |
reme | -1.010 |
Token | let |
Token ID | 1309 |
Feature activation | +8.88e-02 |
Pos logit contributions | |
GOODMAN | +0.620 |
cast | +0.618 |
CAST | +0.606 |
fisher | +0.601 |
#$ | +0.594 |
Neg logit contributions | |
ificate | -0.565 |
ills | -0.528 |
riet | -0.519 |
Downloadha | -0.510 |
reme | -0.510 |
Token | off |
Token ID | 572 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
GOODMAN | +0.295 |
cast | +0.294 |
CAST | +0.289 |
fisher | +0.286 |
#$ | +0.283 |
Neg logit contributions | |
ificate | -0.257 |
ills | -0.240 |
riet | -0.236 |
Downloadha | -0.232 |
reme | -0.232 |
Token | because |
Token ID | 780 |
Feature activation | +9.41e-02 |
Pos logit contributions | |
ificate | +4.441 |
ills | +4.131 |
iss | +4.080 |
riet | +4.003 |
iously | +3.963 |
Neg logit contributions | |
CAST | -5.100 |
GOODMAN | -5.091 |
cast | -5.067 |
#$ | -4.955 |
� | -4.944 |
Token | it |
Token ID | 340 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
GOODMAN | +0.290 |
cast | +0.290 |
CAST | +0.283 |
fisher | +0.281 |
#$ | +0.277 |
Neg logit contributions | |
ificate | -0.295 |
ills | -0.276 |
riet | -0.272 |
Downloadha | -0.269 |
reme | -0.268 |
Token | had |
Token ID | 550 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
GOODMAN | +0.403 |
cast | +0.399 |
CAST | +0.394 |
fisher | +0.386 |
#$ | +0.384 |
Neg logit contributions | |
ificate | -0.320 |
ills | -0.298 |
riet | -0.294 |
iously | -0.289 |
reme | -0.287 |
Token | blown |
Token ID | 16318 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
GOODMAN | +1.097 |
cast | +1.094 |
CAST | +1.073 |
fisher | +1.063 |
#$ | +1.049 |
Neg logit contributions | |
ificate | -1.006 |
ills | -0.938 |
riet | -0.924 |
Downloadha | -0.911 |
reme | -0.908 |
Token | the |
Token ID | 262 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ificate | +0.752 |
ills | +0.707 |
riet | +0.691 |
reme | +0.684 |
iously | +0.681 |
Neg logit contributions | |
GOODMAN | -0.743 |
cast | -0.729 |
CAST | -0.723 |
fisher | -0.710 |
#$ | -0.707 |
Token | � |
Token ID | 247 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
ificate | +0.639 |
ills | +0.602 |
riet | +0.593 |
reme | +0.582 |
Downloadha | +0.581 |
Neg logit contributions | |
GOODMAN | -0.541 |
cast | -0.539 |
CAST | -0.526 |
fisher | -0.522 |
Zimmer | -0.511 |
Token | . |
Token ID | 13 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
GOODMAN | +1.024 |
cast | +1.023 |
CAST | +1.001 |
fisher | +0.995 |
#$ | +0.978 |
Neg logit contributions | |
ificate | -0.996 |
ills | -0.930 |
riet | -0.918 |
Downloadha | -0.907 |
reme | -0.902 |
Token | Like |
Token ID | 4525 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
ificate | +0.241 |
ills | +0.226 |
riet | +0.220 |
Downloadha | +0.218 |
reme | +0.218 |
Neg logit contributions | |
cast | -0.236 |
GOODMAN | -0.236 |
CAST | -0.231 |
fisher | -0.230 |
#$ | -0.226 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ificate | +1.700 |
ills | +1.616 |
riet | +1.562 |
reme | +1.555 |
iously | +1.550 |
Neg logit contributions | |
GOODMAN | -1.538 |
cast | -1.526 |
CAST | -1.514 |
fisher | -1.487 |
#$ | -1.482 |
Token | first |
Token ID | 717 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
ificate | +0.404 |
ills | +0.379 |
riet | +0.372 |
reme | +0.367 |
Downloadha | +0.367 |
Neg logit contributions | |
GOODMAN | -0.392 |
cast | -0.392 |
CAST | -0.385 |
fisher | -0.381 |
#$ | -0.377 |
Token | time |
Token ID | 640 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ificate | +2.907 |
ills | +2.800 |
riet | +2.725 |
iously | +2.698 |
reme | +2.694 |
Neg logit contributions | |
CAST | -2.552 |
cast | -2.549 |
GOODMAN | -2.548 |
#$ | -2.485 |
fisher | -2.484 |
Token | you |
Token ID | 345 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
ificate | +4.613 |
ills | +4.528 |
iously | +4.291 |
iss | +4.272 |
Downloadha | +4.234 |
Neg logit contributions | |
cast | -4.613 |
CAST | -4.610 |
GOODMAN | -4.606 |
fisher | -4.394 |
� | -4.386 |
Token | enter |
Token ID | 3802 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
GOODMAN | +0.643 |
cast | +0.639 |
CAST | +0.626 |
fisher | +0.618 |
#$ | +0.609 |
Neg logit contributions | |
ificate | -0.734 |
ills | -0.690 |
riet | -0.681 |
reme | -0.670 |
Downloadha | -0.669 |
Token | the |
Token ID | 262 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
ificate | +1.041 |
ills | +0.990 |
riet | +0.968 |
Downloadha | +0.960 |
iously | +0.956 |
Neg logit contributions | |
cast | -0.869 |
GOODMAN | -0.868 |
CAST | -0.858 |
fisher | -0.841 |
cks | -0.825 |
Token | 64 |
Token ID | 5598 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
ificate | +1.111 |
ills | +1.047 |
riet | +1.027 |
reme | +1.016 |
iously | +1.008 |
Neg logit contributions | |
GOODMAN | -0.974 |
cast | -0.971 |
CAST | -0.954 |
fisher | -0.935 |
#$ | -0.927 |
Token | - |
Token ID | 12 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
ificate | +1.087 |
ills | +1.026 |
riet | +1.002 |
Downloadha | +0.997 |
reme | +0.994 |
Neg logit contributions | |
GOODMAN | -1.037 |
cast | -1.033 |
CAST | -1.016 |
fisher | -1.007 |
#$ | -0.989 |
Token | in |
Token ID | 287 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ificate | +0.509 |
ills | +0.473 |
riet | +0.462 |
Downloadha | +0.461 |
iously | +0.460 |
Neg logit contributions | |
GOODMAN | -0.571 |
cast | -0.563 |
CAST | -0.559 |
fisher | -0.546 |
#$ | -0.543 |
Token | a |
Token ID | 257 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
GOODMAN | +0.952 |
cast | +0.946 |
CAST | +0.927 |
fisher | +0.915 |
#$ | +0.903 |
Neg logit contributions | |
ificate | -1.116 |
ills | -1.054 |
riet | -1.036 |
Downloadha | -1.029 |
reme | -1.021 |
Token | Reuters |
Token ID | 8428 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ificate | +0.578 |
ills | +0.543 |
riet | +0.533 |
Downloadha | +0.526 |
iously | +0.524 |
Neg logit contributions | |
GOODMAN | -0.578 |
cast | -0.573 |
CAST | -0.562 |
fisher | -0.551 |
#$ | -0.547 |
Token | / |
Token ID | 14 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
GOODMAN | +0.572 |
cast | +0.569 |
CAST | +0.557 |
fisher | +0.552 |
#$ | +0.542 |
Neg logit contributions | |
ificate | -0.684 |
ills | -0.645 |
riet | -0.634 |
Downloadha | -0.628 |
reme | -0.624 |
Token | I |
Token ID | 40 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
ificate | +0.607 |
ills | +0.557 |
riet | +0.546 |
Downloadha | +0.537 |
reme | +0.534 |
Neg logit contributions | |
GOODMAN | -0.975 |
cast | -0.974 |
CAST | -0.957 |
fisher | -0.952 |
#$ | -0.939 |
Token | ps |
Token ID | 862 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
GOODMAN | +1.028 |
cast | +1.022 |
CAST | +1.016 |
fisher | +1.006 |
Zimmer | +0.993 |
Neg logit contributions | |
ificate | -0.491 |
ills | -0.444 |
riet | -0.439 |
reme | -0.424 |
Downloadha | -0.420 |
Token | os |
Token ID | 418 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
ificate | +4.193 |
iss | +3.942 |
ills | +3.864 |
riet | +3.819 |
iously | +3.813 |
Neg logit contributions | |
GOODMAN | -5.268 |
CAST | -5.103 |
Zimmer | -5.027 |
#$ | -4.997 |
cast | -4.985 |
Token | poll |
Token ID | 3278 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
ificate | +2.489 |
ills | +2.365 |
riet | +2.290 |
Downloadha | +2.286 |
iss | +2.266 |
Neg logit contributions | |
GOODMAN | -2.584 |
cast | -2.540 |
CAST | -2.516 |
fisher | -2.478 |
cks | -2.441 |
Token | , |
Token ID | 11 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
ificate | +2.064 |
ills | +1.932 |
riet | +1.898 |
Downloadha | +1.865 |
reme | +1.859 |
Neg logit contributions | |
GOODMAN | -2.140 |
CAST | -2.078 |
cast | -2.077 |
fisher | -2.045 |
#$ | -2.027 |
Token | half |
Token ID | 2063 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
ificate | +0.812 |
ills | +0.765 |
riet | +0.750 |
Downloadha | +0.740 |
reme | +0.738 |
Neg logit contributions | |
GOODMAN | -0.836 |
cast | -0.826 |
CAST | -0.822 |
fisher | -0.797 |
#$ | -0.795 |
Token | believe |
Token ID | 1975 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
ificate | +0.306 |
ills | +0.286 |
riet | +0.284 |
reme | +0.277 |
Downloadha | +0.276 |
Neg logit contributions | |
GOODMAN | -0.311 |
cast | -0.308 |
CAST | -0.306 |
fisher | -0.298 |
#$ | -0.297 |
Token | Vend |
Token ID | 44220 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
GOODMAN | +0.673 |
cast | +0.672 |
CAST | +0.656 |
fisher | +0.651 |
#$ | +0.639 |
Neg logit contributions | |
ificate | -0.822 |
ills | -0.774 |
riet | -0.764 |
Downloadha | -0.756 |
reme | -0.753 |
Token | read |
Token ID | 961 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
cast | +0.738 |
GOODMAN | +0.732 |
CAST | +0.713 |
fisher | +0.709 |
#$ | +0.693 |
Neg logit contributions | |
ificate | -1.106 |
ills | -1.045 |
riet | -1.032 |
Downloadha | -1.028 |
reme | -1.019 |
Token | Deck |
Token ID | 20961 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
GOODMAN | +0.660 |
cast | +0.659 |
CAST | +0.644 |
fisher | +0.639 |
#$ | +0.628 |
Neg logit contributions | |
ificate | -0.720 |
ills | -0.676 |
riet | -0.667 |
Downloadha | -0.659 |
reme | -0.656 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
GOODMAN | +0.156 |
cast | +0.156 |
CAST | +0.153 |
fisher | +0.151 |
#$ | +0.149 |
Neg logit contributions | |
ificate | -0.161 |
ills | -0.150 |
riet | -0.148 |
reme | -0.146 |
Downloadha | -0.146 |
Token | but |
Token ID | 475 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
ificate | +0.388 |
ills | +0.362 |
riet | +0.354 |
reme | +0.350 |
Downloadha | +0.349 |
Neg logit contributions | |
GOODMAN | -0.430 |
cast | -0.429 |
CAST | -0.423 |
fisher | -0.416 |
#$ | -0.413 |
Token | just |
Token ID | 655 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ificate | +1.890 |
ills | +1.783 |
reme | +1.738 |
iously | +1.729 |
riet | +1.727 |
Neg logit contributions | |
GOODMAN | -1.672 |
cast | -1.667 |
CAST | -1.641 |
#$ | -1.627 |
fisher | -1.620 |
Token | about |
Token ID | 546 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
ificate | +4.761 |
ills | +4.376 |
reme | +4.345 |
iss | +4.256 |
iously | +4.183 |
Neg logit contributions | |
GOODMAN | -4.590 |
#$ | -4.472 |
cast | -4.398 |
fisher | -4.368 |
CAST | -4.349 |
Token | any |
Token ID | 597 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ificate | +1.254 |
ills | +1.190 |
riet | +1.158 |
reme | +1.153 |
Downloadha | +1.145 |
Neg logit contributions | |
GOODMAN | -1.053 |
cast | -1.037 |
CAST | -1.029 |
fisher | -1.014 |
#$ | -1.005 |
Token | strategy |
Token ID | 4811 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
cast | +1.253 |
GOODMAN | +1.249 |
CAST | +1.218 |
fisher | +1.213 |
#$ | +1.188 |
Neg logit contributions | |
ificate | -1.401 |
ills | -1.314 |
riet | -1.300 |
Downloadha | -1.285 |
reme | -1.276 |
Token | you |
Token ID | 345 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
ificate | +0.525 |
ills | +0.496 |
riet | +0.487 |
reme | +0.482 |
Downloadha | +0.481 |
Neg logit contributions | |
GOODMAN | -0.418 |
cast | -0.417 |
CAST | -0.410 |
fisher | -0.403 |
#$ | -0.397 |
Token | can |
Token ID | 460 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
GOODMAN | +0.058 |
cast | +0.057 |
CAST | +0.056 |
fisher | +0.056 |
#$ | +0.055 |
Neg logit contributions | |
ificate | -0.068 |
ills | -0.064 |
riet | -0.063 |
reme | -0.062 |
iously | -0.062 |
Token | car |
Token ID | 1097 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ificate | +0.917 |
ills | +0.848 |
riet | +0.838 |
reme | +0.830 |
iously | +0.830 |
Neg logit contributions | |
GOODMAN | -0.829 |
cast | -0.811 |
CAST | -0.801 |
#$ | -0.781 |
fisher | -0.778 |
Token | crash |
Token ID | 7014 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
GOODMAN | +0.466 |
cast | +0.465 |
CAST | +0.452 |
fisher | +0.448 |
#$ | +0.438 |
Neg logit contributions | |
ificate | -0.778 |
ills | -0.738 |
riet | -0.730 |
Downloadha | -0.722 |
reme | -0.720 |
Token | ) |
Token ID | 8 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
ificate | +0.136 |
ills | +0.127 |
riet | +0.124 |
iously | +0.123 |
Downloadha | +0.122 |
Neg logit contributions | |
GOODMAN | -0.148 |
cast | -0.145 |
CAST | -0.144 |
fisher | -0.142 |
#$ | -0.141 |
Token | got |
Token ID | 1392 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
ificate | +0.808 |
ills | +0.760 |
riet | +0.739 |
iously | +0.732 |
reme | +0.729 |
Neg logit contributions | |
GOODMAN | -1.009 |
CAST | -0.988 |
cast | -0.985 |
#$ | -0.962 |
fisher | -0.958 |
Token | his |
Token ID | 465 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
ificate | +0.304 |
ills | +0.286 |
riet | +0.280 |
reme | +0.279 |
iously | +0.278 |
Neg logit contributions | |
GOODMAN | -0.246 |
cast | -0.243 |
CAST | -0.242 |
#$ | -0.234 |
fisher | -0.233 |
Token | start |
Token ID | 923 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ificate | +1.463 |
ills | +1.377 |
reme | +1.349 |
riet | +1.348 |
iously | +1.335 |
Neg logit contributions | |
cast | -1.046 |
CAST | -1.031 |
GOODMAN | -1.031 |
#$ | -1.001 |
� | -0.991 |
Token | catching |
Token ID | 16508 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
ificate | +3.919 |
ills | +3.708 |
iss | +3.523 |
iously | +3.512 |
reme | +3.495 |
Neg logit contributions | |
GOODMAN | -5.327 |
CAST | -5.163 |
cast | -5.157 |
#$ | -5.093 |
�醒 | -5.067 |
Token | tad |
Token ID | 36264 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
ificate | +0.139 |
ills | +0.130 |
riet | +0.127 |
reme | +0.127 |
iously | +0.127 |
Neg logit contributions | |
GOODMAN | -0.122 |
cast | -0.120 |
CAST | -0.119 |
#$ | -0.115 |
� | -0.115 |
Token | p |
Token ID | 79 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
ificate | +0.457 |
ills | +0.427 |
riet | +0.414 |
reme | +0.409 |
iously | +0.408 |
Neg logit contributions | |
GOODMAN | -0.608 |
cast | -0.603 |
CAST | -0.596 |
fisher | -0.585 |
Zimmer | -0.584 |
Token | oles |
Token ID | 4316 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
ificate | +0.619 |
ills | +0.585 |
reme | +0.536 |
iss | +0.535 |
riet | +0.532 |
Neg logit contributions | |
GOODMAN | -1.410 |
cast | -1.385 |
CAST | -1.385 |
fisher | -1.360 |
Zimmer | -1.356 |
Token | and |
Token ID | 290 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
ificate | +1.163 |
ills | +1.104 |
iously | +1.064 |
riet | +1.062 |
iss | +1.060 |
Neg logit contributions | |
GOODMAN | -1.348 |
CAST | -1.314 |
cast | -1.312 |
� | -1.281 |
#$ | -1.271 |
Token | Diane |
Token ID | 26542 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
ificate | +3.311 |
ills | +3.079 |
riet | +3.021 |
iss | +3.006 |
reme | +2.993 |
Neg logit contributions | |
GOODMAN | -1.880 |
#$ | -1.816 |
CAST | -1.813 |
cast | -1.812 |
fisher | -1.798 |
Token | Rodham |
Token ID | 41848 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
cast | +0.767 |
GOODMAN | +0.757 |
fisher | +0.737 |
CAST | +0.733 |
Zimmer | +0.722 |
Neg logit contributions | |
ificate | -1.214 |
ills | -1.146 |
riet | -1.139 |
Downloadha | -1.132 |
reme | -1.120 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
ificate | +0.940 |
ills | +0.866 |
riet | +0.847 |
Downloadha | +0.835 |
reme | +0.834 |
Neg logit contributions | |
GOODMAN | -1.332 |
cast | -1.329 |
CAST | -1.307 |
fisher | -1.299 |
#$ | -1.283 |
Token | Sanders |
Token ID | 26747 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
ificate | +2.188 |
ills | +2.032 |
reme | +1.992 |
riet | +1.971 |
iss | +1.966 |
Neg logit contributions | |
GOODMAN | -2.315 |
cast | -2.211 |
fisher | -2.202 |
CAST | -2.194 |
#$ | -2.174 |
Token | : |
Token ID | 25 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
ificate | +1.186 |
ills | +1.099 |
riet | +1.065 |
reme | +1.057 |
Downloadha | +1.050 |
Neg logit contributions | |
GOODMAN | -1.589 |
cast | -1.576 |
CAST | -1.567 |
fisher | -1.542 |
cks | -1.531 |
Token | ' |
Token ID | 705 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ificate | +2.741 |
ills | +2.572 |
riet | +2.473 |
reme | +2.446 |
iously | +2.418 |
Neg logit contributions | |
CAST | -3.211 |
GOODMAN | -3.182 |
cast | -3.152 |
fisher | -3.099 |
cks | -3.065 |
Token | I |
Token ID | 40 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
ificate | +3.707 |
ills | +3.592 |
reme | +3.328 |
riet | +3.299 |
iss | +3.294 |
Neg logit contributions | |
GOODMAN | -5.710 |
fisher | -5.588 |
cast | -5.444 |
CAST | -5.399 |
#$ | -5.399 |
Token | fully |
Token ID | 3938 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
ificate | +1.509 |
ills | +1.416 |
riet | +1.394 |
reme | +1.380 |
Downloadha | +1.374 |
Neg logit contributions | |
GOODMAN | -1.308 |
cast | -1.304 |
CAST | -1.280 |
fisher | -1.264 |
#$ | -1.242 |
Token | expect |
Token ID | 1607 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
ificate | +1.197 |
ills | +1.122 |
iss | +1.107 |
reme | +1.102 |
riet | +1.074 |
Neg logit contributions | |
CAST | -1.269 |
GOODMAN | -1.256 |
cast | -1.243 |
fisher | -1.210 |
#$ | -1.194 |
Token | ' |
Token ID | 6 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
ificate | +3.713 |
ills | +3.514 |
riet | +3.463 |
reme | +3.432 |
Downloadha | +3.420 |
Neg logit contributions | |
cast | -2.433 |
GOODMAN | -2.412 |
CAST | -2.365 |
fisher | -2.337 |
#$ | -2.316 |
Token | fair |
Token ID | 3148 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
ificate | +1.486 |
ills | +1.388 |
iously | +1.377 |
riet | +1.374 |
reme | +1.368 |
Neg logit contributions | |
GOODMAN | -1.064 |
cast | -1.059 |
CAST | -1.042 |
#$ | -1.039 |
fisher | -1.031 |
Token | hand |
Token ID | 1021 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ificate | +0.702 |
ills | +0.654 |
riet | +0.643 |
reme | +0.635 |
iously | +0.634 |
Neg logit contributions | |
GOODMAN | -0.706 |
cast | -0.697 |
CAST | -0.687 |
#$ | -0.676 |
fisher | -0.675 |
Token | . |
Token ID | 13 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
ificate | +0.651 |
ills | +0.608 |
riet | +0.599 |
reme | +0.590 |
Downloadha | +0.588 |
Neg logit contributions | |
GOODMAN | -0.693 |
cast | -0.687 |
CAST | -0.676 |
fisher | -0.669 |
#$ | -0.661 |
Token |
|
Token ID | 198 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
GOODMAN | +0.210 |
cast | +0.210 |
CAST | +0.204 |
fisher | +0.202 |
Zimmer | +0.200 |
Neg logit contributions | |
ificate | -0.240 |
ills | -0.225 |
riet | -0.223 |
Downloadha | -0.221 |
reme | -0.219 |
Token |
|
Token ID | 198 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
cast | +0.982 |
GOODMAN | +0.978 |
CAST | +0.958 |
fisher | +0.949 |
#$ | +0.934 |
Neg logit contributions | |
ificate | -1.083 |
ills | -1.017 |
riet | -1.005 |
Downloadha | -0.998 |
reme | -0.989 |
Token | Det |
Token ID | 11242 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
cast | +0.847 |
GOODMAN | +0.843 |
CAST | +0.832 |
fisher | +0.820 |
#$ | +0.811 |
Neg logit contributions | |
ificate | -0.756 |
ills | -0.703 |
riet | -0.693 |
Downloadha | -0.686 |
reme | -0.681 |
Token | Sgt |
Token ID | 22925 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ificate | +1.373 |
ills | +1.269 |
riet | +1.247 |
Downloadha | +1.227 |
reme | +1.225 |
Neg logit contributions | |
GOODMAN | -1.885 |
cast | -1.882 |
CAST | -1.847 |
fisher | -1.836 |
#$ | -1.812 |
Token | Ronnie |
Token ID | 40892 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ificate | +4.247 |
ills | +4.062 |
riet | +3.926 |
reme | +3.914 |
iss | +3.882 |
Neg logit contributions | |
GOODMAN | -4.811 |
cast | -4.732 |
CAST | -4.702 |
#$ | -4.642 |
fisher | -4.565 |
Token | Payne |
Token ID | 32788 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
ificate | +0.942 |
ills | +0.887 |
riet | +0.871 |
reme | +0.856 |
iss | +0.854 |
Neg logit contributions | |
GOODMAN | -0.832 |
cast | -0.828 |
CAST | -0.815 |
fisher | -0.803 |
#$ | -0.794 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ificate | +0.166 |
ills | +0.155 |
riet | +0.153 |
Downloadha | +0.151 |
reme | +0.150 |
Neg logit contributions | |
GOODMAN | -0.163 |
cast | -0.163 |
CAST | -0.159 |
fisher | -0.158 |
#$ | -0.155 |
Token | anyone |
Token ID | 2687 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
GOODMAN | +0.553 |
cast | +0.552 |
CAST | +0.539 |
fisher | +0.535 |
#$ | +0.528 |
Neg logit contributions | |
ificate | -0.615 |
ills | -0.579 |
riet | -0.571 |
Downloadha | -0.562 |
reme | -0.562 |
Token | with |
Token ID | 351 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
cast | +2.352 |
GOODMAN | +2.335 |
CAST | +2.297 |
fisher | +2.296 |
Zimmer | +2.253 |
Neg logit contributions | |
ificate | -1.762 |
ills | -1.621 |
riet | -1.601 |
Downloadha | -1.596 |
reme | -1.574 |
Token | We |
Token ID | 1135 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
GOODMAN | +0.201 |
cast | +0.201 |
CAST | +0.197 |
fisher | +0.196 |
#$ | +0.193 |
Neg logit contributions | |
ificate | -0.164 |
ills | -0.152 |
riet | -0.150 |
Downloadha | -0.148 |
reme | -0.147 |
Token | � |
Token ID | 447 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
cast | +0.603 |
GOODMAN | +0.602 |
CAST | +0.590 |
fisher | +0.583 |
#$ | +0.581 |
Neg logit contributions | |
ificate | -0.529 |
ills | -0.490 |
riet | -0.483 |
Downloadha | -0.478 |
iously | -0.474 |
Token | � |
Token ID | 247 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
ificate | +0.799 |
ills | +0.753 |
riet | +0.740 |
reme | +0.728 |
iously | +0.724 |
Neg logit contributions | |
GOODMAN | -0.684 |
cast | -0.679 |
CAST | -0.665 |
fisher | -0.663 |
Zimmer | -0.645 |
Token | ve |
Token ID | 303 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
GOODMAN | +0.217 |
cast | +0.214 |
CAST | +0.212 |
fisher | +0.211 |
Zimmer | +0.208 |
Neg logit contributions | |
ificate | -0.152 |
ills | -0.140 |
riet | -0.138 |
Downloadha | -0.136 |
reme | -0.135 |
Token | Had |
Token ID | 25383 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
GOODMAN | +0.105 |
cast | +0.104 |
fisher | +0.103 |
CAST | +0.102 |
Zimmer | +0.101 |
Neg logit contributions | |
ificate | -0.041 |
ills | -0.036 |
riet | -0.035 |
Downloadha | -0.034 |
reme | -0.034 |
Token | Enough |
Token ID | 47323 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
cast | +1.170 |
GOODMAN | +1.168 |
CAST | +1.143 |
fisher | +1.126 |
#$ | +1.112 |
Neg logit contributions | |
ificate | -1.592 |
ills | -1.500 |
riet | -1.485 |
Downloadha | -1.468 |
reme | -1.467 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
cast | +2.964 |
GOODMAN | +2.945 |
CAST | +2.864 |
fisher | +2.841 |
Zimmer | +2.799 |
Neg logit contributions | |
ificate | -3.711 |
ills | -3.477 |
riet | -3.436 |
Downloadha | -3.426 |
reme | -3.391 |
Token | In |
Token ID | 554 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
GOODMAN | +0.045 |
cast | +0.045 |
CAST | +0.044 |
fisher | +0.044 |
#$ | +0.043 |
Neg logit contributions | |
ificate | -0.046 |
ills | -0.043 |
riet | -0.042 |
Downloadha | -0.041 |
iously | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
GOODMAN | +0.624 |
cast | +0.621 |
CAST | +0.609 |
fisher | +0.600 |
#$ | +0.595 |
Neg logit contributions | |
ificate | -0.673 |
ills | -0.633 |
riet | -0.621 |
Downloadha | -0.613 |
iously | -0.613 |
Token | Kal |
Token ID | 12612 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
ificate | +0.084 |
ills | +0.079 |
riet | +0.078 |
reme | +0.077 |
iously | +0.077 |
Neg logit contributions | |
GOODMAN | -0.078 |
cast | -0.077 |
CAST | -0.075 |
#$ | -0.074 |
fisher | -0.074 |
Token | uga |
Token ID | 30302 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
ificate | +2.221 |
ills | +2.071 |
iss | +2.011 |
riet | +2.007 |
reme | +1.987 |
Neg logit contributions | |
GOODMAN | -2.471 |
cast | -2.394 |
CAST | -2.391 |
#$ | -2.353 |
fisher | -2.353 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ificate | +0.360 |
ills | +0.340 |
riet | +0.334 |
reme | +0.329 |
iously | +0.329 |
Neg logit contributions | |
GOODMAN | -0.300 |
cast | -0.296 |
CAST | -0.292 |
fisher | -0.284 |
#$ | -0.284 |
Token | Mau |
Token ID | 28931 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
ificate | +0.324 |
ills | +0.304 |
riet | +0.299 |
reme | +0.295 |
iously | +0.294 |
Neg logit contributions | |
GOODMAN | -0.304 |
cast | -0.302 |
CAST | -0.296 |
fisher | -0.290 |
#$ | -0.290 |
Token | Mau |
Token ID | 28931 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ificate | +0.752 |
ills | +0.714 |
riet | +0.698 |
Downloadha | +0.686 |
reme | +0.684 |
Neg logit contributions | |
GOODMAN | -0.737 |
cast | -0.729 |
CAST | -0.723 |
fisher | -0.703 |
#$ | -0.697 |
Token | . |
Token ID | 13 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ificate | +0.401 |
ills | +0.378 |
riet | +0.369 |
reme | +0.364 |
iss | +0.362 |
Neg logit contributions | |
GOODMAN | -0.390 |
cast | -0.387 |
CAST | -0.383 |
fisher | -0.373 |
#$ | -0.372 |
Token | K |
Token ID | 509 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ificate | +0.780 |
ills | +0.730 |
reme | +0.706 |
riet | +0.705 |
iss | +0.700 |
Neg logit contributions | |
GOODMAN | -0.771 |
cast | -0.766 |
CAST | -0.755 |
fisher | -0.747 |
#$ | -0.742 |
Token | AN |
Token ID | 1565 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
GOODMAN | +0.489 |
cast | +0.488 |
CAST | +0.474 |
fisher | +0.469 |
#$ | +0.458 |
Neg logit contributions | |
ificate | -0.840 |
ills | -0.798 |
riet | -0.789 |
Downloadha | -0.781 |
reme | -0.779 |
Token | U |
Token ID | 52 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
cast | +1.919 |
GOODMAN | +1.897 |
CAST | +1.855 |
fisher | +1.801 |
#$ | +1.779 |
Neg logit contributions | |
ificate | -4.413 |
ills | -4.218 |
Downloadha | -4.181 |
riet | -4.175 |
reme | -4.122 |
Token | then |
Token ID | 788 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
cast | +1.561 |
GOODMAN | +1.561 |
CAST | +1.526 |
fisher | +1.523 |
Zimmer | +1.491 |
Neg logit contributions | |
ificate | -1.452 |
ills | -1.352 |
riet | -1.337 |
Downloadha | -1.326 |
reme | -1.306 |
Token | declared |
Token ID | 6875 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
GOODMAN | +0.423 |
cast | +0.422 |
CAST | +0.414 |
fisher | +0.411 |
#$ | +0.405 |
Neg logit contributions | |
ificate | -0.363 |
ills | -0.338 |
riet | -0.333 |
Downloadha | -0.328 |
reme | -0.327 |
Token | that |
Token ID | 326 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ificate | +0.538 |
ills | +0.505 |
riet | +0.494 |
reme | +0.489 |
iously | +0.488 |
Neg logit contributions | |
GOODMAN | -0.541 |
cast | -0.534 |
CAST | -0.530 |
#$ | -0.520 |
fisher | -0.516 |
Token | it |
Token ID | 340 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
ificate | +0.475 |
ills | +0.449 |
riet | +0.439 |
reme | +0.435 |
iss | +0.433 |
Neg logit contributions | |
GOODMAN | -0.417 |
cast | -0.415 |
CAST | -0.411 |
#$ | -0.402 |
fisher | -0.399 |
Token | delta |
Token ID | 25979 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
GOODMAN | +0.344 |
cast | +0.341 |
CAST | +0.335 |
#$ | +0.327 |
fisher | +0.326 |
Neg logit contributions | |
ificate | -0.415 |
ills | -0.391 |
riet | -0.386 |
reme | -0.380 |
iously | -0.379 |
Token | is |
Token ID | 318 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
GOODMAN | +0.907 |
cast | +0.898 |
CAST | +0.886 |
#$ | +0.866 |
fisher | +0.863 |
Neg logit contributions | |
ificate | -0.894 |
ills | -0.840 |
riet | -0.824 |
iously | -0.811 |
reme | -0.809 |
Token | a |
Token ID | 257 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
ificate | +0.228 |
ills | +0.215 |
riet | +0.212 |
iously | +0.209 |
Downloadha | +0.208 |
Neg logit contributions | |
GOODMAN | -0.197 |
cast | -0.193 |
CAST | -0.192 |
#$ | -0.187 |
cks | -0.186 |
Token | UNESCO |
Token ID | 49372 |
Feature activation | -7.05e-02 |
Pos logit contributions | |
GOODMAN | +0.071 |
cast | +0.070 |
CAST | +0.069 |
#$ | +0.067 |
cks | +0.067 |
Neg logit contributions | |
ificate | -0.068 |
ills | -0.063 |
riet | -0.063 |
reme | -0.062 |
iously | -0.062 |
Token | World |
Token ID | 2159 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
ificate | +0.244 |
ills | +0.231 |
riet | +0.227 |
reme | +0.224 |
Downloadha | +0.222 |
Neg logit contributions | |
GOODMAN | -0.193 |
cast | -0.193 |
CAST | -0.189 |
fisher | -0.186 |
#$ | -0.184 |
Token | Heritage |
Token ID | 18518 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ificate | +0.199 |
ills | +0.186 |
riet | +0.182 |
reme | +0.180 |
iously | +0.178 |
Neg logit contributions | |
GOODMAN | -0.206 |
cast | -0.204 |
CAST | -0.202 |
fisher | -0.197 |
#$ | -0.197 |
Token | site |
Token ID | 2524 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
cast | +3.801 |
GOODMAN | +3.745 |
fisher | +3.706 |
CAST | +3.644 |
#$ | +3.597 |
Neg logit contributions | |
ificate | -3.885 |
ills | -3.691 |
Downloadha | -3.681 |
riet | -3.647 |
reme | -3.567 |
Token | that |
Token ID | 326 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
GOODMAN | +0.518 |
cast | +0.514 |
CAST | +0.508 |
fisher | +0.499 |
#$ | +0.494 |
Neg logit contributions | |
ificate | -0.511 |
ills | -0.478 |
riet | -0.471 |
reme | -0.463 |
Downloadha | -0.462 |
Token | encompasses |
Token ID | 38932 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
GOODMAN | +1.050 |
cast | +1.047 |
CAST | +1.032 |
fisher | +1.009 |
#$ | +1.002 |
Neg logit contributions | |
ificate | -1.024 |
ills | -0.960 |
riet | -0.944 |
Downloadha | -0.928 |
reme | -0.927 |
Token | some |
Token ID | 617 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
GOODMAN | +0.845 |
cast | +0.836 |
CAST | +0.823 |
fisher | +0.806 |
#$ | +0.803 |
Neg logit contributions | |
ificate | -0.950 |
ills | -0.895 |
riet | -0.880 |
reme | -0.868 |
Downloadha | -0.865 |
Token | 3 |
Token ID | 513 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
GOODMAN | +0.988 |
cast | +0.981 |
CAST | +0.965 |
fisher | +0.952 |
#$ | +0.940 |
Neg logit contributions | |
ificate | -0.976 |
ills | -0.913 |
riet | -0.899 |
Downloadha | -0.887 |
reme | -0.884 |
Token | terrorist |
Token ID | 7417 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
ificate | +0.154 |
ills | +0.144 |
riet | +0.141 |
reme | +0.139 |
iously | +0.139 |
Neg logit contributions | |
GOODMAN | -0.166 |
cast | -0.165 |
CAST | -0.163 |
fisher | -0.160 |
#$ | -0.158 |
Token | attacks |
Token ID | 3434 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
cast | +1.567 |
GOODMAN | +1.553 |
fisher | +1.517 |
CAST | +1.514 |
Zimmer | +1.492 |
Neg logit contributions | |
ificate | -2.020 |
ills | -1.906 |
riet | -1.895 |
Downloadha | -1.888 |
reme | -1.863 |
Token | of |
Token ID | 286 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
GOODMAN | +1.615 |
cast | +1.611 |
CAST | +1.579 |
fisher | +1.567 |
#$ | +1.540 |
Neg logit contributions | |
ificate | -1.527 |
ills | -1.427 |
riet | -1.403 |
Downloadha | -1.386 |
reme | -1.380 |
Token | Sept |
Token ID | 2362 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
GOODMAN | +0.039 |
cast | +0.039 |
CAST | +0.038 |
fisher | +0.038 |
#$ | +0.037 |
Neg logit contributions | |
ificate | -0.032 |
ills | -0.030 |
riet | -0.029 |
reme | -0.029 |
iss | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
ificate | +0.659 |
ills | +0.616 |
riet | +0.596 |
reme | +0.591 |
iss | +0.591 |
Neg logit contributions | |
GOODMAN | -0.748 |
cast | -0.735 |
CAST | -0.730 |
fisher | -0.727 |
#$ | -0.710 |
Token | 11 |
Token ID | 1367 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
cast | +0.676 |
GOODMAN | +0.675 |
CAST | +0.661 |
fisher | +0.657 |
#$ | +0.646 |
Neg logit contributions | |
ificate | -0.611 |
ills | -0.569 |
riet | -0.561 |
Downloadha | -0.554 |
reme | -0.551 |
Token | , |
Token ID | 11 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
cast | +2.847 |
GOODMAN | +2.827 |
CAST | +2.766 |
fisher | +2.746 |
Zimmer | +2.719 |
Neg logit contributions | |
ificate | -3.466 |
riet | -3.289 |
ills | -3.226 |
Downloadha | -3.209 |
iously | -3.157 |
Token | 2001 |
Token ID | 5878 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
ificate | +0.173 |
ills | +0.162 |
riet | +0.158 |
reme | +0.157 |
Downloadha | +0.157 |
Neg logit contributions | |
GOODMAN | -0.176 |
cast | -0.175 |
CAST | -0.172 |
fisher | -0.170 |
#$ | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
cast | +0.732 |
GOODMAN | +0.729 |
CAST | +0.711 |
fisher | +0.708 |
#$ | +0.696 |
Neg logit contributions | |
ificate | -0.803 |
riet | -0.750 |
ills | -0.750 |
Downloadha | -0.739 |
reme | -0.730 |
Token |
|
Token ID | 198 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
GOODMAN | +0.585 |
cast | +0.585 |
CAST | +0.574 |
fisher | +0.568 |
#$ | +0.559 |
Neg logit contributions | |
ificate | -0.638 |
ills | -0.599 |
riet | -0.585 |
Downloadha | -0.579 |
reme | -0.579 |
Token |
|
Token ID | 198 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
GOODMAN | +0.661 |
cast | +0.658 |
CAST | +0.644 |
fisher | +0.640 |
#$ | +0.629 |
Neg logit contributions | |
ificate | -0.704 |
ills | -0.660 |
riet | -0.651 |
Downloadha | -0.642 |
reme | -0.641 |
Token | ( |
Token ID | 357 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
GOODMAN | +0.040 |
cast | +0.040 |
CAST | +0.039 |
fisher | +0.039 |
#$ | +0.038 |
Neg logit contributions | |
ificate | -0.050 |
ills | -0.048 |
riet | -0.046 |
reme | -0.046 |
iously | -0.046 |
Token | read |
Token ID | 961 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
GOODMAN | +0.386 |
cast | +0.386 |
CAST | +0.378 |
fisher | +0.376 |
#$ | +0.370 |
Neg logit contributions | |
ificate | -0.346 |
ills | -0.322 |
riet | -0.317 |
Downloadha | -0.313 |
reme | -0.312 |
Token | the |
Token ID | 262 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
GOODMAN | +1.318 |
cast | +1.316 |
CAST | +1.285 |
fisher | +1.276 |
#$ | +1.253 |
Neg logit contributions | |
ificate | -1.580 |
ills | -1.487 |
riet | -1.467 |
Downloadha | -1.451 |
reme | -1.445 |
Token | full |
Token ID | 1336 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
cast | +0.681 |
GOODMAN | +0.681 |
CAST | +0.667 |
fisher | +0.659 |
#$ | +0.651 |
Neg logit contributions | |
ificate | -0.779 |
ills | -0.735 |
riet | -0.722 |
Downloadha | -0.713 |
reme | -0.712 |
Token | profile |
Token ID | 7034 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
GOODMAN | +0.318 |
cast | +0.316 |
CAST | +0.310 |
fisher | +0.307 |
#$ | +0.302 |
Neg logit contributions | |
ificate | -0.428 |
ills | -0.406 |
riet | -0.399 |
reme | -0.394 |
Downloadha | -0.393 |
Token | here |
Token ID | 994 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
GOODMAN | +0.058 |
cast | +0.058 |
CAST | +0.057 |
fisher | +0.057 |
#$ | +0.056 |
Neg logit contributions | |
ificate | -0.065 |
ills | -0.061 |
riet | -0.060 |
Downloadha | -0.059 |
reme | -0.059 |
Token | ). |
Token ID | 737 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
cast | +2.926 |
GOODMAN | +2.918 |
CAST | +2.829 |
fisher | +2.809 |
#$ | +2.752 |
Neg logit contributions | |
ificate | -3.078 |
ills | -2.889 |
riet | -2.888 |
Downloadha | -2.842 |
reme | -2.804 |
Token | Talking |
Token ID | 33445 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
GOODMAN | +0.395 |
cast | +0.395 |
CAST | +0.387 |
fisher | +0.386 |
#$ | +0.379 |
Neg logit contributions | |
ificate | -0.397 |
ills | -0.373 |
riet | -0.364 |
reme | -0.360 |
Downloadha | -0.358 |
Token | Points |
Token ID | 11045 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ificate | +0.099 |
ills | +0.093 |
riet | +0.091 |
reme | +0.090 |
Downloadha | +0.090 |
Neg logit contributions | |
GOODMAN | -0.098 |
cast | -0.097 |
CAST | -0.096 |
fisher | -0.095 |
#$ | -0.094 |
Token | Mem |
Token ID | 4942 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
cast | +0.846 |
GOODMAN | +0.845 |
CAST | +0.837 |
fisher | +0.832 |
cks | +0.821 |
Neg logit contributions | |
ificate | -0.269 |
ills | -0.234 |
riet | -0.226 |
reme | -0.219 |
iously | -0.218 |
Token | o |
Token ID | 78 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
ificate | +0.436 |
ills | +0.408 |
riet | +0.403 |
reme | +0.400 |
Downloadha | +0.399 |
Neg logit contributions | |
GOODMAN | -0.364 |
cast | -0.363 |
CAST | -0.355 |
fisher | -0.353 |
#$ | -0.347 |
Token | � |
Token ID | 447 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
GOODMAN | +0.931 |
cast | +0.923 |
fisher | +0.900 |
CAST | +0.900 |
Zimmer | +0.879 |
Neg logit contributions | |
ificate | -1.054 |
ills | -0.992 |
riet | -0.977 |
Downloadha | -0.963 |
reme | -0.961 |
Token | � |
Token ID | 250 |
Feature activation | +4.48e-03 |
Pos logit contributions | |
GOODMAN | +0.085 |
cast | +0.085 |
CAST | +0.083 |
fisher | +0.082 |
#$ | +0.080 |
Neg logit contributions | |
ificate | -0.117 |
ills | -0.110 |
riet | -0.109 |
Downloadha | -0.108 |
reme | -0.107 |
Token | What |
Token ID | 2061 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
GOODMAN | +0.014 |
cast | +0.014 |
CAST | +0.014 |
fisher | +0.013 |
#$ | +0.013 |
Neg logit contributions | |
ificate | -0.014 |
ills | -0.013 |
riet | -0.013 |
reme | -0.013 |
Downloadha | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
GOODMAN | +1.229 |
cast | +1.228 |
CAST | +1.203 |
fisher | +1.188 |
#$ | +1.168 |
Neg logit contributions | |
ificate | -1.341 |
ills | -1.261 |
riet | -1.239 |
Downloadha | -1.224 |
reme | -1.219 |
Token | study |
Token ID | 2050 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
cast | +0.251 |
GOODMAN | +0.250 |
CAST | +0.245 |
fisher | +0.241 |
#$ | +0.239 |
Neg logit contributions | |
ificate | -0.310 |
ills | -0.294 |
riet | -0.287 |
reme | -0.283 |
iously | -0.282 |
Token | demonstrates |
Token ID | 15687 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
GOODMAN | +0.984 |
cast | +0.979 |
CAST | +0.959 |
fisher | +0.953 |
#$ | +0.935 |
Neg logit contributions | |
ificate | -1.007 |
ills | -0.941 |
riet | -0.927 |
Downloadha | -0.915 |
reme | -0.910 |
Token | is |
Token ID | 318 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
GOODMAN | +0.689 |
cast | +0.688 |
CAST | +0.674 |
fisher | +0.669 |
#$ | +0.656 |
Neg logit contributions | |
ificate | -0.734 |
ills | -0.689 |
riet | -0.678 |
Downloadha | -0.671 |
reme | -0.668 |
Token | that |
Token ID | 326 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
GOODMAN | +0.091 |
cast | +0.091 |
CAST | +0.089 |
fisher | +0.088 |
#$ | +0.086 |
Neg logit contributions | |
ificate | -0.139 |
ills | -0.132 |
riet | -0.130 |
Downloadha | -0.128 |
reme | -0.127 |
Token | there |
Token ID | 612 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
ificate | +0.831 |
ills | +0.789 |
riet | +0.771 |
Downloadha | +0.756 |
reme | +0.754 |
Neg logit contributions | |
GOODMAN | -0.741 |
cast | -0.737 |
CAST | -0.725 |
fisher | -0.706 |
#$ | -0.701 |
Token | is |
Token ID | 318 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
cast | +0.121 |
GOODMAN | +0.121 |
CAST | +0.119 |
fisher | +0.117 |
#$ | +0.116 |
Neg logit contributions | |
ificate | -0.122 |
ills | -0.114 |
riet | -0.112 |
Downloadha | -0.110 |
reme | -0.110 |
Token | incredibly |
Token ID | 8131 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
ificate | +0.075 |
ills | +0.070 |
riet | +0.069 |
Downloadha | +0.068 |
iously | +0.068 |
Neg logit contributions | |
GOODMAN | -0.069 |
cast | -0.069 |
CAST | -0.067 |
fisher | -0.066 |
#$ | -0.066 |
Token | suffered |
Token ID | 6989 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
ificate | +0.300 |
ills | +0.279 |
riet | +0.273 |
iously | +0.269 |
reme | +0.268 |
Neg logit contributions | |
GOODMAN | -0.394 |
cast | -0.391 |
CAST | -0.387 |
fisher | -0.380 |
#$ | -0.377 |
Token | a |
Token ID | 257 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
ificate | +1.087 |
ills | +1.020 |
riet | +1.008 |
iously | +0.986 |
reme | +0.980 |
Neg logit contributions | |
GOODMAN | -1.266 |
cast | -1.250 |
CAST | -1.236 |
fisher | -1.213 |
#$ | -1.206 |
Token | head |
Token ID | 1182 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ificate | +0.589 |
ills | +0.548 |
riet | +0.543 |
reme | +0.531 |
iously | +0.530 |
Neg logit contributions | |
GOODMAN | -0.679 |
cast | -0.667 |
CAST | -0.659 |
fisher | -0.645 |
#$ | -0.643 |
Token | injury |
Token ID | 5095 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
ificate | +0.622 |
ills | +0.582 |
riet | +0.574 |
reme | +0.568 |
Downloadha | +0.563 |
Neg logit contributions | |
GOODMAN | -0.540 |
cast | -0.530 |
CAST | -0.526 |
fisher | -0.519 |
#$ | -0.517 |
Token | and |
Token ID | 290 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
ificate | +1.320 |
ills | +1.242 |
riet | +1.219 |
iously | +1.206 |
iss | +1.197 |
Neg logit contributions | |
GOODMAN | -1.450 |
cast | -1.421 |
CAST | -1.420 |
fisher | -1.387 |
� | -1.377 |
Token | was |
Token ID | 373 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
GOODMAN | +0.070 |
cast | +0.070 |
CAST | +0.069 |
fisher | +0.068 |
#$ | +0.067 |
Neg logit contributions | |
ificate | -0.056 |
ills | -0.052 |
riet | -0.051 |
reme | -0.050 |
Downloadha | -0.050 |
Token | taken |
Token ID | 2077 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
cast | +1.863 |
GOODMAN | +1.850 |
CAST | +1.803 |
fisher | +1.796 |
Zimmer | +1.761 |
Neg logit contributions | |
ificate | -2.200 |
ills | -2.063 |
riet | -2.043 |
Downloadha | -2.035 |
reme | -2.013 |
Token | to |
Token ID | 284 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
cast | +0.680 |
GOODMAN | +0.680 |
CAST | +0.665 |
fisher | +0.662 |
#$ | +0.651 |
Neg logit contributions | |
ificate | -0.595 |
ills | -0.553 |
riet | -0.545 |
Downloadha | -0.538 |
reme | -0.536 |
Token | a |
Token ID | 257 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
ificate | +0.073 |
ills | +0.069 |
riet | +0.068 |
Downloadha | +0.067 |
reme | +0.067 |
Neg logit contributions | |
GOODMAN | -0.063 |
cast | -0.063 |
CAST | -0.061 |
fisher | -0.061 |
#$ | -0.060 |
Token | nearby |
Token ID | 6716 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ificate | +1.272 |
ills | +1.203 |
riet | +1.184 |
reme | +1.163 |
Downloadha | +1.160 |
Neg logit contributions | |
GOODMAN | -1.182 |
cast | -1.171 |
CAST | -1.147 |
fisher | -1.134 |
#$ | -1.120 |
Token | hospital |
Token ID | 4436 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
GOODMAN | +0.521 |
cast | +0.520 |
CAST | +0.509 |
fisher | +0.505 |
#$ | +0.497 |
Neg logit contributions | |
ificate | -0.505 |
ills | -0.473 |
riet | -0.466 |
Downloadha | -0.460 |
reme | -0.458 |
Token | an |
Token ID | 281 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
cast | +1.186 |
GOODMAN | +1.183 |
CAST | +1.156 |
fisher | +1.153 |
Zimmer | +1.131 |
Neg logit contributions | |
ificate | -1.271 |
ills | -1.192 |
riet | -1.177 |
Downloadha | -1.167 |
reme | -1.160 |
Token | enc |
Token ID | 2207 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
GOODMAN | +0.852 |
cast | +0.844 |
CAST | +0.828 |
fisher | +0.815 |
#$ | +0.805 |
Neg logit contributions | |
ificate | -1.088 |
ills | -1.025 |
riet | -1.007 |
Downloadha | -0.996 |
reme | -0.995 |
Token | irc |
Token ID | 1980 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
GOODMAN | +0.756 |
cast | +0.754 |
CAST | +0.745 |
fisher | +0.741 |
#$ | +0.733 |
Neg logit contributions | |
ificate | -0.221 |
ills | -0.189 |
riet | -0.182 |
Downloadha | -0.177 |
reme | -0.176 |
Token | lement |
Token ID | 1732 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
cast | +1.154 |
GOODMAN | +1.145 |
CAST | +1.121 |
fisher | +1.114 |
#$ | +1.096 |
Neg logit contributions | |
ificate | -1.330 |
ills | -1.252 |
riet | -1.237 |
Downloadha | -1.232 |
reme | -1.217 |
Token | as |
Token ID | 355 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ificate | +0.204 |
ills | +0.189 |
riet | +0.185 |
Downloadha | +0.183 |
reme | +0.183 |
Neg logit contributions | |
GOODMAN | -0.232 |
cast | -0.230 |
CAST | -0.227 |
fisher | -0.224 |
#$ | -0.223 |
Token | a |
Token ID | 257 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
ificate | +0.680 |
ills | +0.640 |
riet | +0.623 |
iously | +0.619 |
reme | +0.617 |
Neg logit contributions | |
GOODMAN | -0.670 |
cast | -0.659 |
CAST | -0.654 |
fisher | -0.638 |
#$ | -0.636 |
Token | reason |
Token ID | 1738 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
GOODMAN | +0.214 |
cast | +0.213 |
CAST | +0.210 |
fisher | +0.204 |
#$ | +0.203 |
Neg logit contributions | |
ificate | -0.258 |
ills | -0.243 |
riet | -0.239 |
reme | -0.237 |
iously | -0.235 |
Token | for |
Token ID | 329 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
ificate | +0.679 |
ills | +0.628 |
riet | +0.613 |
Downloadha | +0.606 |
iously | +0.605 |
Neg logit contributions | |
GOODMAN | -0.879 |
cast | -0.873 |
CAST | -0.861 |
fisher | -0.853 |
#$ | -0.841 |
Token | it |
Token ID | 340 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
GOODMAN | +0.707 |
cast | +0.706 |
CAST | +0.690 |
fisher | +0.685 |
#$ | +0.673 |
Neg logit contributions | |
ificate | -0.805 |
ills | -0.756 |
riet | -0.746 |
Downloadha | -0.738 |
reme | -0.735 |
Token | .[ |
Token ID | 3693 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
cast | +0.276 |
GOODMAN | +0.276 |
CAST | +0.270 |
fisher | +0.268 |
#$ | +0.264 |
Neg logit contributions | |
ificate | -0.257 |
ills | -0.240 |
riet | -0.237 |
Downloadha | -0.234 |
reme | -0.233 |
Token | 28 |
Token ID | 2078 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
ificate | +0.296 |
ills | +0.278 |
riet | +0.274 |
Downloadha | +0.270 |
reme | +0.270 |
Neg logit contributions | |
GOODMAN | -0.274 |
cast | -0.272 |
CAST | -0.267 |
fisher | -0.266 |
#$ | -0.261 |
Token | this |
Token ID | 428 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ificate | +1.171 |
ills | +1.106 |
iss | +1.065 |
iously | +1.063 |
riet | +1.061 |
Neg logit contributions | |
GOODMAN | -0.944 |
cast | -0.908 |
CAST | -0.905 |
fisher | -0.882 |
cks | -0.881 |
Token | question |
Token ID | 1808 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
GOODMAN | +0.408 |
cast | +0.403 |
CAST | +0.399 |
fisher | +0.390 |
#$ | +0.389 |
Neg logit contributions | |
ificate | -0.421 |
ills | -0.394 |
riet | -0.385 |
iously | -0.382 |
reme | -0.382 |
Token | , |
Token ID | 11 |
Feature activation | +5.68e-03 |
Pos logit contributions | |
ificate | +0.190 |
ills | +0.177 |
riet | +0.173 |
reme | +0.172 |
iously | +0.172 |
Neg logit contributions | |
GOODMAN | -0.199 |
cast | -0.196 |
CAST | -0.194 |
fisher | -0.191 |
#$ | -0.190 |
Token | but |
Token ID | 475 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
GOODMAN | +0.018 |
cast | +0.018 |
CAST | +0.018 |
fisher | +0.018 |
#$ | +0.018 |
Neg logit contributions | |
ificate | -0.017 |
ills | -0.016 |
riet | -0.015 |
Downloadha | -0.015 |
reme | -0.015 |
Token | were |
Token ID | 547 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ificate | +0.735 |
ills | +0.689 |
riet | +0.670 |
iously | +0.665 |
reme | +0.661 |
Neg logit contributions | |
GOODMAN | -0.727 |
cast | -0.713 |
CAST | -0.705 |
fisher | -0.690 |
#$ | -0.688 |
Token | you |
Token ID | 345 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ificate | +0.543 |
ills | +0.514 |
riet | +0.498 |
reme | +0.495 |
iously | +0.493 |
Neg logit contributions | |
GOODMAN | -0.438 |
CAST | -0.429 |
cast | -0.426 |
#$ | -0.417 |
fisher | -0.414 |
Token | a |
Token ID | 257 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
GOODMAN | +0.383 |
cast | +0.382 |
CAST | +0.377 |
fisher | +0.370 |
#$ | +0.368 |
Neg logit contributions | |
ificate | -0.310 |
ills | -0.288 |
riet | -0.282 |
reme | -0.277 |
iously | -0.277 |
Token | Star |
Token ID | 2907 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
ificate | +1.221 |
ills | +1.147 |
riet | +1.126 |
reme | +1.119 |
iously | +1.114 |
Neg logit contributions | |
GOODMAN | -1.163 |
cast | -1.127 |
CAST | -1.123 |
cks | -1.093 |
fisher | -1.086 |
Token | Wars |
Token ID | 6176 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
ificate | +0.982 |
ills | +0.897 |
riet | +0.876 |
reme | +0.868 |
iously | +0.861 |
Neg logit contributions | |
GOODMAN | -1.744 |
CAST | -1.702 |
cast | -1.693 |
fisher | -1.681 |
#$ | -1.668 |
Token | fan |
Token ID | 4336 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
cast | +1.463 |
GOODMAN | +1.455 |
CAST | +1.421 |
fisher | +1.414 |
#$ | +1.385 |
Neg logit contributions | |
ificate | -1.764 |
ills | -1.657 |
riet | -1.638 |
Downloadha | -1.629 |
reme | -1.611 |
Token | as |
Token ID | 355 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
ificate | +0.070 |
ills | +0.066 |
riet | +0.064 |
iously | +0.063 |
reme | +0.063 |
Neg logit contributions | |
GOODMAN | -0.075 |
cast | -0.074 |
CAST | -0.073 |
fisher | -0.072 |
#$ | -0.071 |
Token | ize |
Token ID | 1096 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ificate | +0.875 |
ills | +0.762 |
iously | +0.747 |
riet | +0.742 |
reme | +0.730 |
Neg logit contributions | |
GOODMAN | -1.866 |
cast | -1.838 |
CAST | -1.828 |
fisher | -1.814 |
#$ | -1.800 |
Token | its |
Token ID | 663 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ificate | +0.427 |
ills | +0.402 |
iously | +0.392 |
reme | +0.392 |
riet | +0.392 |
Neg logit contributions | |
GOODMAN | -0.354 |
cast | -0.347 |
CAST | -0.346 |
#$ | -0.337 |
fisher | -0.336 |
Token | geopolitical |
Token ID | 35493 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
ificate | +0.380 |
ills | +0.356 |
iously | +0.353 |
reme | +0.352 |
riet | +0.351 |
Neg logit contributions | |
GOODMAN | -0.264 |
CAST | -0.255 |
cast | -0.255 |
#$ | -0.251 |
cks | -0.244 |
Token | opponents |
Token ID | 7691 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
GOODMAN | +0.142 |
cast | +0.140 |
CAST | +0.139 |
#$ | +0.135 |
fisher | +0.133 |
Neg logit contributions | |
ificate | -0.216 |
ills | -0.203 |
riet | -0.200 |
iously | -0.199 |
reme | -0.199 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
GOODMAN | +0.180 |
cast | +0.179 |
CAST | +0.176 |
fisher | +0.174 |
#$ | +0.172 |
Neg logit contributions | |
ificate | -0.172 |
ills | -0.161 |
riet | -0.158 |
Downloadha | -0.156 |
reme | -0.156 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
cast | +0.500 |
GOODMAN | +0.499 |
CAST | +0.489 |
fisher | +0.485 |
#$ | +0.477 |
Neg logit contributions | |
ificate | -0.507 |
ills | -0.475 |
riet | -0.465 |
Downloadha | -0.460 |
reme | -0.459 |
Token |
|
Token ID | 198 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
GOODMAN | +0.369 |
cast | +0.366 |
CAST | +0.359 |
fisher | +0.358 |
#$ | +0.350 |
Neg logit contributions | |
ificate | -0.382 |
ills | -0.357 |
riet | -0.351 |
reme | -0.345 |
Downloadha | -0.345 |
Token | According |
Token ID | 4821 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
GOODMAN | +0.262 |
cast | +0.259 |
fisher | +0.255 |
CAST | +0.253 |
Zimmer | +0.249 |
Neg logit contributions | |
ificate | -0.223 |
ills | -0.207 |
riet | -0.203 |
Downloadha | -0.200 |
reme | -0.200 |
Token | to |
Token ID | 284 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
ificate | +2.240 |
ills | +2.060 |
iously | +2.023 |
riet | +2.005 |
reme | +1.992 |
Neg logit contributions | |
GOODMAN | -2.939 |
cast | -2.926 |
CAST | -2.887 |
fisher | -2.881 |
cks | -2.830 |
Token | Paul |
Token ID | 3362 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ificate | +1.578 |
ills | +1.500 |
riet | +1.465 |
iously | +1.449 |
Downloadha | +1.449 |
Neg logit contributions | |
GOODMAN | -1.419 |
cast | -1.416 |
CAST | -1.389 |
fisher | -1.360 |
#$ | -1.352 |
Token | Gob |
Token ID | 16909 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
ificate | +1.092 |
ills | +1.030 |
riet | +1.013 |
iss | +0.995 |
reme | +0.994 |
Neg logit contributions | |
GOODMAN | -0.959 |
cast | -0.952 |
CAST | -0.948 |
fisher | -0.926 |
#$ | -0.921 |
Token | the |
Token ID | 262 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
GOODMAN | +0.676 |
cast | +0.674 |
CAST | +0.663 |
fisher | +0.655 |
#$ | +0.644 |
Neg logit contributions | |
ificate | -0.790 |
ills | -0.742 |
riet | -0.730 |
Downloadha | -0.722 |
reme | -0.719 |
Token | boot |
Token ID | 6297 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
ificate | +0.644 |
ills | +0.603 |
riet | +0.597 |
iously | +0.592 |
Downloadha | +0.591 |
Neg logit contributions | |
GOODMAN | -0.443 |
cast | -0.441 |
CAST | -0.440 |
#$ | -0.427 |
fisher | -0.424 |
Token | partition |
Token ID | 18398 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
ificate | +0.503 |
ills | +0.469 |
riet | +0.460 |
iously | +0.456 |
reme | +0.453 |
Neg logit contributions | |
GOODMAN | -0.445 |
cast | -0.438 |
CAST | -0.438 |
fisher | -0.430 |
#$ | -0.426 |
Token | , |
Token ID | 11 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
ificate | +1.237 |
ills | +1.144 |
riet | +1.111 |
iously | +1.110 |
iss | +1.100 |
Neg logit contributions | |
GOODMAN | -1.310 |
CAST | -1.306 |
cast | -1.303 |
fisher | -1.272 |
Zimmer | -1.257 |
Token | forcing |
Token ID | 10833 |
Feature activation | -7.46e-03 |
Pos logit contributions | |
GOODMAN | +0.143 |
cast | +0.142 |
CAST | +0.140 |
fisher | +0.138 |
#$ | +0.136 |
Neg logit contributions | |
ificate | -0.138 |
ills | -0.129 |
riet | -0.127 |
Downloadha | -0.125 |
reme | -0.125 |
Token | a |
Token ID | 257 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
ificate | +0.027 |
ills | +0.026 |
riet | +0.025 |
iously | +0.025 |
Downloadha | +0.025 |
Neg logit contributions | |
GOODMAN | -0.019 |
cast | -0.019 |
CAST | -0.019 |
fisher | -0.018 |
#$ | -0.018 |
Token | reboot |
Token ID | 20149 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ificate | +0.198 |
ills | +0.184 |
riet | +0.181 |
reme | +0.178 |
iously | +0.178 |
Neg logit contributions | |
GOODMAN | -0.210 |
cast | -0.209 |
CAST | -0.206 |
fisher | -0.203 |
#$ | -0.201 |
Token | . |
Token ID | 13 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
GOODMAN | +0.466 |
cast | +0.461 |
CAST | +0.457 |
fisher | +0.450 |
#$ | +0.444 |
Neg logit contributions | |
ificate | -0.434 |
ills | -0.403 |
riet | -0.394 |
iously | -0.390 |
reme | -0.389 |
Token |
|
Token ID | 198 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
ificate | +0.487 |
ills | +0.455 |
riet | +0.443 |
iously | +0.440 |
reme | +0.439 |
Neg logit contributions | |
GOODMAN | -0.511 |
cast | -0.509 |
CAST | -0.505 |
fisher | -0.498 |
#$ | -0.492 |
Token |
|
Token ID | 198 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
ificate | +0.137 |
ills | +0.128 |
riet | +0.125 |
iously | +0.123 |
reme | +0.123 |
Neg logit contributions | |
GOODMAN | -0.138 |
cast | -0.136 |
CAST | -0.134 |
fisher | -0.134 |
� | -0.131 |
Token | When |
Token ID | 2215 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
ificate | +0.236 |
ills | +0.219 |
riet | +0.215 |
Downloadha | +0.213 |
reme | +0.211 |
Neg logit contributions | |
GOODMAN | -0.300 |
cast | -0.296 |
fisher | -0.292 |
CAST | -0.291 |
Zimmer | -0.287 |
Token | would |
Token ID | 561 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
GOODMAN | +0.128 |
cast | +0.127 |
CAST | +0.125 |
fisher | +0.123 |
#$ | +0.121 |
Neg logit contributions | |
ificate | -0.129 |
ills | -0.121 |
riet | -0.119 |
reme | -0.117 |
Downloadha | -0.116 |
Token | � |
Token ID | 447 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
GOODMAN | +0.772 |
cast | +0.765 |
CAST | +0.751 |
fisher | +0.741 |
#$ | +0.731 |
Neg logit contributions | |
ificate | -0.797 |
ills | -0.746 |
riet | -0.734 |
reme | -0.724 |
iously | -0.719 |
Token | � |
Token ID | 247 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
cast | +0.588 |
GOODMAN | +0.587 |
CAST | +0.573 |
fisher | +0.568 |
#$ | +0.559 |
Neg logit contributions | |
ificate | -0.780 |
ills | -0.734 |
riet | -0.726 |
Downloadha | -0.722 |
reme | -0.716 |
Token | ve |
Token ID | 303 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
GOODMAN | +0.410 |
cast | +0.405 |
CAST | +0.401 |
fisher | +0.397 |
Zimmer | +0.391 |
Neg logit contributions | |
ificate | -0.311 |
ills | -0.288 |
riet | -0.284 |
reme | -0.278 |
iously | -0.277 |
Token | made |
Token ID | 925 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ificate | +0.478 |
ills | +0.448 |
riet | +0.441 |
reme | +0.428 |
iously | +0.427 |
Neg logit contributions | |
GOODMAN | -0.552 |
cast | -0.539 |
CAST | -0.537 |
fisher | -0.524 |
#$ | -0.523 |
Token | it |
Token ID | 340 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
GOODMAN | +0.042 |
cast | +0.042 |
CAST | +0.041 |
fisher | +0.040 |
#$ | +0.040 |
Neg logit contributions | |
ificate | -0.045 |
ills | -0.042 |
riet | -0.041 |
reme | -0.041 |
Downloadha | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
GOODMAN | +0.078 |
cast | +0.078 |
CAST | +0.076 |
fisher | +0.075 |
#$ | +0.074 |
Neg logit contributions | |
ificate | -0.088 |
ills | -0.083 |
riet | -0.082 |
reme | -0.080 |
Downloadha | -0.080 |
Token | less |
Token ID | 1342 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
GOODMAN | +0.613 |
cast | +0.612 |
CAST | +0.600 |
fisher | +0.596 |
#$ | +0.586 |
Neg logit contributions | |
ificate | -0.543 |
ills | -0.506 |
riet | -0.498 |
Downloadha | -0.492 |
reme | -0.490 |
Token | upsetting |
Token ID | 38423 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
cast | +1.166 |
GOODMAN | +1.166 |
CAST | +1.141 |
fisher | +1.136 |
#$ | +1.118 |
Neg logit contributions | |
ificate | -1.004 |
ills | -0.934 |
riet | -0.920 |
Downloadha | -0.910 |
reme | -0.904 |
Token | book |
Token ID | 1492 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
GOODMAN | +1.343 |
cast | +1.342 |
CAST | +1.310 |
fisher | +1.301 |
#$ | +1.278 |
Neg logit contributions | |
ificate | -1.557 |
ills | -1.463 |
riet | -1.444 |
Downloadha | -1.429 |
reme | -1.423 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
cast | +1.591 |
GOODMAN | +1.587 |
CAST | +1.547 |
fisher | +1.546 |
#$ | +1.512 |
Neg logit contributions | |
ificate | -1.634 |
ills | -1.533 |
riet | -1.520 |
Downloadha | -1.509 |
reme | -1.490 |
Token | isn |
Token ID | 2125 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
GOODMAN | +0.056 |
cast | +0.056 |
CAST | +0.055 |
fisher | +0.054 |
#$ | +0.054 |
Neg logit contributions | |
ificate | -0.049 |
ills | -0.045 |
riet | -0.045 |
reme | -0.044 |
Downloadha | -0.044 |
Token | 't |
Token ID | 470 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
ificate | +0.522 |
ills | +0.491 |
riet | +0.483 |
iously | +0.478 |
reme | +0.476 |
Neg logit contributions | |
GOODMAN | -0.411 |
cast | -0.403 |
CAST | -0.398 |
fisher | -0.396 |
Zimmer | -0.387 |
Token | just |
Token ID | 655 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
ificate | +1.160 |
ills | +1.089 |
riet | +1.074 |
Downloadha | +1.058 |
reme | +1.058 |
Neg logit contributions | |
GOODMAN | -0.966 |
cast | -0.947 |
CAST | -0.945 |
fisher | -0.914 |
#$ | -0.907 |
Token | measured |
Token ID | 8630 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
ificate | +0.616 |
ills | +0.578 |
riet | +0.568 |
reme | +0.563 |
Downloadha | +0.562 |
Neg logit contributions | |
GOODMAN | -0.540 |
cast | -0.530 |
CAST | -0.525 |
fisher | -0.514 |
#$ | -0.507 |
Token | on |
Token ID | 319 |
Feature activation | -2.04e-03 |
Pos logit contributions | |
GOODMAN | +0.201 |
cast | +0.200 |
CAST | +0.197 |
fisher | +0.195 |
#$ | +0.191 |
Neg logit contributions | |
ificate | -0.186 |
ills | -0.174 |
riet | -0.171 |
Downloadha | -0.169 |
reme | -0.168 |
Token | the |
Token ID | 262 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
ificate | +0.007 |
ills | +0.006 |
riet | +0.006 |
iously | +0.006 |
reme | +0.006 |
Neg logit contributions | |
GOODMAN | -0.006 |
cast | -0.006 |
CAST | -0.006 |
fisher | -0.006 |
#$ | -0.006 |
Token | street |
Token ID | 4675 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
ificate | +0.108 |
ills | +0.102 |
riet | +0.100 |
Downloadha | +0.099 |
reme | +0.099 |
Neg logit contributions | |
GOODMAN | -0.102 |
cast | -0.102 |
CAST | -0.100 |
fisher | -0.099 |
#$ | -0.097 |
Token | or |
Token ID | 393 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
GOODMAN | +1.289 |
cast | +1.279 |
CAST | +1.263 |
fisher | +1.244 |
#$ | +1.225 |
Neg logit contributions | |
ificate | -1.290 |
ills | -1.217 |
riet | -1.190 |
reme | -1.175 |
Downloadha | -1.175 |
Token | at |
Token ID | 379 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
GOODMAN | +0.119 |
cast | +0.118 |
CAST | +0.117 |
fisher | +0.114 |
#$ | +0.113 |
Neg logit contributions | |
ificate | -0.117 |
ills | -0.110 |
riet | -0.108 |
Downloadha | -0.106 |
iously | -0.106 |
Token | the |
Token ID | 262 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ificate | +0.128 |
ills | +0.122 |
riet | +0.119 |
reme | +0.118 |
iously | +0.118 |
Neg logit contributions | |
GOODMAN | -0.101 |
cast | -0.099 |
CAST | -0.099 |
fisher | -0.095 |
cks | -0.093 |
Token | track |
Token ID | 2610 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
GOODMAN | +0.657 |
cast | +0.653 |
CAST | +0.641 |
fisher | +0.626 |
#$ | +0.616 |
Neg logit contributions | |
ificate | -0.949 |
ills | -0.903 |
riet | -0.888 |
Downloadha | -0.877 |
reme | -0.877 |
Token | , |
Token ID | 11 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ificate | +0.214 |
ills | +0.200 |
riet | +0.195 |
reme | +0.193 |
iously | +0.193 |
Neg logit contributions | |
GOODMAN | -0.231 |
cast | -0.230 |
CAST | -0.227 |
fisher | -0.225 |
#$ | -0.221 |
Token | but |
Token ID | 475 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ificate | +0.389 |
ills | +0.364 |
riet | +0.357 |
Downloadha | +0.353 |
reme | +0.351 |
Neg logit contributions | |
GOODMAN | -0.427 |
cast | -0.425 |
CAST | -0.418 |
fisher | -0.413 |
#$ | -0.408 |
Token | there |
Token ID | 612 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
ificate | +0.514 |
ills | +0.482 |
riet | +0.472 |
Downloadha | +0.468 |
iously | +0.467 |
Neg logit contributions | |
GOODMAN | -0.489 |
cast | -0.483 |
CAST | -0.477 |
fisher | -0.469 |
#$ | -0.465 |
Token | is |
Token ID | 318 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ificate | +0.995 |
ills | +0.931 |
iously | +0.906 |
riet | +0.904 |
iss | +0.900 |
Neg logit contributions | |
GOODMAN | -1.024 |
cast | -1.014 |
CAST | -1.012 |
#$ | -0.987 |
fisher | -0.984 |
Token | a |
Token ID | 257 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
ificate | +0.403 |
ills | +0.377 |
riet | +0.369 |
iously | +0.368 |
reme | +0.365 |
Neg logit contributions | |
GOODMAN | -0.378 |
cast | -0.374 |
CAST | -0.370 |
#$ | -0.361 |
fisher | -0.361 |
Token | definite |
Token ID | 21892 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
ificate | +1.213 |
ills | +1.128 |
riet | +1.112 |
iously | +1.098 |
reme | +1.094 |
Neg logit contributions | |
GOODMAN | -1.273 |
cast | -1.256 |
CAST | -1.242 |
#$ | -1.212 |
fisher | -1.208 |
Token | push |
Token ID | 4574 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
GOODMAN | +0.097 |
cast | +0.096 |
CAST | +0.094 |
fisher | +0.092 |
#$ | +0.092 |
Neg logit contributions | |
ificate | -0.096 |
ills | -0.089 |
riet | -0.087 |
reme | -0.086 |
iss | -0.086 |
Token | to |
Token ID | 284 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
ificate | +1.917 |
ills | +1.773 |
iss | +1.723 |
riet | +1.713 |
reme | +1.710 |
Neg logit contributions | |
GOODMAN | -2.378 |
CAST | -2.334 |
cast | -2.318 |
fisher | -2.288 |
#$ | -2.287 |
Token | keep |
Token ID | 1394 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
ificate | +1.725 |
ills | +1.622 |
iously | +1.587 |
riet | +1.575 |
iss | +1.568 |
Neg logit contributions | |
GOODMAN | -1.642 |
cast | -1.631 |
CAST | -1.602 |
#$ | -1.573 |
fisher | -1.571 |
Token | this |
Token ID | 428 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
ificate | +2.221 |
ills | +2.091 |
iously | +2.039 |
riet | +2.032 |
Downloadha | +2.016 |
Neg logit contributions | |
GOODMAN | -2.352 |
cast | -2.302 |
CAST | -2.285 |
#$ | -2.237 |
fisher | -2.232 |
Token | momentum |
Token ID | 12858 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ificate | +0.208 |
ills | +0.193 |
riet | +0.190 |
iously | +0.187 |
reme | +0.187 |
Neg logit contributions | |
GOODMAN | -0.243 |
cast | -0.241 |
CAST | -0.237 |
fisher | -0.234 |
#$ | -0.232 |
Token | felt |
Token ID | 2936 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
ificate | +1.125 |
ills | +1.055 |
riet | +1.035 |
reme | +1.008 |
iss | +1.007 |
Neg logit contributions | |
GOODMAN | -1.357 |
cast | -1.352 |
CAST | -1.331 |
fisher | -1.313 |
#$ | -1.300 |
Token | like |
Token ID | 588 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
GOODMAN | +0.174 |
cast | +0.173 |
CAST | +0.170 |
fisher | +0.168 |
#$ | +0.166 |
Neg logit contributions | |
ificate | -0.193 |
ills | -0.182 |
riet | -0.179 |
Downloadha | -0.177 |
reme | -0.176 |
Token | they |
Token ID | 484 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ificate | +0.290 |
ills | +0.273 |
riet | +0.267 |
reme | +0.264 |
Downloadha | +0.263 |
Neg logit contributions | |
GOODMAN | -0.281 |
cast | -0.279 |
CAST | -0.275 |
fisher | -0.270 |
#$ | -0.268 |
Token | should |
Token ID | 815 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
ificate | +0.622 |
ills | +0.577 |
riet | +0.567 |
reme | +0.555 |
Downloadha | +0.553 |
Neg logit contributions | |
GOODMAN | -0.803 |
cast | -0.800 |
CAST | -0.786 |
fisher | -0.780 |
#$ | -0.771 |
Token | ask |
Token ID | 1265 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ificate | +0.599 |
ills | +0.559 |
riet | +0.546 |
reme | +0.542 |
iously | +0.540 |
Neg logit contributions | |
GOODMAN | -0.576 |
cast | -0.568 |
CAST | -0.562 |
fisher | -0.552 |
#$ | -0.550 |
Token | me |
Token ID | 502 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
ificate | +0.447 |
ills | +0.417 |
riet | +0.408 |
reme | +0.402 |
Downloadha | +0.402 |
Neg logit contributions | |
GOODMAN | -0.486 |
cast | -0.484 |
CAST | -0.476 |
fisher | -0.470 |
#$ | -0.463 |
Token | . |
Token ID | 13 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ificate | +0.693 |
ills | +0.645 |
riet | +0.626 |
iously | +0.622 |
iss | +0.618 |
Neg logit contributions | |
GOODMAN | -0.676 |
cast | -0.673 |
CAST | -0.665 |
fisher | -0.651 |
#$ | -0.645 |
Token | I |
Token ID | 314 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
ificate | +0.833 |
ills | +0.781 |
riet | +0.756 |
iously | +0.750 |
reme | +0.747 |
Neg logit contributions | |
GOODMAN | -0.913 |
cast | -0.908 |
CAST | -0.894 |
fisher | -0.889 |
#$ | -0.869 |
Token | said |
Token ID | 531 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
ificate | +0.135 |
ills | +0.126 |
riet | +0.125 |
reme | +0.122 |
iss | +0.122 |
Neg logit contributions | |
GOODMAN | -0.144 |
cast | -0.143 |
CAST | -0.141 |
fisher | -0.139 |
#$ | -0.137 |
Token | � |
Token ID | 564 |
Feature activation | +8.74e-03 |
Pos logit contributions | |
ificate | +0.099 |
ills | +0.093 |
riet | +0.091 |
Downloadha | +0.090 |
iously | +0.090 |
Neg logit contributions | |
GOODMAN | -0.088 |
cast | -0.087 |
CAST | -0.086 |
fisher | -0.085 |
#$ | -0.083 |
Token | � |
Token ID | 250 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
GOODMAN | +0.011 |
cast | +0.011 |
CAST | +0.011 |
fisher | +0.011 |
Zimmer | +0.010 |
Neg logit contributions | |
ificate | -0.043 |
ills | -0.042 |
riet | -0.041 |
reme | -0.041 |
iously | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
cast | +1.590 |
GOODMAN | +1.587 |
CAST | +1.550 |
fisher | +1.543 |
Zimmer | +1.520 |
Neg logit contributions | |
ificate | -1.584 |
ills | -1.480 |
riet | -1.465 |
Downloadha | -1.448 |
reme | -1.440 |
Token | � |
Token ID | 564 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
GOODMAN | +0.101 |
cast | +0.101 |
CAST | +0.099 |
fisher | +0.098 |
#$ | +0.096 |
Neg logit contributions | |
ificate | -0.114 |
ills | -0.107 |
riet | -0.105 |
Downloadha | -0.104 |
reme | -0.104 |
Token | � |
Token ID | 250 |
Feature activation | +8.58e-03 |
Pos logit contributions | |
GOODMAN | +0.330 |
cast | +0.329 |
CAST | +0.320 |
fisher | +0.316 |
Zimmer | +0.308 |
Neg logit contributions | |
ificate | -0.587 |
ills | -0.560 |
riet | -0.552 |
reme | -0.545 |
Downloadha | -0.544 |
Token | But |
Token ID | 1537 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
GOODMAN | +0.031 |
cast | +0.031 |
CAST | +0.030 |
fisher | +0.030 |
Zimmer | +0.029 |
Neg logit contributions | |
ificate | -0.023 |
ills | -0.021 |
riet | -0.020 |
Downloadha | -0.020 |
reme | -0.020 |
Token | I |
Token ID | 314 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
ificate | +0.851 |
ills | +0.798 |
riet | +0.778 |
iously | +0.775 |
Downloadha | +0.774 |
Neg logit contributions | |
GOODMAN | -0.806 |
cast | -0.801 |
CAST | -0.790 |
fisher | -0.774 |
#$ | -0.763 |
Token | just |
Token ID | 655 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
ificate | +0.110 |
ills | +0.103 |
riet | +0.101 |
reme | +0.099 |
iously | +0.099 |
Neg logit contributions | |
GOODMAN | -0.123 |
cast | -0.122 |
CAST | -0.121 |
fisher | -0.118 |
#$ | -0.117 |
Token | felt |
Token ID | 2936 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
ificate | +2.745 |
ills | +2.556 |
riet | +2.489 |
iss | +2.485 |
reme | +2.452 |
Neg logit contributions | |
GOODMAN | -3.378 |
CAST | -3.294 |
cast | -3.281 |
#$ | -3.207 |
fisher | -3.193 |
Token | like |
Token ID | 588 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
GOODMAN | +0.875 |
cast | +0.872 |
CAST | +0.854 |
fisher | +0.846 |
#$ | +0.832 |
Neg logit contributions | |
ificate | -0.995 |
ills | -0.935 |
riet | -0.921 |
Downloadha | -0.912 |
reme | -0.907 |
Token | God |
Token ID | 1793 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ificate | +0.142 |
ills | +0.133 |
riet | +0.130 |
Downloadha | +0.129 |
iously | +0.129 |
Neg logit contributions | |
GOODMAN | -0.137 |
cast | -0.136 |
CAST | -0.134 |
fisher | -0.131 |
#$ | -0.130 |
Token | kept |
Token ID | 4030 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
GOODMAN | +0.936 |
cast | +0.931 |
CAST | +0.916 |
fisher | +0.909 |
#$ | +0.894 |
Neg logit contributions | |
ificate | -0.851 |
ills | -0.795 |
riet | -0.781 |
reme | -0.767 |
Downloadha | -0.767 |
Token | getting |
Token ID | 1972 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ificate | +2.267 |
ills | +2.130 |
iss | +2.109 |
iously | +2.038 |
riet | +2.004 |
Neg logit contributions | |
GOODMAN | -2.770 |
CAST | -2.711 |
cast | -2.684 |
#$ | -2.617 |
fisher | -2.609 |
Token | against |
Token ID | 1028 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
GOODMAN | +0.130 |
cast | +0.128 |
CAST | +0.127 |
fisher | +0.126 |
#$ | +0.125 |
Neg logit contributions | |
ificate | -0.073 |
ills | -0.066 |
riet | -0.064 |
Downloadha | -0.064 |
iously | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
ificate | +1.164 |
ills | +1.099 |
riet | +1.079 |
reme | +1.078 |
iously | +1.069 |
Neg logit contributions | |
GOODMAN | -0.933 |
cast | -0.932 |
CAST | -0.911 |
fisher | -0.897 |
#$ | -0.895 |
Token | All |
Token ID | 1439 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
GOODMAN | +0.097 |
cast | +0.097 |
CAST | +0.095 |
fisher | +0.093 |
#$ | +0.093 |
Neg logit contributions | |
ificate | -0.117 |
ills | -0.111 |
riet | -0.109 |
reme | -0.108 |
iously | -0.107 |
Token | ent |
Token ID | 298 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ificate | +0.088 |
ills | +0.083 |
riet | +0.081 |
reme | +0.080 |
iss | +0.079 |
Neg logit contributions | |
GOODMAN | -0.126 |
cast | -0.123 |
CAST | -0.122 |
fisher | -0.122 |
#$ | -0.120 |
Token | own |
Token ID | 593 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
ificate | +0.496 |
ills | +0.472 |
riet | +0.461 |
reme | +0.458 |
iously | +0.453 |
Neg logit contributions | |
GOODMAN | -0.411 |
cast | -0.398 |
CAST | -0.396 |
fisher | -0.394 |
#$ | -0.389 |
Token | detective |
Token ID | 20775 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
ificate | +0.568 |
ills | +0.540 |
reme | +0.525 |
riet | +0.524 |
iss | +0.519 |
Neg logit contributions | |
GOODMAN | -0.501 |
cast | -0.498 |
CAST | -0.485 |
#$ | -0.475 |
fisher | -0.475 |
Token | he |
Token ID | 339 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
ificate | +2.423 |
ills | +2.277 |
iously | +2.197 |
riet | +2.197 |
reme | +2.170 |
Neg logit contributions | |
cast | -3.029 |
GOODMAN | -3.016 |
CAST | -3.003 |
#$ | -2.909 |
� | -2.896 |
Token | claims |
Token ID | 3667 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
ificate | +0.206 |
ills | +0.192 |
riet | +0.189 |
iously | +0.188 |
iss | +0.185 |
Neg logit contributions | |
GOODMAN | -0.240 |
cast | -0.235 |
CAST | -0.234 |
fisher | -0.229 |
#$ | -0.229 |
Token | is |
Token ID | 318 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
ificate | +1.812 |
ills | +1.669 |
iously | +1.657 |
riet | +1.639 |
iss | +1.633 |
Neg logit contributions | |
GOODMAN | -2.310 |
cast | -2.270 |
CAST | -2.269 |
fisher | -2.214 |
#$ | -2.204 |
Token | responsible |
Token ID | 4497 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
ificate | +0.613 |
ills | +0.572 |
riet | +0.563 |
iously | +0.561 |
reme | +0.559 |
Neg logit contributions | |
GOODMAN | -0.569 |
cast | -0.565 |
CAST | -0.555 |
fisher | -0.543 |
#$ | -0.540 |
Token | for |
Token ID | 329 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
ificate | +0.671 |
ills | +0.621 |
riet | +0.609 |
Downloadha | +0.600 |
reme | +0.598 |
Neg logit contributions | |
GOODMAN | -0.898 |
cast | -0.896 |
CAST | -0.880 |
fisher | -0.874 |
#$ | -0.862 |
Token | . |
Token ID | 13 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
ificate | +1.106 |
ills | +1.047 |
reme | +1.022 |
riet | +1.018 |
iss | +1.017 |
Neg logit contributions | |
GOODMAN | -0.949 |
cast | -0.936 |
CAST | -0.922 |
fisher | -0.900 |
#$ | -0.898 |
Token |
|
Token ID | 198 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
GOODMAN | +0.293 |
cast | +0.292 |
CAST | +0.285 |
fisher | +0.284 |
#$ | +0.278 |
Neg logit contributions | |
ificate | -0.319 |
ills | -0.299 |
riet | -0.296 |
Downloadha | -0.292 |
reme | -0.291 |
Token |
|
Token ID | 198 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
GOODMAN | +0.426 |
cast | +0.423 |
CAST | +0.414 |
fisher | +0.412 |
#$ | +0.404 |
Neg logit contributions | |
ificate | -0.446 |
ills | -0.417 |
riet | -0.410 |
reme | -0.404 |
Downloadha | -0.404 |
Token | ' |
Token ID | 6 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
GOODMAN | +0.267 |
cast | +0.264 |
fisher | +0.259 |
CAST | +0.257 |
Zimmer | +0.254 |
Neg logit contributions | |
ificate | -0.244 |
ills | -0.228 |
riet | -0.224 |
reme | -0.221 |
Downloadha | -0.221 |
Token | Now |
Token ID | 3844 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ificate | +1.298 |
ills | +1.227 |
riet | +1.185 |
reme | +1.174 |
Downloadha | +1.173 |
Neg logit contributions | |
GOODMAN | -1.428 |
cast | -1.390 |
fisher | -1.381 |
CAST | -1.354 |
Zimmer | -1.352 |
Token | here |
Token ID | 1456 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
GOODMAN | +0.511 |
cast | +0.502 |
CAST | +0.495 |
fisher | +0.488 |
#$ | +0.483 |
Neg logit contributions | |
ificate | -0.496 |
ills | -0.468 |
riet | -0.454 |
reme | -0.452 |
Downloadha | -0.450 |
Token | is |
Token ID | 318 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
ificate | +2.795 |
ills | +2.690 |
iously | +2.597 |
riet | +2.593 |
iss | +2.583 |
Neg logit contributions | |
GOODMAN | -3.707 |
cast | -3.673 |
CAST | -3.663 |
#$ | -3.564 |
fisher | -3.542 |
Token | safe |
Token ID | 3338 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ificate | +1.600 |
ills | +1.509 |
riet | +1.474 |
reme | +1.463 |
iss | +1.461 |
Neg logit contributions | |
GOODMAN | -1.527 |
cast | -1.506 |
CAST | -1.485 |
#$ | -1.437 |
� | -1.428 |
Token | ' |
Token ID | 6 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
ificate | +0.362 |
ills | +0.340 |
iously | +0.334 |
riet | +0.331 |
iss | +0.330 |
Neg logit contributions | |
GOODMAN | -0.277 |
cast | -0.269 |
CAST | -0.266 |
fisher | -0.261 |
#$ | -0.260 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ificate | +0.159 |
ills | +0.148 |
riet | +0.146 |
reme | +0.143 |
iously | +0.143 |
Neg logit contributions | |
GOODMAN | -0.160 |
cast | -0.158 |
CAST | -0.156 |
fisher | -0.153 |
#$ | -0.153 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ificate | +0.503 |
ills | +0.468 |
riet | +0.458 |
iously | +0.453 |
reme | +0.452 |
Neg logit contributions | |
GOODMAN | -0.517 |
cast | -0.506 |
fisher | -0.500 |
CAST | -0.499 |
� | -0.490 |
Token | which |
Token ID | 543 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
ificate | +0.403 |
ills | +0.379 |
riet | +0.372 |
iously | +0.370 |
Downloadha | +0.367 |
Neg logit contributions | |
GOODMAN | -0.338 |
cast | -0.334 |
CAST | -0.332 |
#$ | -0.328 |
fisher | -0.323 |
Token | they |
Token ID | 484 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
GOODMAN | +0.096 |
cast | +0.095 |
CAST | +0.094 |
#$ | +0.092 |
fisher | +0.092 |
Neg logit contributions | |
ificate | -0.104 |
ills | -0.098 |
riet | -0.095 |
iss | -0.094 |
iously | -0.094 |
Token | are |
Token ID | 389 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
ificate | +0.103 |
ills | +0.096 |
riet | +0.095 |
reme | +0.094 |
iously | +0.094 |
Neg logit contributions | |
GOODMAN | -0.101 |
cast | -0.100 |
CAST | -0.099 |
#$ | -0.099 |
fisher | -0.096 |
Token | en |
Token ID | 551 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
ificate | +0.157 |
ills | +0.147 |
riet | +0.144 |
reme | +0.142 |
Downloadha | +0.141 |
Neg logit contributions | |
GOODMAN | -0.181 |
cast | -0.178 |
CAST | -0.176 |
#$ | -0.174 |
fisher | -0.174 |
Token | mes |
Token ID | 6880 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
ificate | +0.232 |
ills | +0.220 |
riet | +0.216 |
reme | +0.214 |
iously | +0.213 |
Neg logit contributions | |
GOODMAN | -0.170 |
cast | -0.166 |
CAST | -0.164 |
fisher | -0.162 |
#$ | -0.160 |
Token | hed |
Token ID | 704 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ificate | +0.689 |
ills | +0.661 |
riet | +0.644 |
iously | +0.642 |
reme | +0.634 |
Neg logit contributions | |
GOODMAN | -0.600 |
CAST | -0.586 |
cast | -0.585 |
fisher | -0.577 |
Zimmer | -0.571 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ificate | +2.776 |
ills | +2.601 |
iss | +2.508 |
iously | +2.505 |
riet | +2.492 |
Neg logit contributions | |
GOODMAN | -3.347 |
cast | -3.321 |
CAST | -3.310 |
#$ | -3.243 |
fisher | -3.243 |
Token | Thus |
Token ID | 6660 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
GOODMAN | +0.596 |
cast | +0.595 |
CAST | +0.584 |
fisher | +0.580 |
#$ | +0.572 |
Neg logit contributions | |
ificate | -0.596 |
ills | -0.558 |
riet | -0.546 |
reme | -0.538 |
Downloadha | -0.538 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
cast | +1.673 |
GOODMAN | +1.670 |
CAST | +1.626 |
fisher | +1.622 |
Zimmer | +1.590 |
Neg logit contributions | |
ificate | -1.883 |
ills | -1.765 |
riet | -1.744 |
Downloadha | -1.729 |
reme | -1.719 |
Token | power |
Token ID | 1176 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
GOODMAN | +0.301 |
cast | +0.299 |
CAST | +0.296 |
fisher | +0.290 |
#$ | +0.289 |
Neg logit contributions | |
ificate | -0.327 |
ills | -0.307 |
riet | -0.303 |
Downloadha | -0.297 |
reme | -0.297 |
Token | and |
Token ID | 290 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
GOODMAN | +0.869 |
cast | +0.865 |
CAST | +0.850 |
fisher | +0.842 |
#$ | +0.830 |
Neg logit contributions | |
ificate | -0.882 |
ills | -0.825 |
riet | -0.815 |
Downloadha | -0.803 |
reme | -0.800 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
ificate | +0.592 |
ills | +0.556 |
riet | +0.545 |
Downloadha | +0.538 |
reme | +0.538 |
Neg logit contributions | |
GOODMAN | -0.579 |
cast | -0.577 |
CAST | -0.566 |
fisher | -0.561 |
#$ | -0.553 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
GOODMAN | +0.056 |
cast | +0.056 |
CAST | +0.055 |
fisher | +0.055 |
#$ | +0.054 |
Neg logit contributions | |
ificate | -0.058 |
ills | -0.054 |
riet | -0.053 |
reme | -0.053 |
iously | -0.052 |
Token | According |
Token ID | 4821 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
ificate | +0.040 |
ills | +0.037 |
riet | +0.037 |
Downloadha | +0.036 |
reme | +0.036 |
Neg logit contributions | |
GOODMAN | -0.046 |
cast | -0.045 |
fisher | -0.044 |
CAST | -0.044 |
Zimmer | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
ificate | +2.143 |
ills | +1.974 |
iously | +1.936 |
riet | +1.932 |
reme | +1.917 |
Neg logit contributions | |
GOODMAN | -2.805 |
cast | -2.764 |
CAST | -2.740 |
fisher | -2.723 |
#$ | -2.680 |
Token | the |
Token ID | 262 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
ificate | +1.789 |
ills | +1.700 |
riet | +1.668 |
reme | +1.649 |
Downloadha | +1.648 |
Neg logit contributions | |
GOODMAN | -1.529 |
cast | -1.519 |
CAST | -1.496 |
fisher | -1.463 |
#$ | -1.454 |
Token | FIR |
Token ID | 23703 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
ificate | +1.240 |
ills | +1.180 |
riet | +1.152 |
reme | +1.140 |
iously | +1.137 |
Neg logit contributions | |
GOODMAN | -1.028 |
cast | -1.023 |
CAST | -1.005 |
#$ | -0.985 |
fisher | -0.981 |
Token | , |
Token ID | 11 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ificate | +2.868 |
ills | +2.685 |
riet | +2.635 |
iss | +2.588 |
iously | +2.584 |
Neg logit contributions | |
GOODMAN | -2.950 |
cast | -2.941 |
CAST | -2.907 |
fisher | -2.847 |
#$ | -2.845 |
Token | � |
Token ID | 564 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
ificate | +1.041 |
ills | +0.978 |
riet | +0.963 |
reme | +0.954 |
Downloadha | +0.952 |
Neg logit contributions | |
GOODMAN | -0.947 |
cast | -0.943 |
CAST | -0.931 |
fisher | -0.911 |
#$ | -0.910 |
Token | � |
Token ID | 250 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
cast | +0.145 |
GOODMAN | +0.144 |
CAST | +0.140 |
fisher | +0.139 |
� | +0.136 |
Neg logit contributions | |
ificate | -0.263 |
ills | -0.250 |
riet | -0.247 |
Downloadha | -0.246 |
reme | -0.244 |
Token | inn |
Token ID | 3732 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
GOODMAN | +0.563 |
cast | +0.555 |
CAST | +0.545 |
fisher | +0.544 |
Zimmer | +0.535 |
Neg logit contributions | |
ificate | -0.542 |
ills | -0.510 |
riet | -0.501 |
Downloadha | -0.495 |
reme | -0.494 |
Token | ocent |
Token ID | 29421 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ificate | +1.167 |
ills | +1.098 |
riet | +1.077 |
reme | +1.061 |
iously | +1.061 |
Neg logit contributions | |
GOODMAN | -1.207 |
CAST | -1.197 |
cast | -1.191 |
fisher | -1.163 |
#$ | -1.156 |