Token | in |
Token ID | 287 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
urga | +0.334 |
ahi | +0.308 |
rika | +0.298 |
ordinate | +0.293 |
htar | +0.289 |
Neg logit contributions | |
Brief | -0.259 |
Learns | -0.250 |
loose | -0.249 |
Neutral | -0.238 |
consequential | -0.234 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
urga | +0.323 |
ahi | +0.297 |
rika | +0.288 |
ordinate | +0.282 |
htar | +0.279 |
Neg logit contributions | |
Brief | -0.257 |
Learns | -0.247 |
loose | -0.246 |
Neutral | -0.236 |
camps | -0.232 |
Token | , |
Token ID | 11 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
urga | +0.967 |
ahi | +0.891 |
rika | +0.856 |
ordinate | +0.841 |
htar | +0.834 |
Neg logit contributions | |
Brief | -0.853 |
Learns | -0.832 |
loose | -0.821 |
Neutral | -0.791 |
consequential | -0.779 |
Token | Steve |
Token ID | 6542 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
urga | +0.284 |
ahi | +0.263 |
rika | +0.255 |
ordinate | +0.251 |
htar | +0.249 |
Neg logit contributions | |
Brief | -0.193 |
Learns | -0.187 |
loose | -0.185 |
Neutral | -0.177 |
consequential | -0.173 |
Token | Kor |
Token ID | 14769 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Brief | +0.514 |
Learns | +0.489 |
loose | +0.485 |
Neutral | +0.467 |
Cable | +0.456 |
Neg logit contributions | |
urga | -0.602 |
ahi | -0.548 |
rika | -0.534 |
ordinate | -0.532 |
htar | -0.518 |
Token | |
Token ID | 3907 |
Feature activation | +7.27e+00 |
Pos logit contributions | |
urga | +1.110 |
ahi | +1.005 |
rika | +0.969 |
ordinate | +0.954 |
htar | +0.938 |
Neg logit contributions | |
Brief | -1.122 |
Learns | -1.088 |
loose | -1.081 |
Neutral | -1.042 |
camps | -1.027 |
Token | n |
Token ID | 77 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
Brief | +5.094 |
Learns | +4.928 |
loose | +4.882 |
conom | +4.791 |
camps | +4.662 |
Neg logit contributions | |
urga | -5.092 |
ahi | -4.554 |
ordinate | -4.457 |
rika | -4.367 |
htar | -4.276 |
Token | ack |
Token ID | 441 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Brief | +2.315 |
Learns | +2.259 |
loose | +2.240 |
Neutral | +2.152 |
camps | +2.129 |
Neg logit contributions | |
urga | -2.204 |
ahi | -1.967 |
rika | -1.929 |
ordinate | -1.910 |
htar | -1.859 |
Token | i |
Token ID | 72 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
Brief | +0.275 |
Learns | +0.264 |
loose | +0.264 |
Neutral | +0.250 |
camps | +0.247 |
Neg logit contributions | |
urga | -0.369 |
ahi | -0.337 |
rika | -0.329 |
ordinate | -0.326 |
htar | -0.319 |
Token | has |
Token ID | 468 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
urga | +0.612 |
ahi | +0.563 |
rika | +0.546 |
ordinate | +0.538 |
htar | +0.530 |
Neg logit contributions | |
Brief | -0.474 |
Learns | -0.459 |
loose | -0.455 |
Neutral | -0.435 |
consequential | -0.428 |
Token | noted |
Token ID | 4367 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Brief | +0.258 |
loose | +0.250 |
Learns | +0.249 |
Neutral | +0.236 |
camps | +0.234 |
Neg logit contributions | |
urga | -0.336 |
ahi | -0.308 |
rika | -0.300 |
ordinate | -0.295 |
htar | -0.290 |
Token | cohesive |
Token ID | 42403 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
Brief | +0.173 |
Learns | +0.167 |
loose | +0.166 |
Neutral | +0.159 |
consequential | +0.156 |
Neg logit contributions | |
urga | -0.240 |
ahi | -0.222 |
rika | -0.215 |
ordinate | -0.212 |
htar | -0.209 |
Token | record |
Token ID | 1700 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
Brief | +0.242 |
loose | +0.234 |
Learns | +0.234 |
Neutral | +0.223 |
consequential | +0.220 |
Neg logit contributions | |
urga | -0.307 |
ahi | -0.282 |
rika | -0.272 |
ordinate | -0.268 |
htar | -0.265 |
Token | ." |
Token ID | 526 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
Brief | +0.032 |
Learns | +0.031 |
loose | +0.031 |
Neutral | +0.030 |
consequential | +0.029 |
Neg logit contributions | |
urga | -0.041 |
ahi | -0.038 |
rika | -0.037 |
ordinate | -0.036 |
htar | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
urga | +0.063 |
ahi | +0.058 |
rika | +0.056 |
ordinate | +0.055 |
htar | +0.054 |
Neg logit contributions | |
Brief | -0.052 |
Learns | -0.050 |
loose | -0.050 |
Neutral | -0.048 |
consequential | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
urga | +0.304 |
ahi | +0.277 |
rika | +0.267 |
ordinate | +0.262 |
htar | +0.258 |
Neg logit contributions | |
Brief | -0.310 |
Learns | -0.303 |
loose | -0.300 |
Neutral | -0.289 |
consequential | -0.286 |
Token | https |
Token ID | 5450 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
urga | +0.139 |
ahi | +0.127 |
rika | +0.122 |
ordinate | +0.120 |
htar | +0.119 |
Neg logit contributions | |
Brief | -0.122 |
Learns | -0.118 |
loose | -0.117 |
Neutral | -0.113 |
consequential | -0.111 |
Token | :// |
Token ID | 1378 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
Brief | +3.391 |
loose | +3.350 |
Learns | +3.236 |
Neutral | +3.161 |
conom | +3.020 |
Neg logit contributions | |
urga | -5.806 |
ahi | -5.361 |
ordinate | -5.226 |
rika | -5.160 |
htar | -5.104 |
Token | le |
Token ID | 293 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
Brief | +3.690 |
loose | +3.658 |
Learns | +3.527 |
camps | +3.451 |
Neutral | +3.436 |
Neg logit contributions | |
urga | -4.457 |
ahi | -4.042 |
rika | -3.917 |
ordinate | -3.890 |
htar | -3.830 |
Token | high |
Token ID | 8929 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
urga | +0.727 |
ahi | +0.670 |
rika | +0.645 |
ordinate | +0.635 |
htar | +0.628 |
Neg logit contributions | |
Brief | -0.603 |
Learns | -0.586 |
loose | -0.579 |
Neutral | -0.557 |
consequential | -0.549 |
Token | val |
Token ID | 2100 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Brief | +0.636 |
Learns | +0.615 |
loose | +0.613 |
Neutral | +0.580 |
camps | +0.578 |
Neg logit contributions | |
urga | -0.933 |
ahi | -0.869 |
rika | -0.839 |
ordinate | -0.822 |
htar | -0.817 |
Token | ley |
Token ID | 1636 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Brief | +1.471 |
Learns | +1.423 |
loose | +1.416 |
Neutral | +1.352 |
camps | +1.317 |
Neg logit contributions | |
urga | -2.277 |
ahi | -2.100 |
rika | -2.035 |
ordinate | -2.008 |
htar | -1.993 |
Token | of |
Token ID | 286 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
Brief | +0.324 |
Learns | +0.312 |
loose | +0.309 |
Neutral | +0.294 |
consequential | +0.289 |
Neg logit contributions | |
urga | -0.522 |
ahi | -0.486 |
rika | -0.471 |
ordinate | -0.464 |
htar | -0.459 |
Token | Pre |
Token ID | 3771 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
Brief | +0.555 |
Learns | +0.533 |
loose | +0.528 |
Neutral | +0.504 |
consequential | +0.491 |
Neg logit contributions | |
urga | -0.895 |
ahi | -0.830 |
rika | -0.806 |
ordinate | -0.794 |
htar | -0.786 |
Token | y |
Token ID | 88 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
urga | +0.277 |
ahi | +0.245 |
rika | +0.232 |
ordinate | +0.226 |
htar | +0.221 |
Neg logit contributions | |
Brief | -0.471 |
Learns | -0.461 |
loose | -0.458 |
Neutral | -0.445 |
consequential | -0.440 |
Token |
|
Token ID | 198 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
urga | +0.615 |
ahi | +0.567 |
rika | +0.547 |
ordinate | +0.537 |
htar | +0.531 |
Neg logit contributions | |
Brief | -0.516 |
Learns | -0.502 |
loose | -0.496 |
Neutral | -0.476 |
consequential | -0.471 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Brief | +1.574 |
loose | +1.521 |
Learns | +1.499 |
Neutral | +1.459 |
camps | +1.419 |
Neg logit contributions | |
urga | -1.777 |
ahi | -1.622 |
rika | -1.557 |
ordinate | -1.535 |
htar | -1.510 |
Token | https |
Token ID | 5450 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
Brief | +0.797 |
loose | +0.774 |
Learns | +0.770 |
Neutral | +0.741 |
camps | +0.724 |
Neg logit contributions | |
urga | -0.901 |
ahi | -0.823 |
rika | -0.792 |
ordinate | -0.781 |
htar | -0.771 |
Token | :// |
Token ID | 1378 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
Brief | +3.294 |
loose | +3.282 |
Learns | +3.149 |
Neutral | +3.082 |
camps | +2.926 |
Neg logit contributions | |
urga | -5.842 |
ahi | -5.378 |
ordinate | -5.239 |
rika | -5.183 |
htar | -5.104 |
Token | kill |
Token ID | 12728 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
loose | +3.078 |
Brief | +3.075 |
Learns | +3.022 |
camps | +2.857 |
Neutral | +2.848 |
Neg logit contributions | |
urga | -3.818 |
ahi | -3.438 |
rika | -3.308 |
ordinate | -3.279 |
htar | -3.242 |
Token | ert |
Token ID | 861 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
urga | +0.403 |
ahi | +0.368 |
rika | +0.355 |
ordinate | +0.349 |
htar | +0.345 |
Neg logit contributions | |
Brief | -0.367 |
Learns | -0.357 |
loose | -0.355 |
Neutral | -0.340 |
camps | -0.335 |
Token | of |
Token ID | 1659 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
Brief | +1.612 |
loose | +1.573 |
Learns | +1.564 |
Neutral | +1.507 |
camps | +1.498 |
Neg logit contributions | |
urga | -1.425 |
ahi | -1.285 |
rika | -1.234 |
ordinate | -1.204 |
htar | -1.202 |
Token | ure |
Token ID | 495 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
Brief | +0.395 |
loose | +0.384 |
Learns | +0.382 |
Neutral | +0.367 |
camps | +0.364 |
Neg logit contributions | |
urga | -0.346 |
ahi | -0.311 |
rika | -0.298 |
ordinate | -0.293 |
htar | -0.289 |
Token | ce |
Token ID | 344 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Brief | +1.338 |
Learns | +1.290 |
loose | +1.288 |
camps | +1.236 |
Neutral | +1.224 |
Neg logit contributions | |
urga | -1.390 |
ahi | -1.270 |
rika | -1.214 |
ordinate | -1.182 |
htar | -1.170 |
Token | ives |
Token ID | 1083 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Brief | +1.066 |
Learns | +1.024 |
loose | +0.991 |
camps | +0.945 |
conom | +0.941 |
Neg logit contributions | |
urga | -1.837 |
ahi | -1.701 |
rika | -1.656 |
ordinate | -1.626 |
htar | -1.619 |
Token | from |
Token ID | 422 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
urga | +1.193 |
ahi | +1.102 |
rika | +1.065 |
ordinate | +1.048 |
htar | +1.037 |
Neg logit contributions | |
Brief | -0.901 |
Learns | -0.873 |
loose | -0.864 |
Neutral | -0.829 |
consequential | -0.814 |
Token | his |
Token ID | 465 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
urga | +0.752 |
ahi | +0.695 |
rika | +0.673 |
ordinate | +0.662 |
htar | +0.655 |
Neg logit contributions | |
Brief | -0.543 |
Learns | -0.526 |
loose | -0.521 |
Neutral | -0.498 |
consequential | -0.490 |
Token | fel |
Token ID | 10756 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Brief | +0.195 |
Learns | +0.188 |
loose | +0.187 |
Neutral | +0.179 |
consequential | +0.176 |
Neg logit contributions | |
urga | -0.248 |
ahi | -0.228 |
rika | -0.221 |
ordinate | -0.217 |
htar | -0.215 |
Token | |
Token ID | 3907 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
Brief | +0.813 |
loose | +0.794 |
Learns | +0.786 |
camps | +0.749 |
Neutral | +0.746 |
Neg logit contributions | |
urga | -0.882 |
ahi | -0.792 |
rika | -0.768 |
ordinate | -0.756 |
htar | -0.745 |
Token | low |
Token ID | 9319 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Brief | +3.158 |
loose | +3.136 |
Learns | +3.016 |
conom | +2.949 |
camps | +2.888 |
Neg logit contributions | |
urga | -5.600 |
ahi | -5.108 |
SOS | -4.921 |
Ras | -4.904 |
rika | -4.876 |
Token | Demo |
Token ID | 34588 |
Feature activation | -9.99e-02 |
Pos logit contributions | |
Brief | +0.092 |
Learns | +0.089 |
loose | +0.089 |
Neutral | +0.085 |
camps | +0.084 |
Neg logit contributions | |
urga | -0.104 |
ahi | -0.095 |
rika | -0.092 |
ordinate | -0.090 |
htar | -0.089 |
Token | |
Token ID | 3907 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
urga | +0.074 |
ahi | +0.068 |
rika | +0.065 |
ordinate | +0.064 |
htar | +0.063 |
Neg logit contributions | |
Brief | -0.073 |
loose | -0.070 |
Learns | -0.070 |
Neutral | -0.068 |
camps | -0.067 |
Token | cr |
Token ID | 6098 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
Brief | +0.686 |
loose | +0.661 |
Learns | +0.659 |
camps | +0.628 |
Neutral | +0.627 |
Neg logit contributions | |
urga | -0.812 |
ahi | -0.743 |
rika | -0.711 |
ordinate | -0.711 |
htar | -0.695 |
Token | ats |
Token ID | 1381 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
urga | +0.528 |
ahi | +0.470 |
rika | +0.452 |
ordinate | +0.442 |
htar | +0.436 |
Neg logit contributions | |
Brief | -0.701 |
loose | -0.679 |
Learns | -0.678 |
Neutral | -0.659 |
camps | -0.648 |
Token | di |
Token ID | 10989 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
Brief | +2.307 |
loose | +2.259 |
Learns | +2.200 |
camps | +2.128 |
conom | +2.123 |
Neg logit contributions | |
urga | -2.559 |
ahi | -2.306 |
rika | -2.182 |
htar | -2.133 |
ordinate | -2.108 |
Token | |
Token ID | 3907 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
urga | +0.017 |
ahi | +0.015 |
rika | +0.015 |
ordinate | +0.015 |
htar | +0.014 |
Neg logit contributions | |
Brief | -0.017 |
loose | -0.016 |
Learns | -0.016 |
Neutral | -0.015 |
camps | -0.015 |
Token | um |
Token ID | 388 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Brief | +3.370 |
Learns | +3.277 |
loose | +3.277 |
conom | +3.126 |
camps | +3.119 |
Neg logit contributions | |
urga | -2.962 |
ahi | -2.649 |
rika | -2.476 |
ordinate | -2.458 |
htar | -2.411 |
Token | and |
Token ID | 290 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
Brief | +0.083 |
Learns | +0.081 |
loose | +0.080 |
Neutral | +0.077 |
consequential | +0.075 |
Neg logit contributions | |
urga | -0.104 |
ahi | -0.095 |
rika | -0.092 |
ordinate | -0.091 |
htar | -0.090 |
Token | al |
Token ID | 435 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
Brief | +0.522 |
loose | +0.505 |
Learns | +0.503 |
Neutral | +0.477 |
camps | +0.474 |
Neg logit contributions | |
urga | -0.716 |
ahi | -0.657 |
rika | -0.639 |
ordinate | -0.630 |
htar | -0.616 |
Token | |
Token ID | 3907 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
Brief | +0.022 |
Learns | +0.021 |
loose | +0.021 |
Neutral | +0.020 |
camps | +0.020 |
Neg logit contributions | |
urga | -0.022 |
ahi | -0.020 |
rika | -0.019 |
ordinate | -0.019 |
htar | -0.019 |
Token | l |
Token ID | 75 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Brief | +4.162 |
loose | +4.097 |
Learns | +3.937 |
conom | +3.904 |
camps | +3.838 |
Neg logit contributions | |
urga | -4.676 |
ahi | -4.246 |
rika | -4.074 |
Ras | -4.041 |
Sus | -3.984 |
Token | owed |
Token ID | 6972 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Brief | +1.102 |
Learns | +1.073 |
loose | +1.068 |
Neutral | +1.024 |
camps | +1.016 |
Neg logit contributions | |
urga | -1.043 |
ahi | -0.941 |
rika | -0.916 |
ordinate | -0.893 |
htar | -0.887 |
Token | only |
Token ID | 691 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
Brief | +0.718 |
loose | +0.700 |
Learns | +0.692 |
Neutral | +0.659 |
camps | +0.653 |
Neg logit contributions | |
urga | -0.963 |
ahi | -0.883 |
rika | -0.859 |
ordinate | -0.845 |
htar | -0.831 |
Token | a |
Token ID | 257 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
Brief | +0.480 |
loose | +0.467 |
Learns | +0.461 |
Neutral | +0.440 |
camps | +0.435 |
Neg logit contributions | |
urga | -0.627 |
ahi | -0.579 |
rika | -0.559 |
ordinate | -0.554 |
htar | -0.544 |
Token | brief |
Token ID | 4506 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
urga | +0.716 |
ahi | +0.661 |
rika | +0.639 |
ordinate | +0.630 |
htar | +0.623 |
Neg logit contributions | |
Brief | -0.528 |
Learns | -0.511 |
loose | -0.507 |
Neutral | -0.485 |
consequential | -0.477 |
Token | nothing |
Token ID | 2147 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
urga | +1.098 |
ahi | +1.014 |
rika | +0.981 |
ordinate | +0.965 |
htar | +0.954 |
Neg logit contributions | |
Brief | -0.831 |
Learns | -0.807 |
loose | -0.797 |
Neutral | -0.764 |
consequential | -0.752 |
Token | in |
Token ID | 287 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Brief | +1.305 |
loose | +1.263 |
Learns | +1.262 |
Neutral | +1.199 |
consequential | +1.188 |
Neg logit contributions | |
urga | -1.835 |
ahi | -1.694 |
rika | -1.641 |
ordinate | -1.615 |
htar | -1.595 |
Token | their |
Token ID | 511 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
Brief | +0.983 |
loose | +0.946 |
Learns | +0.944 |
Neutral | +0.899 |
consequential | +0.882 |
Neg logit contributions | |
urga | -1.385 |
ahi | -1.277 |
rika | -1.234 |
htar | -1.209 |
ordinate | -1.204 |
Token | writings |
Token ID | 19336 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Brief | +0.501 |
Learns | +0.483 |
loose | +0.482 |
Neutral | +0.458 |
camps | +0.452 |
Neg logit contributions | |
urga | -0.706 |
ahi | -0.651 |
rika | -0.630 |
ordinate | -0.620 |
htar | -0.617 |
Token | to |
Token ID | 284 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
Brief | +1.238 |
loose | +1.202 |
Learns | +1.191 |
Neutral | +1.136 |
consequential | +1.126 |
Neg logit contributions | |
urga | -1.702 |
ahi | -1.568 |
rika | -1.515 |
ordinate | -1.492 |
htar | -1.478 |
Token | warrant |
Token ID | 8084 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
Brief | +1.687 |
loose | +1.648 |
Learns | +1.603 |
Neutral | +1.556 |
camps | +1.530 |
Neg logit contributions | |
urga | -1.969 |
ahi | -1.792 |
rika | -1.722 |
htar | -1.668 |
ordinate | -1.665 |
Token | anything |
Token ID | 1997 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Brief | +3.616 |
loose | +3.535 |
Learns | +3.460 |
consequential | +3.334 |
Neutral | +3.334 |
Neg logit contributions | |
urga | -5.092 |
ahi | -4.662 |
rika | -4.533 |
htar | -4.407 |
ordinate | -4.382 |
Token | approaching |
Token ID | 13885 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Brief | +0.754 |
Learns | +0.728 |
loose | +0.726 |
Neutral | +0.689 |
consequential | +0.680 |
Neg logit contributions | |
urga | -1.199 |
ahi | -1.113 |
rika | -1.082 |
ordinate | -1.064 |
htar | -1.053 |
Token | the |
Token ID | 262 |
Feature activation | +9.97e-02 |
Pos logit contributions | |
Brief | +1.035 |
loose | +1.006 |
Learns | +1.000 |
Neutral | +0.960 |
consequential | +0.947 |
Neg logit contributions | |
urga | -1.383 |
ahi | -1.272 |
rika | -1.232 |
htar | -1.198 |
ordinate | -1.198 |
Token | kind |
Token ID | 1611 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Brief | +0.068 |
loose | +0.065 |
Learns | +0.065 |
Neutral | +0.063 |
consequential | +0.062 |
Neg logit contributions | |
urga | -0.079 |
ahi | -0.073 |
rika | -0.070 |
ordinate | -0.069 |
htar | -0.068 |
Token | of |
Token ID | 286 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
Brief | +0.868 |
loose | +0.836 |
Learns | +0.834 |
Neutral | +0.790 |
consequential | +0.775 |
Neg logit contributions | |
urga | -1.497 |
ahi | -1.388 |
rika | -1.344 |
ordinate | -1.323 |
htar | -1.313 |
Token | T |
Token ID | 51 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Brief | +2.533 |
Learns | +2.440 |
loose | +2.439 |
Neutral | +2.370 |
Proud | +2.295 |
Neg logit contributions | |
urga | -2.494 |
ahi | -2.267 |
rika | -2.141 |
ordinate | -2.134 |
htar | -2.089 |
Token | Pick |
Token ID | 12346 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
urga | +1.036 |
ahi | +0.956 |
rika | +0.930 |
ordinate | +0.910 |
htar | +0.900 |
Neg logit contributions | |
Brief | -0.835 |
Learns | -0.821 |
loose | -0.810 |
consequential | -0.772 |
Neutral | -0.767 |
Token | Stephen |
Token ID | 7970 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
Brief | +0.376 |
Learns | +0.362 |
loose | +0.361 |
Neutral | +0.347 |
consequential | +0.340 |
Neg logit contributions | |
urga | -0.466 |
ahi | -0.428 |
rika | -0.414 |
ordinate | -0.409 |
htar | -0.403 |
Token | East |
Token ID | 3687 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Brief | +1.795 |
Learns | +1.720 |
loose | +1.707 |
Neutral | +1.661 |
camps | +1.610 |
Neg logit contributions | |
urga | -1.959 |
ahi | -1.785 |
rika | -1.722 |
ordinate | -1.716 |
htar | -1.695 |
Token | on |
Token ID | 261 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Brief | +0.139 |
Learns | +0.135 |
loose | +0.133 |
Neutral | +0.129 |
camps | +0.126 |
Neg logit contributions | |
urga | -0.172 |
ahi | -0.158 |
rika | -0.152 |
ordinate | -0.150 |
htar | -0.149 |
Token | PA |
Token ID | 8147 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
Brief | +0.660 |
Learns | +0.635 |
loose | +0.631 |
Neutral | +0.608 |
consequential | +0.593 |
Neg logit contributions | |
urga | -0.865 |
ahi | -0.797 |
rika | -0.775 |
ordinate | -0.761 |
htar | -0.755 |
Token | 1 |
Token ID | 352 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
Brief | +3.144 |
loose | +2.933 |
Learns | +2.922 |
Neutral | +2.841 |
Proud | +2.788 |
Neg logit contributions | |
urga | -5.486 |
ahi | -5.128 |
rika | -4.989 |
ordinate | -4.943 |
htar | -4.942 |
Token | hour |
Token ID | 1711 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Brief | +0.240 |
Learns | +0.229 |
loose | +0.226 |
Neutral | +0.213 |
consequential | +0.208 |
Neg logit contributions | |
urga | -0.528 |
ahi | -0.494 |
rika | -0.481 |
ordinate | -0.475 |
htar | -0.470 |
Token | ago |
Token ID | 2084 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
Brief | +0.847 |
loose | +0.813 |
Learns | +0.812 |
Neutral | +0.774 |
camps | +0.760 |
Neg logit contributions | |
urga | -1.209 |
ahi | -1.116 |
rika | -1.080 |
ordinate | -1.062 |
htar | -1.048 |
Token | I |
Token ID | 314 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
Brief | +0.248 |
Learns | +0.241 |
loose | +0.239 |
Neutral | +0.229 |
consequential | +0.225 |
Neg logit contributions | |
urga | -0.317 |
ahi | -0.293 |
rika | -0.283 |
ordinate | -0.278 |
htar | -0.275 |
Token | think |
Token ID | 892 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Brief | +0.042 |
loose | +0.040 |
Learns | +0.040 |
Neutral | +0.038 |
consequential | +0.038 |
Neg logit contributions | |
urga | -0.059 |
ahi | -0.054 |
rika | -0.053 |
ordinate | -0.052 |
htar | -0.051 |
Token | pull |
Token ID | 2834 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
Brief | +1.056 |
Learns | +1.025 |
loose | +1.019 |
Neutral | +0.978 |
consequential | +0.963 |
Neg logit contributions | |
urga | -1.132 |
ahi | -1.036 |
rika | -0.998 |
ordinate | -0.984 |
htar | -0.973 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
Brief | +0.411 |
loose | +0.398 |
Learns | +0.398 |
Neutral | +0.382 |
camps | +0.377 |
Neg logit contributions | |
urga | -0.394 |
ahi | -0.358 |
rika | -0.343 |
ordinate | -0.338 |
htar | -0.333 |
Token |
|
Token ID | 198 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Brief | +1.420 |
Learns | +1.360 |
loose | +1.345 |
Neutral | +1.295 |
consequential | +1.254 |
Neg logit contributions | |
urga | -1.750 |
ahi | -1.613 |
rika | -1.557 |
ordinate | -1.538 |
htar | -1.521 |
Token |
|
Token ID | 198 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
Brief | +0.778 |
loose | +0.752 |
Learns | +0.750 |
Neutral | +0.723 |
camps | +0.707 |
Neg logit contributions | |
urga | -0.826 |
ahi | -0.755 |
rika | -0.725 |
ordinate | -0.714 |
htar | -0.704 |
Token | http |
Token ID | 4023 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
Brief | +0.341 |
Learns | +0.330 |
loose | +0.328 |
Neutral | +0.315 |
consequential | +0.309 |
Neg logit contributions | |
urga | -0.399 |
ahi | -0.366 |
rika | -0.353 |
ordinate | -0.347 |
htar | -0.344 |
Token | :// |
Token ID | 1378 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
Brief | +2.009 |
loose | +1.942 |
Learns | +1.939 |
Neutral | +1.843 |
camps | +1.789 |
Neg logit contributions | |
urga | -2.972 |
ahi | -2.736 |
rika | -2.646 |
ordinate | -2.632 |
htar | -2.591 |
Token | api |
Token ID | 15042 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
Brief | +4.052 |
Learns | +3.968 |
loose | +3.910 |
conom | +3.794 |
camps | +3.736 |
Neg logit contributions | |
urga | -4.222 |
ahi | -3.871 |
rika | -3.710 |
ordinate | -3.700 |
htar | -3.675 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
urga | +0.535 |
ahi | +0.488 |
rika | +0.470 |
ordinate | +0.461 |
htar | +0.455 |
Neg logit contributions | |
Brief | -0.530 |
Learns | -0.516 |
loose | -0.512 |
Neutral | -0.493 |
consequential | -0.486 |
Token | c |
Token ID | 66 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
Brief | +1.044 |
Learns | +1.018 |
loose | +1.006 |
Neutral | +0.965 |
camps | +0.953 |
Neg logit contributions | |
urga | -1.066 |
ahi | -0.973 |
rika | -0.935 |
ordinate | -0.924 |
htar | -0.916 |
Token | ensus |
Token ID | 7314 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Brief | +0.317 |
Learns | +0.305 |
loose | +0.301 |
Neutral | +0.285 |
consequential | +0.278 |
Neg logit contributions | |
urga | -0.622 |
ahi | -0.582 |
rika | -0.565 |
ordinate | -0.558 |
htar | -0.553 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
urga | +0.240 |
ahi | +0.219 |
rika | +0.211 |
ordinate | +0.207 |
htar | +0.205 |
Neg logit contributions | |
Brief | -0.232 |
Learns | -0.225 |
loose | -0.224 |
Neutral | -0.215 |
consequential | -0.212 |
Token | crisis |
Token ID | 4902 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Brief | +1.091 |
loose | +1.054 |
Learns | +1.050 |
Neutral | +1.006 |
camps | +0.992 |
Neg logit contributions | |
urga | -1.467 |
ahi | -1.353 |
rika | -1.308 |
ordinate | -1.283 |
htar | -1.278 |
Token | of |
Token ID | 286 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Brief | +0.859 |
loose | +0.832 |
Learns | +0.828 |
Neutral | +0.793 |
camps | +0.788 |
Neg logit contributions | |
urga | -1.055 |
ahi | -0.973 |
rika | -0.937 |
ordinate | -0.926 |
htar | -0.917 |
Token | capitalism |
Token ID | 12129 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Brief | +0.691 |
Learns | +0.665 |
loose | +0.664 |
Neutral | +0.633 |
consequential | +0.621 |
Neg logit contributions | |
urga | -1.018 |
ahi | -0.942 |
rika | -0.912 |
ordinate | -0.897 |
htar | -0.890 |
Token | , |
Token ID | 11 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
Brief | +1.327 |
loose | +1.296 |
Learns | +1.271 |
Neutral | +1.231 |
camps | +1.230 |
Neg logit contributions | |
urga | -1.636 |
ahi | -1.511 |
rika | -1.451 |
ordinate | -1.438 |
htar | -1.426 |
Token | with |
Token ID | 351 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
urga | +0.679 |
ahi | +0.626 |
rika | +0.605 |
ordinate | +0.595 |
htar | +0.588 |
Neg logit contributions | |
Brief | -0.533 |
Learns | -0.518 |
loose | -0.511 |
Neutral | -0.490 |
consequential | -0.482 |
Token | mass |
Token ID | 2347 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
Brief | +0.361 |
Learns | +0.347 |
loose | +0.347 |
Neutral | +0.331 |
consequential | +0.325 |
Neg logit contributions | |
urga | -0.540 |
ahi | -0.500 |
rika | -0.484 |
ordinate | -0.477 |
htar | -0.474 |
Token | unemployment |
Token ID | 10681 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
Brief | +3.587 |
loose | +3.535 |
Learns | +3.458 |
camps | +3.387 |
Neutral | +3.361 |
Neg logit contributions | |
urga | -4.864 |
ahi | -4.450 |
htar | -4.260 |
ordinate | -4.247 |
rika | -4.246 |
Token | at |
Token ID | 379 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
Brief | +1.502 |
loose | +1.472 |
Learns | +1.443 |
camps | +1.395 |
consequential | +1.389 |
Neg logit contributions | |
urga | -2.184 |
ahi | -2.014 |
rika | -1.949 |
ordinate | -1.922 |
htar | -1.902 |
Token | home |
Token ID | 1363 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
urga | +0.459 |
ahi | +0.425 |
rika | +0.412 |
ordinate | +0.406 |
htar | +0.401 |
Neg logit contributions | |
Brief | -0.311 |
Learns | -0.301 |
loose | -0.297 |
Neutral | -0.284 |
consequential | -0.279 |
Token | and |
Token ID | 290 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Brief | +0.243 |
Learns | +0.235 |
loose | +0.235 |
Neutral | +0.224 |
consequential | +0.221 |
Neg logit contributions | |
urga | -0.337 |
ahi | -0.312 |
rika | -0.302 |
ordinate | -0.297 |
htar | -0.294 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Brief | +0.619 |
Learns | +0.598 |
loose | +0.598 |
Neutral | +0.567 |
consequential | +0.559 |
Neg logit contributions | |
urga | -0.910 |
ahi | -0.844 |
rika | -0.817 |
ordinate | -0.804 |
htar | -0.797 |
Token | is |
Token ID | 318 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Brief | +1.646 |
Learns | +1.576 |
loose | +1.568 |
Neutral | +1.504 |
camps | +1.475 |
Neg logit contributions | |
urga | -2.494 |
ahi | -2.296 |
rika | -2.231 |
ordinate | -2.214 |
htar | -2.181 |
Token | unsupported |
Token ID | 24222 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
Brief | +0.096 |
Learns | +0.092 |
loose | +0.092 |
Neutral | +0.088 |
consequential | +0.087 |
Neg logit contributions | |
urga | -0.120 |
ahi | -0.110 |
rika | -0.107 |
ordinate | -0.105 |
htar | -0.103 |
Token | on |
Token ID | 319 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Brief | +0.358 |
Learns | +0.347 |
loose | +0.344 |
Neutral | +0.331 |
consequential | +0.325 |
Neg logit contributions | |
urga | -0.417 |
ahi | -0.383 |
rika | -0.369 |
ordinate | -0.363 |
htar | -0.359 |
Token | your |
Token ID | 534 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
Brief | +0.111 |
Learns | +0.107 |
loose | +0.105 |
Neutral | +0.099 |
consequential | +0.097 |
Neg logit contributions | |
urga | -0.220 |
ahi | -0.205 |
rika | -0.200 |
ordinate | -0.197 |
htar | -0.196 |
Token | device |
Token ID | 3335 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
urga | +0.372 |
ahi | +0.334 |
rika | +0.324 |
ordinate | +0.317 |
htar | +0.315 |
Neg logit contributions | |
Brief | -0.379 |
Learns | -0.372 |
loose | -0.361 |
Neutral | -0.347 |
consequential | -0.347 |
Token | Media |
Token ID | 6343 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
Brief | +0.453 |
loose | +0.445 |
Learns | +0.444 |
consequential | +0.414 |
camps | +0.408 |
Neg logit contributions | |
urga | -0.857 |
ahi | -0.803 |
rika | -0.779 |
ordinate | -0.763 |
htar | -0.759 |
Token | caption |
Token ID | 8305 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
Brief | +3.898 |
loose | +3.762 |
Learns | +3.732 |
Neutral | +3.604 |
camps | +3.522 |
Neg logit contributions | |
urga | -4.635 |
ahi | -4.266 |
rika | -4.102 |
ordinate | -4.079 |
htar | -3.957 |
Token | A |
Token ID | 317 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
Brief | +3.335 |
Learns | +3.094 |
Neutral | +3.014 |
loose | +2.990 |
Cable | +2.962 |
Neg logit contributions | |
urga | -3.872 |
ahi | -3.514 |
ordinate | -3.419 |
rika | -3.409 |
htar | -3.325 |
Token | drone |
Token ID | 12170 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Brief | +0.595 |
loose | +0.571 |
Learns | +0.567 |
Neutral | +0.545 |
camps | +0.538 |
Neg logit contributions | |
urga | -0.703 |
ahi | -0.645 |
rika | -0.623 |
ordinate | -0.613 |
htar | -0.602 |
Token | - |
Token ID | 12 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
urga | +0.216 |
ahi | +0.200 |
rika | +0.193 |
ordinate | +0.190 |
htar | +0.188 |
Neg logit contributions | |
Brief | -0.165 |
Learns | -0.160 |
loose | -0.158 |
Neutral | -0.152 |
consequential | -0.149 |
Token | camera |
Token ID | 25695 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
Brief | +0.651 |
loose | +0.634 |
Learns | +0.630 |
Neutral | +0.606 |
consequential | +0.599 |
Neg logit contributions | |
urga | -0.655 |
ahi | -0.594 |
rika | -0.570 |
ordinate | -0.559 |
htar | -0.551 |
Token | record |
Token ID | 1700 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
Brief | +0.242 |
loose | +0.234 |
Learns | +0.234 |
Neutral | +0.223 |
consequential | +0.220 |
Neg logit contributions | |
urga | -0.307 |
ahi | -0.282 |
rika | -0.272 |
ordinate | -0.268 |
htar | -0.265 |
Token | ." |
Token ID | 526 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
Brief | +0.032 |
Learns | +0.031 |
loose | +0.031 |
Neutral | +0.030 |
consequential | +0.029 |
Neg logit contributions | |
urga | -0.041 |
ahi | -0.038 |
rika | -0.037 |
ordinate | -0.036 |
htar | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
urga | +0.063 |
ahi | +0.058 |
rika | +0.056 |
ordinate | +0.055 |
htar | +0.054 |
Neg logit contributions | |
Brief | -0.052 |
Learns | -0.050 |
loose | -0.050 |
Neutral | -0.048 |
consequential | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
urga | +0.304 |
ahi | +0.277 |
rika | +0.267 |
ordinate | +0.262 |
htar | +0.258 |
Neg logit contributions | |
Brief | -0.310 |
Learns | -0.303 |
loose | -0.300 |
Neutral | -0.289 |
consequential | -0.286 |
Token | https |
Token ID | 5450 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
urga | +0.139 |
ahi | +0.127 |
rika | +0.122 |
ordinate | +0.120 |
htar | +0.119 |
Neg logit contributions | |
Brief | -0.122 |
Learns | -0.118 |
loose | -0.117 |
Neutral | -0.113 |
consequential | -0.111 |
Token | :// |
Token ID | 1378 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
Brief | +3.391 |
loose | +3.350 |
Learns | +3.236 |
Neutral | +3.161 |
conom | +3.020 |
Neg logit contributions | |
urga | -5.806 |
ahi | -5.361 |
ordinate | -5.226 |
rika | -5.160 |
htar | -5.104 |
Token | le |
Token ID | 293 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
Brief | +3.690 |
loose | +3.658 |
Learns | +3.527 |
camps | +3.451 |
Neutral | +3.436 |
Neg logit contributions | |
urga | -4.457 |
ahi | -4.042 |
rika | -3.917 |
ordinate | -3.890 |
htar | -3.830 |
Token | high |
Token ID | 8929 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
urga | +0.727 |
ahi | +0.670 |
rika | +0.645 |
ordinate | +0.635 |
htar | +0.628 |
Neg logit contributions | |
Brief | -0.603 |
Learns | -0.586 |
loose | -0.579 |
Neutral | -0.557 |
consequential | -0.549 |
Token | val |
Token ID | 2100 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Brief | +0.636 |
Learns | +0.615 |
loose | +0.613 |
Neutral | +0.580 |
camps | +0.578 |
Neg logit contributions | |
urga | -0.933 |
ahi | -0.869 |
rika | -0.839 |
ordinate | -0.822 |
htar | -0.817 |
Token | ley |
Token ID | 1636 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Brief | +1.471 |
Learns | +1.423 |
loose | +1.416 |
Neutral | +1.352 |
camps | +1.317 |
Neg logit contributions | |
urga | -2.277 |
ahi | -2.100 |
rika | -2.035 |
ordinate | -2.008 |
htar | -1.993 |
Token | under |
Token ID | 4625 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
Brief | +1.064 |
loose | +1.027 |
Learns | +1.023 |
Neutral | +0.985 |
camps | +0.977 |
Neg logit contributions | |
urga | -1.152 |
ahi | -1.050 |
rika | -1.008 |
ordinate | -0.990 |
htar | -0.986 |
Token | director |
Token ID | 3437 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Brief | +0.499 |
Learns | +0.481 |
loose | +0.479 |
Neutral | +0.456 |
consequential | +0.448 |
Neg logit contributions | |
urga | -0.715 |
ahi | -0.663 |
rika | -0.642 |
ordinate | -0.632 |
htar | -0.625 |
Token | only |
Token ID | 691 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
Brief | +0.878 |
Learns | +0.852 |
loose | +0.848 |
Neutral | +0.804 |
camps | +0.789 |
Neg logit contributions | |
urga | -1.405 |
ahi | -1.307 |
rika | -1.266 |
ordinate | -1.250 |
htar | -1.234 |
Token | needs |
Token ID | 2476 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Brief | +0.213 |
Learns | +0.204 |
loose | +0.201 |
Neutral | +0.190 |
consequential | +0.186 |
Neg logit contributions | |
urga | -0.446 |
ahi | -0.417 |
rika | -0.405 |
ordinate | -0.400 |
htar | -0.396 |
Token | his |
Token ID | 465 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Brief | +0.969 |
loose | +0.939 |
Learns | +0.933 |
Neutral | +0.887 |
consequential | +0.872 |
Neg logit contributions | |
urga | -1.289 |
ahi | -1.197 |
rika | -1.157 |
ordinate | -1.139 |
htar | -1.128 |
Token | / |
Token ID | 14 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
Brief | +0.778 |
loose | +0.750 |
Learns | +0.744 |
Neutral | +0.714 |
camps | +0.700 |
Neg logit contributions | |
urga | -1.042 |
ahi | -0.964 |
rika | -0.932 |
ordinate | -0.913 |
htar | -0.909 |
Token | her |
Token ID | 372 |
Feature activation | +5.78e+00 |
Pos logit contributions | |
urga | +0.297 |
ahi | +0.269 |
rika | +0.258 |
ordinate | +0.252 |
htar | +0.249 |
Neg logit contributions | |
Brief | -0.358 |
Learns | -0.349 |
loose | -0.348 |
Neutral | -0.336 |
consequential | -0.331 |
Token | passport |
Token ID | 17981 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Brief | +3.740 |
loose | +3.609 |
Learns | +3.470 |
Neutral | +3.394 |
pockets | +3.355 |
Neg logit contributions | |
urga | -4.666 |
ahi | -4.310 |
rika | -4.168 |
htar | -4.086 |
ordinate | -4.072 |
Token | and |
Token ID | 290 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
Brief | +1.307 |
loose | +1.263 |
Learns | +1.240 |
Neutral | +1.193 |
consequential | +1.172 |
Neg logit contributions | |
urga | -1.727 |
ahi | -1.592 |
rika | -1.541 |
ordinate | -1.524 |
htar | -1.509 |
Token | the |
Token ID | 262 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
urga | +0.037 |
ahi | +0.035 |
rika | +0.033 |
ordinate | +0.033 |
htar | +0.033 |
Neg logit contributions | |
Brief | -0.027 |
Learns | -0.025 |
loose | -0.025 |
Neutral | -0.024 |
consequential | -0.024 |
Token | name |
Token ID | 1438 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
urga | +0.699 |
ahi | +0.646 |
rika | +0.625 |
ordinate | +0.615 |
htar | +0.608 |
Neg logit contributions | |
Brief | -0.517 |
Learns | -0.499 |
loose | -0.496 |
Neutral | -0.474 |
consequential | -0.466 |
Token | of |
Token ID | 286 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
urga | +0.426 |
ahi | +0.395 |
rika | +0.382 |
ordinate | +0.377 |
htar | +0.373 |
Neg logit contributions | |
Brief | -0.280 |
Learns | -0.270 |
loose | -0.268 |
Neutral | -0.255 |
consequential | -0.250 |
Token | , |
Token ID | 11 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Brief | +0.992 |
loose | +0.964 |
Learns | +0.955 |
Neutral | +0.906 |
camps | +0.901 |
Neg logit contributions | |
urga | -1.322 |
ahi | -1.220 |
rika | -1.184 |
ordinate | -1.167 |
htar | -1.148 |
Token | and |
Token ID | 290 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
Brief | +1.018 |
Learns | +0.984 |
loose | +0.979 |
Neutral | +0.934 |
consequential | +0.918 |
Neg logit contributions | |
urga | -1.346 |
ahi | -1.242 |
rika | -1.202 |
ordinate | -1.182 |
htar | -1.170 |
Token | where |
Token ID | 810 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
Brief | +1.521 |
loose | +1.467 |
Learns | +1.465 |
Neutral | +1.388 |
camps | +1.374 |
Neg logit contributions | |
urga | -2.027 |
ahi | -1.869 |
rika | -1.810 |
ordinate | -1.780 |
htar | -1.769 |
Token | they |
Token ID | 484 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
Brief | +0.032 |
Learns | +0.031 |
loose | +0.031 |
Neutral | +0.030 |
consequential | +0.029 |
Neg logit contributions | |
urga | -0.045 |
ahi | -0.042 |
rika | -0.040 |
ordinate | -0.040 |
htar | -0.039 |
Token | might |
Token ID | 1244 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
Brief | +0.324 |
loose | +0.315 |
Learns | +0.313 |
Neutral | +0.298 |
camps | +0.294 |
Neg logit contributions | |
urga | -0.445 |
ahi | -0.411 |
rika | -0.397 |
ordinate | -0.392 |
htar | -0.388 |
Token | fit |
Token ID | 4197 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
Brief | +0.365 |
loose | +0.355 |
Learns | +0.352 |
Neutral | +0.336 |
camps | +0.332 |
Neg logit contributions | |
urga | -0.479 |
ahi | -0.442 |
rika | -0.427 |
ordinate | -0.419 |
htar | -0.414 |
Token | with |
Token ID | 351 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
Brief | +3.159 |
loose | +3.066 |
Learns | +2.999 |
camps | +2.822 |
Neutral | +2.816 |
Neg logit contributions | |
urga | -5.254 |
ahi | -4.851 |
rika | -4.795 |
ordinate | -4.751 |
htar | -4.569 |
Token | the |
Token ID | 262 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
Brief | +0.423 |
loose | +0.406 |
Learns | +0.406 |
Neutral | +0.386 |
camps | +0.378 |
Neg logit contributions | |
urga | -0.629 |
ahi | -0.581 |
rika | -0.565 |
ordinate | -0.554 |
htar | -0.549 |
Token | Canadiens |
Token ID | 33664 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
Brief | +0.311 |
Learns | +0.299 |
loose | +0.298 |
Neutral | +0.283 |
consequential | +0.278 |
Neg logit contributions | |
urga | -0.468 |
ahi | -0.433 |
rika | -0.420 |
ordinate | -0.414 |
htar | -0.409 |
Token | . |
Token ID | 13 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
urga | +0.451 |
ahi | +0.416 |
rika | +0.401 |
ordinate | +0.395 |
htar | +0.390 |
Neg logit contributions | |
Brief | -0.360 |
Learns | -0.349 |
loose | -0.346 |
Neutral | -0.332 |
consequential | -0.326 |
Token |
|
Token ID | 198 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
urga | +0.514 |
ahi | +0.470 |
rika | +0.451 |
ordinate | +0.442 |
htar | +0.437 |
Neg logit contributions | |
Brief | -0.518 |
Learns | -0.507 |
loose | -0.503 |
Neutral | -0.483 |
consequential | -0.480 |
Token | Force |
Token ID | 5221 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
Brief | +0.349 |
Learns | +0.335 |
loose | +0.331 |
Neutral | +0.319 |
camps | +0.311 |
Neg logit contributions | |
urga | -0.479 |
ahi | -0.442 |
rika | -0.427 |
ordinate | -0.422 |
htar | -0.418 |
Token | Base |
Token ID | 7308 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
Brief | +0.026 |
Learns | +0.025 |
loose | +0.025 |
Neutral | +0.024 |
camps | +0.023 |
Neg logit contributions | |
urga | -0.038 |
ahi | -0.035 |
rika | -0.034 |
ordinate | -0.034 |
htar | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Brief | +0.134 |
Learns | +0.128 |
loose | +0.127 |
Neutral | +0.123 |
camps | +0.120 |
Neg logit contributions | |
urga | -0.159 |
ahi | -0.146 |
rika | -0.141 |
ordinate | -0.139 |
htar | -0.138 |
Token | http |
Token ID | 2638 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
Brief | +0.771 |
Learns | +0.739 |
loose | +0.732 |
Neutral | +0.706 |
camps | +0.690 |
Neg logit contributions | |
urga | -0.962 |
ahi | -0.885 |
rika | -0.859 |
ordinate | -0.846 |
htar | -0.841 |
Token | :// |
Token ID | 1378 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
Brief | +1.767 |
loose | +1.698 |
Learns | +1.692 |
Neutral | +1.618 |
camps | +1.564 |
Neg logit contributions | |
urga | -2.591 |
ahi | -2.389 |
rika | -2.312 |
ordinate | -2.306 |
htar | -2.266 |
Token | www |
Token ID | 2503 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
Brief | +3.657 |
Learns | +3.514 |
loose | +3.506 |
camps | +3.384 |
Neutral | +3.345 |
Neg logit contributions | |
urga | -3.981 |
ahi | -3.623 |
rika | -3.522 |
htar | -3.463 |
ordinate | -3.462 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Brief | +3.432 |
loose | +3.321 |
Learns | +3.251 |
Neutral | +3.151 |
camps | +3.087 |
Neg logit contributions | |
urga | -4.764 |
ahi | -4.344 |
ordinate | -4.185 |
rika | -4.171 |
htar | -4.118 |
Token | ed |
Token ID | 276 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Brief | +1.421 |
Learns | +1.380 |
loose | +1.370 |
Neutral | +1.314 |
camps | +1.306 |
Neg logit contributions | |
urga | -1.405 |
ahi | -1.276 |
rika | -1.229 |
ordinate | -1.207 |
htar | -1.200 |
Token | wards |
Token ID | 2017 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Brief | +0.617 |
Learns | +0.594 |
loose | +0.592 |
Neutral | +0.562 |
camps | +0.558 |
Neg logit contributions | |
urga | -0.866 |
ahi | -0.801 |
rika | -0.773 |
ordinate | -0.762 |
htar | -0.760 |
Token | . |
Token ID | 13 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
Brief | +0.991 |
loose | +0.959 |
Learns | +0.954 |
camps | +0.906 |
Neutral | +0.904 |
Neg logit contributions | |
urga | -1.198 |
ahi | -1.097 |
rika | -1.068 |
htar | -1.040 |
ordinate | -1.037 |
Token | af |
Token ID | 1878 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Brief | +2.275 |
loose | +2.177 |
Learns | +2.162 |
camps | +2.065 |
Neutral | +2.060 |
Neg logit contributions | |
urga | -2.623 |
ahi | -2.405 |
rika | -2.313 |
ordinate | -2.279 |
htar | -2.260 |
Token | , |
Token ID | 11 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
Brief | +0.386 |
Learns | +0.373 |
loose | +0.373 |
Neutral | +0.354 |
consequential | +0.350 |
Neg logit contributions | |
urga | -0.518 |
ahi | -0.476 |
rika | -0.462 |
ordinate | -0.455 |
htar | -0.449 |
Token | $ |
Token ID | 720 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
urga | +0.584 |
ahi | +0.540 |
rika | +0.521 |
ordinate | +0.513 |
htar | +0.507 |
Neg logit contributions | |
Brief | -0.451 |
Learns | -0.438 |
loose | -0.432 |
Neutral | -0.416 |
consequential | -0.408 |
Token | 11 |
Token ID | 1157 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
urga | +0.780 |
ahi | +0.706 |
rika | +0.676 |
ordinate | +0.662 |
htar | +0.653 |
Neg logit contributions | |
Brief | -0.918 |
Learns | -0.895 |
loose | -0.889 |
Neutral | -0.859 |
consequential | -0.849 |
Token | . |
Token ID | 13 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
Brief | +0.786 |
Learns | +0.759 |
loose | +0.759 |
Neutral | +0.720 |
camps | +0.716 |
Neg logit contributions | |
urga | -0.933 |
ahi | -0.857 |
rika | -0.827 |
ordinate | -0.818 |
htar | -0.805 |
Token | 30 |
Token ID | 1270 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
urga | +0.491 |
ahi | +0.444 |
rika | +0.426 |
ordinate | +0.418 |
htar | +0.411 |
Neg logit contributions | |
Brief | -0.577 |
Learns | -0.562 |
loose | -0.558 |
Neutral | -0.539 |
consequential | -0.532 |
Token | worth |
Token ID | 2861 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
Brief | +0.565 |
Learns | +0.544 |
loose | +0.542 |
Neutral | +0.515 |
consequential | +0.508 |
Neg logit contributions | |
urga | -0.798 |
ahi | -0.737 |
rika | -0.714 |
ordinate | -0.703 |
htar | -0.695 |
Token | of |
Token ID | 286 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Brief | +2.777 |
loose | +2.702 |
Learns | +2.615 |
camps | +2.481 |
consequential | +2.468 |
Neg logit contributions | |
urga | -5.470 |
ahi | -5.047 |
rika | -4.959 |
ordinate | -4.876 |
htar | -4.806 |
Token | chocolate |
Token ID | 11311 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
urga | +0.134 |
ahi | +0.123 |
rika | +0.119 |
ordinate | +0.117 |
htar | +0.116 |
Neg logit contributions | |
Brief | -0.110 |
Learns | -0.106 |
loose | -0.105 |
Neutral | -0.101 |
consequential | -0.099 |
Token | bars |
Token ID | 9210 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
urga | +1.445 |
ahi | +1.332 |
rika | +1.283 |
ordinate | +1.262 |
htar | +1.248 |
Neg logit contributions | |
Brief | -1.209 |
Learns | -1.175 |
loose | -1.160 |
Neutral | -1.118 |
consequential | -1.100 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
urga | +0.964 |
ahi | +0.891 |
rika | +0.860 |
ordinate | +0.846 |
htar | +0.837 |
Neg logit contributions | |
Brief | -0.748 |
Learns | -0.725 |
loose | -0.716 |
Neutral | -0.688 |
consequential | -0.676 |
Token | a |
Token ID | 257 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
urga | +0.922 |
ahi | +0.853 |
rika | +0.823 |
ordinate | +0.811 |
htar | +0.801 |
Neg logit contributions | |
Brief | -0.702 |
Learns | -0.682 |
loose | -0.672 |
Neutral | -0.647 |
consequential | -0.635 |
Token | behest |
Token ID | 49672 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
Brief | +0.973 |
loose | +0.942 |
Learns | +0.932 |
Neutral | +0.899 |
consequential | +0.885 |
Neg logit contributions | |
urga | -1.192 |
ahi | -1.084 |
rika | -1.054 |
ordinate | -1.037 |
htar | -1.023 |
Token | of |
Token ID | 286 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
Brief | +1.478 |
loose | +1.434 |
Learns | +1.413 |
Neutral | +1.333 |
camps | +1.322 |
Neg logit contributions | |
urga | -2.724 |
ahi | -2.528 |
rika | -2.452 |
ordinate | -2.426 |
htar | -2.388 |
Token | the |
Token ID | 262 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
Brief | +0.447 |
loose | +0.434 |
Learns | +0.432 |
Neutral | +0.412 |
consequential | +0.406 |
Neg logit contributions | |
urga | -0.589 |
ahi | -0.540 |
rika | -0.524 |
ordinate | -0.513 |
htar | -0.508 |
Token | " |
Token ID | 366 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
Brief | +0.338 |
loose | +0.327 |
Learns | +0.327 |
Neutral | +0.314 |
consequential | +0.309 |
Neg logit contributions | |
urga | -0.391 |
ahi | -0.356 |
rika | -0.345 |
ordinate | -0.339 |
htar | -0.334 |
Token | l |
Token ID | 75 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Brief | +0.337 |
loose | +0.326 |
Learns | +0.326 |
Neutral | +0.313 |
consequential | +0.309 |
Neg logit contributions | |
urga | -0.386 |
ahi | -0.353 |
rika | -0.341 |
ordinate | -0.335 |
htar | -0.330 |
Token | ady |
Token ID | 4597 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
Brief | +0.867 |
loose | +0.841 |
Learns | +0.839 |
Neutral | +0.806 |
camps | +0.793 |
Neg logit contributions | |
urga | -0.890 |
ahi | -0.809 |
rika | -0.786 |
ordinate | -0.769 |
htar | -0.757 |
Token | haw |
Token ID | 23185 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
Brief | +3.670 |
loose | +3.645 |
Learns | +3.467 |
camps | +3.446 |
Neutral | +3.395 |
Neg logit contributions | |
urga | -4.701 |
ahi | -4.206 |
rika | -4.095 |
htar | -3.958 |
ordinate | -3.934 |
Token | ks |
Token ID | 591 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
urga | +0.777 |
ahi | +0.730 |
rika | +0.711 |
ordinate | +0.702 |
htar | +0.696 |
Neg logit contributions | |
Brief | -0.315 |
Learns | -0.300 |
loose | -0.296 |
Neutral | -0.277 |
consequential | -0.270 |
Token | " |
Token ID | 1 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Brief | +0.310 |
Learns | +0.299 |
loose | +0.298 |
Neutral | +0.284 |
consequential | +0.279 |
Neg logit contributions | |
urga | -0.442 |
ahi | -0.408 |
rika | -0.396 |
ordinate | -0.389 |
htar | -0.384 |
Token | in |
Token ID | 287 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
Brief | +0.282 |
Learns | +0.272 |
loose | +0.272 |
Neutral | +0.259 |
consequential | +0.255 |
Neg logit contributions | |
urga | -0.374 |
ahi | -0.344 |
rika | -0.334 |
ordinate | -0.327 |
htar | -0.323 |
Token | his |
Token ID | 465 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
urga | +0.390 |
ahi | +0.360 |
rika | +0.348 |
ordinate | +0.342 |
htar | +0.338 |
Neg logit contributions | |
Brief | -0.295 |
Learns | -0.286 |
loose | -0.284 |
Neutral | -0.272 |
consequential | -0.267 |
Token | is |
Token ID | 318 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
Brief | +1.432 |
Learns | +1.374 |
loose | +1.367 |
Neutral | +1.311 |
camps | +1.284 |
Neg logit contributions | |
urga | -2.145 |
ahi | -1.975 |
rika | -1.918 |
ordinate | -1.902 |
htar | -1.875 |
Token | unsupported |
Token ID | 24222 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
Brief | +0.045 |
Learns | +0.044 |
loose | +0.043 |
Neutral | +0.042 |
consequential | +0.041 |
Neg logit contributions | |
urga | -0.056 |
ahi | -0.051 |
rika | -0.050 |
ordinate | -0.049 |
htar | -0.048 |
Token | on |
Token ID | 319 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
Brief | +0.359 |
Learns | +0.348 |
loose | +0.345 |
Neutral | +0.332 |
consequential | +0.326 |
Neg logit contributions | |
urga | -0.417 |
ahi | -0.383 |
rika | -0.369 |
ordinate | -0.364 |
htar | -0.359 |
Token | your |
Token ID | 534 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
urga | +0.058 |
ahi | +0.054 |
rika | +0.053 |
ordinate | +0.052 |
htar | +0.052 |
Neg logit contributions | |
Brief | -0.030 |
Learns | -0.029 |
loose | -0.028 |
Neutral | -0.027 |
consequential | -0.026 |
Token | device |
Token ID | 3335 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
urga | +0.890 |
ahi | +0.795 |
rika | +0.774 |
ordinate | +0.752 |
htar | +0.751 |
Neg logit contributions | |
Brief | -0.942 |
Learns | -0.929 |
loose | -0.894 |
consequential | -0.864 |
conom | -0.861 |
Token | Media |
Token ID | 6343 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
Brief | +0.344 |
loose | +0.338 |
Learns | +0.338 |
consequential | +0.315 |
camps | +0.312 |
Neg logit contributions | |
urga | -0.640 |
ahi | -0.600 |
rika | -0.581 |
ordinate | -0.569 |
htar | -0.566 |
Token | caption |
Token ID | 8305 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
Brief | +3.824 |
loose | +3.691 |
Learns | +3.660 |
Neutral | +3.536 |
camps | +3.454 |
Neg logit contributions | |
urga | -4.499 |
ahi | -4.137 |
rika | -3.978 |
ordinate | -3.954 |
htar | -3.844 |
Token | Nigel |
Token ID | 28772 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Brief | +3.163 |
Learns | +2.943 |
Neutral | +2.858 |
loose | +2.847 |
Cable | +2.808 |
Neg logit contributions | |
urga | -3.664 |
ahi | -3.330 |
ordinate | -3.236 |
rika | -3.229 |
htar | -3.148 |
Token | Farage |
Token ID | 33904 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
urga | +0.158 |
ahi | +0.144 |
rika | +0.138 |
ordinate | +0.136 |
htar | +0.134 |
Neg logit contributions | |
Brief | -0.158 |
Learns | -0.153 |
loose | -0.151 |
Neutral | -0.146 |
camps | -0.144 |
Token | : |
Token ID | 25 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Brief | +1.095 |
Learns | +1.054 |
loose | +1.049 |
camps | +0.995 |
Neutral | +0.993 |
Neg logit contributions | |
urga | -1.428 |
ahi | -1.308 |
rika | -1.267 |
ordinate | -1.252 |
htar | -1.229 |
Token | " |
Token ID | 366 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
Brief | +0.162 |
Learns | +0.156 |
loose | +0.155 |
Neutral | +0.150 |
consequential | +0.146 |
Neg logit contributions | |
urga | -0.190 |
ahi | -0.175 |
rika | -0.169 |
ordinate | -0.166 |
htar | -0.164 |
Token | went |
Token ID | 1816 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
Brief | +1.226 |
loose | +1.211 |
Learns | +1.177 |
camps | +1.137 |
Neutral | +1.128 |
Neg logit contributions | |
urga | -1.827 |
ahi | -1.687 |
rika | -1.650 |
ordinate | -1.611 |
htar | -1.598 |
Token | back |
Token ID | 736 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
urga | +0.298 |
ahi | +0.275 |
rika | +0.266 |
ordinate | +0.261 |
htar | +0.259 |
Neg logit contributions | |
Brief | -0.231 |
Learns | -0.224 |
loose | -0.222 |
Neutral | -0.213 |
consequential | -0.209 |
Token | and |
Token ID | 290 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
urga | +1.363 |
ahi | +1.258 |
rika | +1.214 |
ordinate | +1.197 |
htar | +1.182 |
Neg logit contributions | |
Brief | -1.047 |
Learns | -1.016 |
loose | -1.004 |
Neutral | -0.964 |
consequential | -0.948 |
Token | forth |
Token ID | 6071 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
Brief | +0.424 |
loose | +0.412 |
Learns | +0.411 |
Neutral | +0.391 |
consequential | +0.385 |
Neg logit contributions | |
urga | -0.585 |
ahi | -0.541 |
rika | -0.526 |
ordinate | -0.514 |
htar | -0.509 |
Token | , |
Token ID | 11 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
Brief | +2.052 |
loose | +2.027 |
Learns | +1.953 |
Neutral | +1.882 |
camps | +1.877 |
Neg logit contributions | |
urga | -2.904 |
ahi | -2.662 |
rika | -2.587 |
ordinate | -2.525 |
htar | -2.505 |
Token | trading |
Token ID | 7313 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
Brief | +1.801 |
loose | +1.757 |
Learns | +1.715 |
Neutral | +1.656 |
camps | +1.634 |
Neg logit contributions | |
urga | -2.585 |
ahi | -2.385 |
rika | -2.326 |
ordinate | -2.266 |
htar | -2.261 |
Token | four |
Token ID | 1440 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
loose | +3.932 |
Brief | +3.787 |
camps | +3.652 |
Learns | +3.626 |
pockets | +3.547 |
Neg logit contributions | |
urga | -4.425 |
ahi | -4.049 |
rika | -3.946 |
htar | -3.797 |
Sus | -3.767 |
Token | quarters |
Token ID | 13620 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
Brief | +0.792 |
loose | +0.785 |
Learns | +0.768 |
Neutral | +0.744 |
camps | +0.736 |
Neg logit contributions | |
urga | -0.914 |
ahi | -0.839 |
rika | -0.809 |
ordinate | -0.791 |
htar | -0.788 |
Token | of |
Token ID | 286 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
urga | +0.700 |
ahi | +0.648 |
rika | +0.626 |
ordinate | +0.617 |
htar | +0.610 |
Neg logit contributions | |
Brief | -0.498 |
Learns | -0.483 |
loose | -0.476 |
Neutral | -0.457 |
consequential | -0.448 |
Token | blows |
Token ID | 20385 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
Brief | +0.759 |
loose | +0.744 |
Learns | +0.736 |
Neutral | +0.708 |
camps | +0.698 |
Neg logit contributions | |
urga | -0.914 |
ahi | -0.843 |
rika | -0.813 |
ordinate | -0.793 |
htar | -0.792 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Brief | +0.461 |
loose | +0.446 |
Learns | +0.445 |
Neutral | +0.424 |
consequential | +0.418 |
Neg logit contributions | |
urga | -0.587 |
ahi | -0.540 |
rika | -0.523 |
ordinate | -0.514 |
htar | -0.507 |
Token | finance |
Token ID | 9604 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Brief | +0.214 |
loose | +0.208 |
Learns | +0.207 |
Neutral | +0.198 |
consequential | +0.195 |
Neg logit contributions | |
urga | -0.284 |
ahi | -0.261 |
rika | -0.253 |
ordinate | -0.249 |
htar | -0.246 |
Token | and |
Token ID | 290 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Brief | +0.074 |
Learns | +0.071 |
loose | +0.071 |
Neutral | +0.068 |
camps | +0.067 |
Neg logit contributions | |
urga | -0.097 |
ahi | -0.089 |
rika | -0.086 |
ordinate | -0.085 |
htar | -0.084 |
Token | ro |
Token ID | 686 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Brief | +0.296 |
loose | +0.287 |
Learns | +0.286 |
Neutral | +0.272 |
consequential | +0.269 |
Neg logit contributions | |
urga | -0.410 |
ahi | -0.378 |
rika | -0.366 |
ordinate | -0.360 |
htar | -0.356 |
Token | iled |
Token ID | 3902 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
Brief | +0.120 |
loose | +0.117 |
Learns | +0.117 |
Neutral | +0.112 |
camps | +0.111 |
Neg logit contributions | |
urga | -0.106 |
ahi | -0.095 |
rika | -0.091 |
ordinate | -0.090 |
htar | -0.089 |
Token | by |
Token ID | 416 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Brief | +0.353 |
loose | +0.343 |
Learns | +0.341 |
Neutral | +0.325 |
consequential | +0.321 |
Neg logit contributions | |
urga | -0.469 |
ahi | -0.434 |
rika | -0.420 |
ordinate | -0.412 |
htar | -0.408 |
Token | mass |
Token ID | 2347 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
Brief | +0.790 |
loose | +0.771 |
Learns | +0.758 |
Neutral | +0.723 |
consequential | +0.718 |
Neg logit contributions | |
urga | -1.143 |
ahi | -1.052 |
rika | -1.021 |
ordinate | -1.001 |
htar | -0.995 |
Token | street |
Token ID | 4675 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
Brief | +3.232 |
loose | +3.232 |
Learns | +3.047 |
camps | +3.014 |
Neutral | +2.976 |
Neg logit contributions | |
urga | -4.980 |
ahi | -4.553 |
rika | -4.430 |
ordinate | -4.378 |
htar | -4.355 |
Token | protests |
Token ID | 8536 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
Brief | +1.436 |
loose | +1.395 |
Learns | +1.379 |
camps | +1.303 |
Neutral | +1.301 |
Neg logit contributions | |
urga | -2.651 |
ahi | -2.491 |
rika | -2.393 |
ordinate | -2.356 |
htar | -2.349 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
urga | +0.045 |
ahi | +0.042 |
rika | +0.040 |
ordinate | +0.040 |
htar | +0.039 |
Neg logit contributions | |
Brief | -0.037 |
loose | -0.035 |
Learns | -0.035 |
Neutral | -0.034 |
consequential | -0.033 |
Token | These |
Token ID | 2312 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
urga | +0.104 |
ahi | +0.096 |
rika | +0.093 |
ordinate | +0.091 |
htar | +0.090 |
Neg logit contributions | |
Brief | -0.087 |
Learns | -0.084 |
loose | -0.083 |
Neutral | -0.081 |
consequential | -0.078 |
Token | were |
Token ID | 547 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
Brief | +0.252 |
Learns | +0.244 |
loose | +0.241 |
Neutral | +0.231 |
consequential | +0.227 |
Neg logit contributions | |
urga | -0.354 |
ahi | -0.328 |
rika | -0.317 |
ordinate | -0.313 |
htar | -0.309 |
Token | . |
Token ID | 13 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
Brief | +2.172 |
loose | +2.115 |
Learns | +2.094 |
Neutral | +2.008 |
camps | +1.969 |
Neg logit contributions | |
urga | -2.732 |
ahi | -2.509 |
rika | -2.389 |
ordinate | -2.383 |
htar | -2.346 |
Token | youtube |
Token ID | 11604 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
urga | +0.403 |
ahi | +0.369 |
rika | +0.354 |
ordinate | +0.348 |
htar | +0.343 |
Neg logit contributions | |
Brief | -0.385 |
Learns | -0.374 |
loose | -0.372 |
Neutral | -0.357 |
consequential | -0.352 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Brief | +1.598 |
loose | +1.547 |
Learns | +1.541 |
Neutral | +1.481 |
camps | +1.448 |
Neg logit contributions | |
urga | -1.851 |
ahi | -1.690 |
rika | -1.625 |
ordinate | -1.606 |
htar | -1.584 |
Token | com |
Token ID | 785 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
urga | +0.851 |
ahi | +0.774 |
rika | +0.743 |
ordinate | +0.726 |
htar | +0.716 |
Neg logit contributions | |
Brief | -0.968 |
Learns | -0.946 |
loose | -0.937 |
Neutral | -0.907 |
consequential | -0.900 |
Token | / |
Token ID | 14 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
urga | +0.123 |
ahi | +0.112 |
rika | +0.108 |
ordinate | +0.106 |
htar | +0.105 |
Neg logit contributions | |
Brief | -0.123 |
Learns | -0.119 |
loose | -0.118 |
Neutral | -0.114 |
consequential | -0.113 |
Token | watch |
Token ID | 8340 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
urga | +3.243 |
ahi | +2.997 |
rika | +2.895 |
ordinate | +2.874 |
htar | +2.834 |
Neg logit contributions | |
Brief | -2.815 |
Learns | -2.761 |
loose | -2.719 |
consequential | -2.619 |
Neutral | -2.600 |
Token | ? |
Token ID | 30 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Brief | +3.031 |
loose | +2.900 |
Learns | +2.845 |
Neutral | +2.743 |
camps | +2.628 |
Neg logit contributions | |
urga | -5.076 |
ahi | -4.703 |
rika | -4.524 |
ordinate | -4.482 |
htar | -4.372 |
Token | v |
Token ID | 85 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
urga | +0.164 |
ahi | +0.150 |
rika | +0.145 |
ordinate | +0.143 |
htar | +0.141 |
Neg logit contributions | |
Brief | -0.141 |
Learns | -0.137 |
loose | -0.136 |
Neutral | -0.130 |
consequential | -0.128 |
Token | = |
Token ID | 28 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
urga | +1.129 |
ahi | +1.039 |
rika | +1.001 |
ordinate | +0.982 |
htar | +0.979 |
Neg logit contributions | |
Brief | -0.898 |
Learns | -0.871 |
loose | -0.859 |
Neutral | -0.828 |
consequential | -0.820 |
Token | 2 |
Token ID | 17 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
Brief | +1.478 |
loose | +1.435 |
Learns | +1.430 |
Neutral | +1.385 |
camps | +1.361 |
Neg logit contributions | |
urga | -1.415 |
ahi | -1.278 |
rika | -1.229 |
ordinate | -1.226 |
htar | -1.198 |
Token | g |
Token ID | 70 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
urga | +0.341 |
ahi | +0.310 |
rika | +0.298 |
ordinate | +0.293 |
htar | +0.289 |
Neg logit contributions | |
Brief | -0.355 |
Learns | -0.344 |
loose | -0.343 |
Neutral | -0.331 |
consequential | -0.325 |
Token | wrote |
Token ID | 2630 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
urga | +1.136 |
ahi | +1.043 |
rika | +1.006 |
ordinate | +0.987 |
htar | +0.976 |
Neg logit contributions | |
Brief | -1.012 |
Learns | -0.984 |
loose | -0.976 |
Neutral | -0.938 |
consequential | -0.925 |
Token | : |
Token ID | 25 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
Brief | +0.222 |
Learns | +0.215 |
loose | +0.214 |
Neutral | +0.206 |
camps | +0.202 |
Neg logit contributions | |
urga | -0.237 |
ahi | -0.216 |
rika | -0.208 |
ordinate | -0.205 |
htar | -0.202 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
urga | +0.348 |
ahi | +0.318 |
rika | +0.305 |
ordinate | +0.300 |
htar | +0.296 |
Neg logit contributions | |
Brief | -0.351 |
Learns | -0.341 |
loose | -0.339 |
Neutral | -0.326 |
consequential | -0.322 |
Token |
|
Token ID | 198 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
urga | +1.039 |
ahi | +0.949 |
rika | +0.912 |
ordinate | +0.893 |
htar | +0.883 |
Neg logit contributions | |
Brief | -1.129 |
Learns | -1.110 |
loose | -1.091 |
Neutral | -1.053 |
consequential | -1.053 |
Token | Show |
Token ID | 15307 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
urga | +1.624 |
ahi | +1.504 |
rika | +1.455 |
ordinate | +1.433 |
htar | +1.420 |
Neg logit contributions | |
Brief | -1.158 |
Learns | -1.124 |
loose | -1.111 |
Neutral | -1.062 |
consequential | -1.044 |
Token | nested |
Token ID | 28376 |
Feature activation | -7.12e+00 |
Pos logit contributions | |
urga | +1.844 |
ahi | +1.699 |
rika | +1.637 |
ordinate | +1.606 |
htar | +1.597 |
Neg logit contributions | |
Brief | -1.600 |
Learns | -1.559 |
loose | -1.539 |
Neutral | -1.480 |
consequential | -1.462 |
Token | quote |
Token ID | 9577 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
urga | +4.583 |
ahi | +4.247 |
rika | +4.055 |
htar | +3.996 |
ordinate | +3.872 |
Neg logit contributions | |
Learns | -5.574 |
Brief | -5.455 |
loose | -5.336 |
conom | -5.275 |
Neutral | -5.182 |
Token | + |
Token ID | 1343 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
urga | +3.592 |
ahi | +3.267 |
rika | +3.179 |
htar | +3.120 |
ordinate | +3.083 |
Neg logit contributions | |
Brief | -3.176 |
Learns | -3.159 |
loose | -3.050 |
Neutral | -2.958 |
consequential | -2.937 |
Token |
|
Token ID | 198 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
urga | +2.189 |
ahi | +2.017 |
rika | +1.918 |
htar | +1.856 |
ordinate | +1.844 |
Neg logit contributions | |
Brief | -2.673 |
Learns | -2.657 |
loose | -2.628 |
consequential | -2.575 |
camps | -2.527 |
Token |
|
Token ID | 198 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
urga | +1.516 |
ahi | +1.382 |
rika | +1.330 |
ordinate | +1.303 |
htar | +1.284 |
Neg logit contributions | |
Brief | -1.725 |
Learns | -1.711 |
loose | -1.670 |
consequential | -1.621 |
Neutral | -1.610 |
Token | On |
Token ID | 2202 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
urga | +1.956 |
ahi | +1.781 |
rika | +1.708 |
ordinate | +1.684 |
htar | +1.658 |
Neg logit contributions | |
Brief | -2.080 |
Learns | -2.047 |
loose | -2.020 |
Neutral | -1.942 |
consequential | -1.919 |
Token | " |
Token ID | 366 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
Brief | +0.218 |
Learns | +0.209 |
loose | +0.204 |
Neutral | +0.197 |
camps | +0.190 |
Neg logit contributions | |
urga | -0.342 |
ahi | -0.317 |
rika | -0.307 |
ordinate | -0.305 |
htar | -0.299 |
Token | Like |
Token ID | 7594 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
urga | +0.594 |
ahi | +0.544 |
rika | +0.524 |
ordinate | +0.517 |
htar | +0.508 |
Neg logit contributions | |
Brief | -0.535 |
Learns | -0.517 |
loose | -0.514 |
Neutral | -0.494 |
camps | -0.485 |
Token | " |
Token ID | 1 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
urga | +1.493 |
ahi | +1.376 |
rika | +1.328 |
ordinate | +1.307 |
htar | +1.292 |
Neg logit contributions | |
Brief | -1.201 |
Learns | -1.165 |
loose | -1.154 |
Neutral | -1.107 |
consequential | -1.090 |
Token | Mam |
Token ID | 29926 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
urga | +0.859 |
ahi | +0.789 |
rika | +0.760 |
ordinate | +0.748 |
htar | +0.742 |
Neg logit contributions | |
Brief | -0.716 |
Learns | -0.691 |
loose | -0.688 |
Neutral | -0.659 |
camps | -0.647 |
Token | ás |
Token ID | 40138 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Brief | +2.275 |
Learns | +2.204 |
loose | +2.173 |
Neutral | +2.111 |
camps | +2.080 |
Neg logit contributions | |
urga | -2.060 |
ahi | -1.830 |
ordinate | -1.780 |
rika | -1.750 |
htar | -1.715 |
Token | Latin |
Token ID | 49022 |
Feature activation | -6.72e+00 |
Pos logit contributions | |
Brief | +1.303 |
Learns | +1.255 |
loose | +1.254 |
Neutral | +1.196 |
camps | +1.179 |
Neg logit contributions | |
urga | -1.439 |
ahi | -1.316 |
ordinate | -1.263 |
rika | -1.260 |
htar | -1.234 |
Token | as |
Token ID | 292 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
urga | +5.009 |
ahi | +4.635 |
rika | +4.496 |
ordinate | +4.310 |
isy | +4.296 |
Neg logit contributions | |
Brief | -4.637 |
Learns | -4.564 |
loose | -4.544 |
Neutral | -4.357 |
consequential | -4.351 |
Token | on |
Token ID | 319 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
urga | +0.813 |
ahi | +0.744 |
rika | +0.716 |
ordinate | +0.706 |
htar | +0.697 |
Neg logit contributions | |
Brief | -0.731 |
Learns | -0.708 |
loose | -0.704 |
Neutral | -0.675 |
camps | -0.666 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
urga | +0.137 |
ahi | +0.126 |
rika | +0.122 |
ordinate | +0.121 |
htar | +0.120 |
Neg logit contributions | |
Brief | -0.100 |
Learns | -0.096 |
loose | -0.096 |
Neutral | -0.091 |
camps | -0.090 |
Token | ! |
Token ID | 0 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
urga | +2.221 |
ahi | +2.050 |
rika | +1.974 |
ordinate | +1.939 |
htar | +1.920 |
Neg logit contributions | |
Brief | -1.858 |
Learns | -1.806 |
loose | -1.790 |
Neutral | -1.721 |
consequential | -1.704 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
urga | +0.963 |
ahi | +0.884 |
rika | +0.853 |
ordinate | +0.840 |
htar | +0.827 |
Neg logit contributions | |
Brief | -0.846 |
Learns | -0.821 |
loose | -0.811 |
Neutral | -0.782 |
consequential | -0.766 |
Token | References |
Token ID | 31458 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
urga | +0.896 |
ahi | +0.824 |
rika | +0.793 |
ordinate | +0.780 |
htar | +0.768 |
Neg logit contributions | |
Brief | -0.794 |
Learns | -0.775 |
loose | -0.767 |
Neutral | -0.737 |
consequential | -0.726 |
Token | : |
Token ID | 25 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
urga | +0.050 |
ahi | +0.046 |
rika | +0.044 |
ordinate | +0.043 |
htar | +0.043 |
Neg logit contributions | |
Brief | -0.046 |
Learns | -0.045 |
loose | -0.044 |
Neutral | -0.043 |
consequential | -0.042 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
urga | +1.013 |
ahi | +0.929 |
rika | +0.892 |
ordinate | +0.875 |
htar | +0.865 |
Neg logit contributions | |
Brief | -0.946 |
Learns | -0.922 |
loose | -0.916 |
Neutral | -0.879 |
consequential | -0.869 |
Token | It |
Token ID | 1026 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Brief | +0.403 |
Learns | +0.390 |
loose | +0.389 |
Neutral | +0.373 |
consequential | +0.367 |
Neg logit contributions | |
urga | -0.449 |
ahi | -0.411 |
rika | -0.395 |
ordinate | -0.389 |
htar | -0.384 |
Token | took |
Token ID | 1718 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
urga | +1.882 |
ahi | +1.749 |
rika | +1.687 |
ordinate | +1.653 |
htar | +1.646 |
Neg logit contributions | |
Brief | -1.335 |
Learns | -1.293 |
loose | -1.278 |
Neutral | -1.227 |
consequential | -1.211 |
Token | until |
Token ID | 1566 |
Feature activation | -6.37e+00 |
Pos logit contributions | |
Brief | +0.201 |
loose | +0.193 |
Learns | +0.193 |
Neutral | +0.184 |
consequential | +0.181 |
Neg logit contributions | |
urga | -0.278 |
ahi | -0.256 |
rika | -0.248 |
ordinate | -0.244 |
htar | -0.242 |
Token | Sunday |
Token ID | 3502 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
urga | +4.800 |
ahi | +4.468 |
ordinate | +4.275 |
rika | +4.219 |
Ras | +4.199 |
Neg logit contributions | |
Learns | -4.134 |
Brief | -4.123 |
loose | -3.954 |
conom | -3.845 |
Neutral | -3.838 |
Token | morning |
Token ID | 3329 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
urga | +0.898 |
ahi | +0.828 |
rika | +0.799 |
ordinate | +0.785 |
htar | +0.778 |
Neg logit contributions | |
Brief | -0.711 |
Learns | -0.693 |
loose | -0.683 |
Neutral | -0.656 |
consequential | -0.647 |
Token | for |
Token ID | 329 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
urga | +0.561 |
ahi | +0.518 |
rika | +0.501 |
ordinate | +0.493 |
htar | +0.487 |
Neg logit contributions | |
Brief | -0.427 |
Learns | -0.414 |
loose | -0.410 |
Neutral | -0.393 |
consequential | -0.386 |
Token | a |
Token ID | 257 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
urga | +0.888 |
ahi | +0.821 |
rika | +0.794 |
ordinate | +0.782 |
htar | +0.773 |
Neg logit contributions | |
Brief | -0.646 |
Learns | -0.626 |
loose | -0.620 |
Neutral | -0.593 |
consequential | -0.583 |
Token | CT |
Token ID | 16356 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
urga | +0.506 |
ahi | +0.468 |
rika | +0.452 |
ordinate | +0.445 |
htar | +0.440 |
Neg logit contributions | |
Brief | -0.376 |
Learns | -0.365 |
loose | -0.361 |
Neutral | -0.346 |
consequential | -0.340 |
Token | ... |
Token ID | 2644 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Brief | +2.291 |
loose | +2.240 |
Learns | +2.192 |
Neutral | +2.111 |
camps | +2.044 |
Neg logit contributions | |
urga | -3.151 |
ahi | -2.884 |
rika | -2.825 |
ordinate | -2.714 |
htar | -2.708 |
Token | prev |
Token ID | 8654 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
urga | +0.322 |
ahi | +0.297 |
rika | +0.288 |
ordinate | +0.283 |
htar | +0.280 |
Neg logit contributions | |
Brief | -0.232 |
Learns | -0.225 |
loose | -0.223 |
Neutral | -0.213 |
consequential | -0.209 |
Token | _ |
Token ID | 62 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
urga | +0.656 |
ahi | +0.577 |
rika | +0.545 |
ordinate | +0.530 |
htar | +0.520 |
Neg logit contributions | |
Brief | -1.169 |
Learns | -1.144 |
loose | -1.137 |
Neutral | -1.105 |
consequential | -1.093 |
Token | state |
Token ID | 5219 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
urga | +0.855 |
ahi | +0.786 |
rika | +0.758 |
ordinate | +0.745 |
htar | +0.737 |
Neg logit contributions | |
Brief | -0.724 |
Learns | -0.703 |
loose | -0.698 |
Neutral | -0.670 |
consequential | -0.659 |
Token | : |
Token ID | 1058 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
urga | +1.747 |
ahi | +1.602 |
rika | +1.539 |
ordinate | +1.516 |
htar | +1.494 |
Neg logit contributions | |
Brief | -1.624 |
Learns | -1.583 |
loose | -1.563 |
Neutral | -1.506 |
consequential | -1.491 |
Token | Option |
Token ID | 16018 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
urga | +1.254 |
ahi | +1.161 |
rika | +1.115 |
ordinate | +1.102 |
htar | +1.086 |
Neg logit contributions | |
Brief | -1.028 |
Learns | -1.001 |
loose | -0.991 |
Neutral | -0.949 |
consequential | -0.939 |
Token | < |
Token ID | 1279 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
urga | +4.281 |
ahi | +3.982 |
ordinate | +3.761 |
rika | +3.709 |
isy | +3.674 |
Neg logit contributions | |
Brief | -4.352 |
Learns | -4.283 |
loose | -4.169 |
Neutral | -4.067 |
consequential | -4.037 |
Token | Arc |
Token ID | 10173 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Brief | +0.178 |
Learns | +0.171 |
loose | +0.169 |
Neutral | +0.162 |
consequential | +0.157 |
Neg logit contributions | |
urga | -0.286 |
ahi | -0.264 |
rika | -0.258 |
ordinate | -0.253 |
htar | -0.252 |
Token | < |
Token ID | 1279 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
urga | +1.233 |
ahi | +1.144 |
rika | +1.103 |
ordinate | +1.090 |
htar | +1.073 |
Neg logit contributions | |
Brief | -0.909 |
Learns | -0.883 |
loose | -0.875 |
Neutral | -0.835 |
consequential | -0.825 |
Token | Board |
Token ID | 5926 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
Brief | +0.703 |
Learns | +0.677 |
loose | +0.671 |
Neutral | +0.646 |
consequential | +0.625 |
Neg logit contributions | |
urga | -0.940 |
ahi | -0.857 |
rika | -0.837 |
ordinate | -0.818 |
htar | -0.815 |
Token | >> |
Token ID | 9609 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
urga | +2.100 |
ahi | +1.942 |
rika | +1.878 |
ordinate | +1.852 |
htar | +1.819 |
Neg logit contributions | |
Brief | -1.602 |
Learns | -1.555 |
loose | -1.541 |
Neutral | -1.472 |
consequential | -1.463 |
Token | ? |
Token ID | 30 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
Brief | +0.267 |
loose | +0.257 |
Learns | +0.256 |
Neutral | +0.246 |
camps | +0.242 |
Neg logit contributions | |
urga | -0.352 |
ahi | -0.326 |
rika | -0.313 |
ordinate | -0.310 |
htar | -0.306 |
Token | prev |
Token ID | 8654 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Brief | +0.052 |
Learns | +0.051 |
loose | +0.050 |
Neutral | +0.048 |
consequential | +0.047 |
Neg logit contributions | |
urga | -0.071 |
ahi | -0.066 |
rika | -0.064 |
ordinate | -0.063 |
htar | -0.062 |
Token | _ |
Token ID | 62 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Brief | +1.549 |
Learns | +1.510 |
loose | +1.506 |
Neutral | +1.455 |
camps | +1.438 |
Neg logit contributions | |
urga | -1.159 |
ahi | -1.037 |
rika | -0.989 |
ordinate | -0.971 |
htar | -0.961 |
Token | state |
Token ID | 5219 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
urga | +0.354 |
ahi | +0.330 |
rika | +0.321 |
ordinate | +0.316 |
htar | +0.314 |
Neg logit contributions | |
Brief | -0.176 |
Learns | -0.169 |
loose | -0.168 |
Neutral | -0.158 |
consequential | -0.154 |
Token | : |
Token ID | 1058 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
urga | +1.636 |
ahi | +1.500 |
rika | +1.442 |
ordinate | +1.418 |
htar | +1.398 |
Neg logit contributions | |
Brief | -1.505 |
Learns | -1.466 |
loose | -1.450 |
Neutral | -1.397 |
consequential | -1.381 |
Token | Option |
Token ID | 16018 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
urga | +1.293 |
ahi | +1.207 |
rika | +1.162 |
ordinate | +1.151 |
htar | +1.139 |
Neg logit contributions | |
Brief | -0.837 |
Learns | -0.817 |
loose | -0.801 |
Neutral | -0.764 |
consequential | -0.757 |
Token | < |
Token ID | 1279 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
urga | +4.536 |
ahi | +4.270 |
ordinate | +4.018 |
rika | +3.993 |
htar | +3.953 |
Neg logit contributions | |
Brief | -4.075 |
Learns | -4.027 |
loose | -3.931 |
Neutral | -3.793 |
consequential | -3.771 |
Token | Board |
Token ID | 5926 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
urga | +0.213 |
ahi | +0.197 |
rika | +0.191 |
ordinate | +0.188 |
htar | +0.186 |
Neg logit contributions | |
Brief | -0.145 |
Learns | -0.139 |
loose | -0.138 |
Neutral | -0.132 |
consequential | -0.129 |
Token | > |
Token ID | 1875 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
urga | +0.912 |
ahi | +0.844 |
rika | +0.816 |
ordinate | +0.804 |
htar | +0.795 |
Neg logit contributions | |
Brief | -0.654 |
Learns | -0.633 |
loose | -0.627 |
Neutral | -0.599 |
consequential | -0.589 |
Token | , |
Token ID | 837 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
urga | +0.664 |
ahi | +0.606 |
rika | +0.584 |
ordinate | +0.572 |
htar | +0.565 |
Neg logit contributions | |
Brief | -0.656 |
Learns | -0.637 |
loose | -0.633 |
Neutral | -0.609 |
consequential | -0.599 |
Token | // |
Token ID | 3373 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
urga | +1.701 |
ahi | +1.578 |
rika | +1.522 |
ordinate | +1.506 |
htar | +1.489 |
Neg logit contributions | |
Brief | -1.145 |
Learns | -1.113 |
loose | -1.093 |
Neutral | -1.046 |
consequential | -1.031 |
Token | / |
Token ID | 14 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
urga | +0.043 |
ahi | +0.039 |
rika | +0.037 |
ordinate | +0.037 |
htar | +0.036 |
Neg logit contributions | |
Brief | -0.041 |
Learns | -0.040 |
loose | -0.040 |
Neutral | -0.038 |
consequential | -0.038 |
Token | O |
Token ID | 46 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
urga | +1.667 |
ahi | +1.521 |
rika | +1.460 |
ordinate | +1.429 |
htar | +1.412 |
Neg logit contributions | |
Brief | -1.753 |
Learns | -1.710 |
loose | -1.693 |
Neutral | -1.633 |
consequential | -1.614 |
Token | JV |
Token ID | 41697 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
urga | +1.365 |
ahi | +1.245 |
rika | +1.197 |
ordinate | +1.172 |
htar | +1.158 |
Neg logit contributions | |
Brief | -1.405 |
Learns | -1.369 |
loose | -1.356 |
Neutral | -1.309 |
consequential | -1.292 |
Token | L |
Token ID | 43 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
urga | +2.596 |
ahi | +2.382 |
rika | +2.281 |
ordinate | +2.219 |
htar | +2.205 |
Neg logit contributions | |
Brief | -2.686 |
Learns | -2.622 |
loose | -2.590 |
Neutral | -2.498 |
consequential | -2.480 |
Token | F |
Token ID | 37 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
urga | +1.598 |
ahi | +1.461 |
rika | +1.403 |
ordinate | +1.371 |
htar | +1.357 |
Neg logit contributions | |
Brief | -1.636 |
Learns | -1.595 |
loose | -1.579 |
Neutral | -1.523 |
consequential | -1.505 |
Token | Re |
Token ID | 3041 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
urga | +1.749 |
ahi | +1.600 |
rika | +1.538 |
ordinate | +1.502 |
htar | +1.486 |
Neg logit contributions | |
Brief | -1.779 |
Learns | -1.736 |
loose | -1.717 |
Neutral | -1.656 |
consequential | -1.638 |
Token | K |
Token ID | 42 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
urga | +4.320 |
ahi | +3.984 |
rika | +3.823 |
ordinate | +3.693 |
htar | +3.671 |
Neg logit contributions | |
Brief | -4.456 |
Learns | -4.360 |
loose | -4.284 |
Neutral | -4.135 |
consequential | -4.130 |
Token | ch |
Token ID | 354 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
urga | +1.732 |
ahi | +1.584 |
rika | +1.520 |
ordinate | +1.485 |
htar | +1.472 |
Neg logit contributions | |
Brief | -1.776 |
Learns | -1.731 |
loose | -1.714 |
Neutral | -1.652 |
consequential | -1.634 |
Token | — |
Token ID | 851 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
urga | +1.559 |
ahi | +1.428 |
rika | +1.370 |
ordinate | +1.342 |
htar | +1.330 |
Neg logit contributions | |
Brief | -1.538 |
Learns | -1.499 |
loose | -1.485 |
Neutral | -1.429 |
consequential | -1.414 |
Token | Dr |
Token ID | 1583 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
Brief | +1.588 |
Learns | +1.516 |
loose | +1.515 |
Neutral | +1.476 |
camps | +1.434 |
Neg logit contributions | |
urga | -1.794 |
ahi | -1.650 |
rika | -1.591 |
ordinate | -1.588 |
htar | -1.561 |
Token | . |
Token ID | 13 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
urga | +1.909 |
ahi | +1.746 |
rika | +1.681 |
ordinate | +1.649 |
htar | +1.629 |
Neg logit contributions | |
Brief | -1.825 |
Learns | -1.776 |
loose | -1.762 |
Neutral | -1.696 |
consequential | -1.673 |
Token | and |
Token ID | 290 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
urga | +1.328 |
ahi | +1.229 |
rika | +1.190 |
ordinate | +1.171 |
htar | +1.163 |
Neg logit contributions | |
Brief | -0.936 |
Learns | -0.906 |
loose | -0.895 |
Neutral | -0.854 |
consequential | -0.844 |
Token | could |
Token ID | 714 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
urga | +0.572 |
ahi | +0.528 |
rika | +0.510 |
ordinate | +0.502 |
htar | +0.496 |
Neg logit contributions | |
Brief | -0.433 |
Learns | -0.420 |
loose | -0.416 |
Neutral | -0.399 |
consequential | -0.392 |
Token | upset |
Token ID | 9247 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
Brief | +0.822 |
loose | +0.810 |
Learns | +0.793 |
Neutral | +0.764 |
camps | +0.754 |
Neg logit contributions | |
urga | -1.045 |
ahi | -0.965 |
rika | -0.929 |
ordinate | -0.905 |
htar | -0.888 |
Token | Na |
Token ID | 11013 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
urga | +0.047 |
ahi | +0.044 |
rika | +0.042 |
ordinate | +0.041 |
htar | +0.041 |
Neg logit contributions | |
Brief | -0.037 |
Learns | -0.036 |
loose | -0.036 |
Neutral | -0.035 |
consequential | -0.034 |
Token | ` |
Token ID | 63 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
urga | +2.145 |
ahi | +1.974 |
rika | +1.890 |
ordinate | +1.842 |
htar | +1.821 |
Neg logit contributions | |
Brief | -2.473 |
Learns | -2.413 |
loose | -2.375 |
Neutral | -2.299 |
consequential | -2.275 |
Token | Vi |
Token ID | 38432 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
urga | +0.779 |
ahi | +0.591 |
rika | +0.523 |
ordinate | +0.515 |
htar | +0.462 |
Neg logit contributions | |
Brief | -3.067 |
loose | -3.002 |
Learns | -3.000 |
Neutral | -2.931 |
camps | -2.906 |
Token | in |
Token ID | 287 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
urga | +4.664 |
ahi | +4.288 |
rika | +4.128 |
ordinate | +4.082 |
htar | +4.080 |
Neg logit contributions | |
Brief | -3.891 |
Learns | -3.824 |
loose | -3.699 |
Neutral | -3.553 |
consequential | -3.538 |
Token | some |
Token ID | 617 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
urga | +1.321 |
ahi | +1.222 |
rika | +1.183 |
ordinate | +1.171 |
htar | +1.154 |
Neg logit contributions | |
Brief | -0.936 |
Learns | -0.909 |
loose | -0.895 |
Neutral | -0.856 |
consequential | -0.842 |
Token | universe |
Token ID | 6881 |
Feature activation | +9.62e-02 |
Pos logit contributions | |
urga | +1.274 |
ahi | +1.168 |
rika | +1.131 |
ordinate | +1.122 |
htar | +1.102 |
Neg logit contributions | |
Brief | -1.010 |
Learns | -0.982 |
loose | -0.963 |
Neutral | -0.929 |
consequential | -0.910 |
Token | , |
Token ID | 11 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
Brief | +0.062 |
Learns | +0.060 |
loose | +0.060 |
Neutral | +0.057 |
consequential | +0.057 |
Neg logit contributions | |
urga | -0.079 |
ahi | -0.073 |
rika | -0.071 |
ordinate | -0.069 |
htar | -0.068 |
Token | but |
Token ID | 475 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
urga | +0.705 |
ahi | +0.657 |
rika | +0.637 |
ordinate | +0.629 |
htar | +0.624 |
Neg logit contributions | |
Brief | -0.404 |
Learns | -0.390 |
loose | -0.384 |
Neutral | -0.365 |
consequential | -0.358 |
Token |
|
Token ID | 198 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
urga | +1.167 |
ahi | +1.065 |
rika | +1.020 |
ordinate | +1.016 |
htar | +0.993 |
Neg logit contributions | |
Brief | -1.100 |
Learns | -1.056 |
loose | -1.052 |
Neutral | -1.019 |
camps | -0.990 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
urga | +0.488 |
ahi | +0.445 |
rika | +0.428 |
ordinate | +0.421 |
htar | +0.415 |
Neg logit contributions | |
Brief | -0.482 |
Learns | -0.467 |
loose | -0.465 |
Neutral | -0.448 |
consequential | -0.440 |
Token | S |
Token ID | 50 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
urga | +1.375 |
ahi | +1.256 |
rika | +1.206 |
ordinate | +1.191 |
htar | +1.171 |
Neg logit contributions | |
Brief | -1.354 |
Learns | -1.312 |
loose | -1.305 |
Neutral | -1.257 |
consequential | -1.237 |
Token | ally |
Token ID | 453 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
urga | +1.057 |
ahi | +0.966 |
rika | +0.930 |
ordinate | +0.915 |
htar | +0.902 |
Neg logit contributions | |
Brief | -1.027 |
Learns | -0.998 |
loose | -0.991 |
Neutral | -0.954 |
consequential | -0.940 |
Token | Potter |
Token ID | 14179 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
urga | +1.713 |
ahi | +1.578 |
rika | +1.522 |
ordinate | +1.493 |
htar | +1.479 |
Neg logit contributions | |
Brief | -1.425 |
Learns | -1.385 |
loose | -1.376 |
Neutral | -1.318 |
consequential | -1.302 |
Token | et |
Token ID | 2123 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
urga | +0.870 |
ahi | +0.802 |
rika | +0.777 |
ordinate | +0.766 |
htar | +0.756 |
Neg logit contributions | |
Brief | -0.665 |
Learns | -0.644 |
loose | -0.638 |
Neutral | -0.610 |
consequential | -0.599 |
Token | al |
Token ID | 435 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
urga | +4.114 |
ahi | +3.779 |
rika | +3.693 |
htar | +3.536 |
ordinate | +3.501 |
Neg logit contributions | |
Brief | -4.248 |
Learns | -4.228 |
loose | -4.024 |
Neutral | -4.006 |
conom | -3.936 |
Token | . |
Token ID | 13 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
urga | +2.779 |
ahi | +2.521 |
rika | +2.418 |
ordinate | +2.367 |
htar | +2.328 |
Neg logit contributions | |
Brief | -2.995 |
Learns | -2.947 |
loose | -2.904 |
Neutral | -2.816 |
consequential | -2.783 |
Token | 2014 |
Token ID | 1946 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
urga | +2.548 |
ahi | +2.345 |
rika | +2.255 |
ordinate | +2.208 |
htar | +2.181 |
Neg logit contributions | |
Brief | -2.264 |
Learns | -2.221 |
loose | -2.213 |
consequential | -2.117 |
Neutral | -2.105 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
urga | +3.004 |
ahi | +2.739 |
rika | +2.646 |
ordinate | +2.557 |
htar | +2.519 |
Neg logit contributions | |
Brief | -3.188 |
Learns | -3.157 |
loose | -3.127 |
consequential | -3.001 |
camps | -2.992 |
Token | Tax |
Token ID | 9241 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
urga | +1.649 |
ahi | +1.525 |
rika | +1.474 |
ordinate | +1.445 |
htar | +1.430 |
Neg logit contributions | |
Brief | -1.261 |
Learns | -1.228 |
loose | -1.227 |
consequential | -1.163 |
Neutral | -1.163 |
Token | . |
Token ID | 13 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
Brief | +1.800 |
loose | +1.749 |
Learns | +1.728 |
Neutral | +1.674 |
camps | +1.626 |
Neg logit contributions | |
urga | -2.188 |
ahi | -1.993 |
rika | -1.914 |
ordinate | -1.894 |
htar | -1.870 |
Token | com |
Token ID | 785 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
urga | +0.558 |
ahi | +0.507 |
rika | +0.486 |
ordinate | +0.478 |
htar | +0.471 |
Neg logit contributions | |
Brief | -0.593 |
Learns | -0.576 |
loose | -0.573 |
Neutral | -0.552 |
camps | -0.542 |
Token | / |
Token ID | 14 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
urga | +0.034 |
ahi | +0.031 |
rika | +0.030 |
ordinate | +0.029 |
htar | +0.029 |
Neg logit contributions | |
Brief | -0.032 |
Learns | -0.031 |
loose | -0.031 |
Neutral | -0.030 |
consequential | -0.030 |
Token | CS |
Token ID | 7902 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
urga | +1.525 |
ahi | +1.390 |
rika | +1.334 |
ordinate | +1.307 |
htar | +1.291 |
Neg logit contributions | |
Brief | -1.606 |
Learns | -1.566 |
loose | -1.551 |
Neutral | -1.497 |
consequential | -1.478 |
Token | 3 |
Token ID | 18 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
urga | +1.509 |
ahi | +1.378 |
rika | +1.324 |
ordinate | +1.297 |
htar | +1.281 |
Neg logit contributions | |
Brief | -1.542 |
Learns | -1.502 |
loose | -1.488 |
Neutral | -1.435 |
consequential | -1.418 |
Token | IV |
Token ID | 3824 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
urga | +2.558 |
ahi | +2.345 |
rika | +2.251 |
ordinate | +2.193 |
htar | +2.171 |
Neg logit contributions | |
Brief | -2.642 |
Learns | -2.582 |
loose | -2.542 |
Neutral | -2.454 |
consequential | -2.437 |
Token | IP |
Token ID | 4061 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
urga | +4.164 |
ahi | +3.845 |
rika | +3.672 |
ordinate | +3.549 |
htar | +3.537 |
Neg logit contributions | |
Brief | -4.339 |
Learns | -4.249 |
loose | -4.164 |
Neutral | -4.026 |
consequential | -4.023 |
Token | 9 |
Token ID | 24 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
urga | +2.351 |
ahi | +2.153 |
rika | +2.064 |
ordinate | +2.012 |
htar | +1.994 |
Neg logit contributions | |
Brief | -2.452 |
Learns | -2.395 |
loose | -2.364 |
Neutral | -2.282 |
consequential | -2.264 |
Token | ib |
Token ID | 571 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
urga | +2.260 |
ahi | +2.069 |
rika | +1.985 |
ordinate | +1.936 |
htar | +1.917 |
Neg logit contributions | |
Brief | -2.352 |
Learns | -2.296 |
loose | -2.266 |
Neutral | -2.187 |
consequential | -2.169 |
Token | - |
Token ID | 532 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
urga | +3.886 |
ahi | +3.620 |
rika | +3.456 |
htar | +3.398 |
ordinate | +3.388 |
Neg logit contributions | |
Brief | -3.118 |
Learns | -3.050 |
loose | -2.997 |
consequential | -2.858 |
Neutral | -2.839 |
Token | Kirk |
Token ID | 13855 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Brief | +0.235 |
Learns | +0.225 |
loose | +0.225 |
Neutral | +0.216 |
camps | +0.212 |
Neg logit contributions | |
urga | -0.292 |
ahi | -0.268 |
rika | -0.260 |
ordinate | -0.256 |
htar | -0.254 |
Token | irmation |
Token ID | 36241 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
Brief | +0.153 |
Learns | +0.148 |
loose | +0.148 |
Neutral | +0.142 |
consequential | +0.140 |
Neg logit contributions | |
urga | -0.143 |
ahi | -0.130 |
rika | -0.124 |
ordinate | -0.121 |
htar | -0.120 |
Token | . |
Token ID | 13 |
Feature activation | +8.71e-02 |
Pos logit contributions | |
Brief | +0.528 |
Learns | +0.509 |
loose | +0.504 |
Neutral | +0.489 |
camps | +0.478 |
Neg logit contributions | |
urga | -0.584 |
ahi | -0.536 |
rika | -0.515 |
ordinate | -0.510 |
htar | -0.502 |
Token | The |
Token ID | 383 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
Brief | +0.058 |
Learns | +0.056 |
loose | +0.055 |
Neutral | +0.054 |
consequential | +0.052 |
Neg logit contributions | |
urga | -0.070 |
ahi | -0.065 |
rika | -0.062 |
ordinate | -0.061 |
htar | -0.061 |
Token | Holy |
Token ID | 7439 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
urga | +0.741 |
ahi | +0.682 |
rika | +0.658 |
ordinate | +0.647 |
htar | +0.640 |
Neg logit contributions | |
Brief | -0.602 |
Learns | -0.581 |
loose | -0.576 |
Neutral | -0.554 |
consequential | -0.543 |
Token | E |
Token ID | 412 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
urga | +1.224 |
ahi | +1.129 |
rika | +1.087 |
ordinate | +1.069 |
htar | +1.059 |
Neg logit contributions | |
Brief | -1.018 |
Learns | -0.984 |
loose | -0.969 |
Neutral | -0.940 |
consequential | -0.914 |
Token | uch |
Token ID | 794 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
urga | +1.223 |
ahi | +1.105 |
rika | +1.066 |
ordinate | +1.044 |
htar | +1.028 |
Neg logit contributions | |
Brief | -1.323 |
Learns | -1.296 |
loose | -1.283 |
Neutral | -1.237 |
consequential | -1.223 |
Token | arist |
Token ID | 34566 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
urga | +5.358 |
ahi | +4.971 |
rika | +4.910 |
ordinate | +4.781 |
isy | +4.683 |
Neg logit contributions | |
Brief | -3.125 |
Learns | -3.057 |
loose | -3.034 |
consequential | -2.837 |
Neutral | -2.808 |
Token | . |
Token ID | 13 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
urga | +1.084 |
ahi | +0.990 |
rika | +0.953 |
ordinate | +0.934 |
htar | +0.922 |
Neg logit contributions | |
Brief | -1.078 |
Learns | -1.052 |
loose | -1.044 |
Neutral | -1.004 |
consequential | -0.991 |
Token | Pen |
Token ID | 7507 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
urga | +0.529 |
ahi | +0.486 |
rika | +0.468 |
ordinate | +0.461 |
htar | +0.456 |
Neg logit contributions | |
Brief | -0.455 |
Learns | -0.441 |
loose | -0.435 |
Neutral | -0.421 |
consequential | -0.411 |
Token | ance |
Token ID | 590 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
urga | +0.778 |
ahi | +0.715 |
rika | +0.689 |
ordinate | +0.678 |
htar | +0.670 |
Neg logit contributions | |
Brief | -0.670 |
Learns | -0.650 |
loose | -0.645 |
Neutral | -0.619 |
consequential | -0.610 |
Token | . |
Token ID | 13 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
urga | +1.395 |
ahi | +1.271 |
rika | +1.225 |
ordinate | +1.200 |
htar | +1.184 |
Neg logit contributions | |
Brief | -1.388 |
Learns | -1.357 |
loose | -1.348 |
Neutral | -1.292 |
consequential | -1.282 |
Token | ade |
Token ID | 671 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Brief | +0.455 |
Learns | +0.444 |
loose | +0.439 |
Neutral | +0.423 |
consequential | +0.418 |
Neg logit contributions | |
urga | -0.452 |
ahi | -0.412 |
rika | -0.397 |
ordinate | -0.389 |
htar | -0.384 |
Token | h |
Token ID | 71 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
urga | +1.025 |
ahi | +0.919 |
rika | +0.877 |
ordinate | +0.856 |
htar | +0.844 |
Neg logit contributions | |
Brief | -1.396 |
Learns | -1.365 |
loose | -1.354 |
Neutral | -1.313 |
consequential | -1.297 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
urga | +1.772 |
ahi | +1.636 |
rika | +1.575 |
ordinate | +1.540 |
htar | +1.528 |
Neg logit contributions | |
Brief | -1.441 |
Learns | -1.402 |
loose | -1.385 |
Neutral | -1.333 |
consequential | -1.313 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
urga | +1.144 |
ahi | +1.048 |
rika | +1.009 |
ordinate | +0.993 |
htar | +0.979 |
Neg logit contributions | |
Brief | -1.055 |
Learns | -1.025 |
loose | -1.016 |
Neutral | -0.978 |
consequential | -0.962 |
Token | NEW |
Token ID | 13965 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
Brief | +0.462 |
Learns | +0.446 |
loose | +0.445 |
Neutral | +0.428 |
consequential | +0.421 |
Neg logit contributions | |
urga | -0.514 |
ahi | -0.471 |
rika | -0.453 |
ordinate | -0.446 |
htar | -0.440 |
Token | DEL |
Token ID | 28163 |
Feature activation | -5.78e+00 |
Pos logit contributions | |
Brief | +0.323 |
Learns | +0.311 |
loose | +0.311 |
Neutral | +0.295 |
camps | +0.290 |
Neg logit contributions | |
urga | -0.426 |
ahi | -0.394 |
rika | -0.378 |
ordinate | -0.374 |
htar | -0.370 |
Token | HI |
Token ID | 25374 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
urga | +3.826 |
ahi | +3.518 |
rika | +3.306 |
ordinate | +3.230 |
htar | +3.170 |
Neg logit contributions | |
Brief | -4.533 |
Learns | -4.486 |
loose | -4.449 |
consequential | -4.328 |
Neutral | -4.261 |
Token | : |
Token ID | 25 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
urga | +1.995 |
ahi | +1.816 |
rika | +1.746 |
ordinate | +1.711 |
htar | +1.684 |
Neg logit contributions | |
Brief | -2.013 |
Learns | -1.967 |
loose | -1.956 |
Neutral | -1.876 |
consequential | -1.865 |
Token | In |
Token ID | 554 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
urga | +1.909 |
ahi | +1.753 |
rika | +1.691 |
ordinate | +1.660 |
htar | +1.643 |
Neg logit contributions | |
Brief | -1.578 |
Learns | -1.541 |
loose | -1.535 |
consequential | -1.458 |
Neutral | -1.458 |
Token | a |
Token ID | 257 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
urga | +0.227 |
ahi | +0.210 |
rika | +0.203 |
ordinate | +0.199 |
htar | +0.197 |
Neg logit contributions | |
Brief | -0.169 |
Learns | -0.162 |
loose | -0.162 |
Neutral | -0.154 |
consequential | -0.152 |
Token | setback |
Token ID | 34116 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
urga | +1.072 |
ahi | +0.993 |
rika | +0.959 |
ordinate | +0.946 |
htar | +0.934 |
Neg logit contributions | |
Brief | -0.776 |
Learns | -0.760 |
loose | -0.741 |
Neutral | -0.713 |
consequential | -0.698 |
Token | -- |
Token ID | 438 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
urga | +2.547 |
ahi | +2.352 |
rika | +2.260 |
ordinate | +2.208 |
htar | +2.173 |
Neg logit contributions | |
Brief | -2.289 |
Learns | -2.225 |
loose | -2.204 |
Neutral | -2.105 |
consequential | -2.095 |
Token | images |
Token ID | 17566 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
urga | +0.262 |
ahi | +0.238 |
rika | +0.229 |
ordinate | +0.224 |
htar | +0.221 |
Neg logit contributions | |
Brief | -0.283 |
Learns | -0.276 |
loose | -0.274 |
Neutral | -0.264 |
consequential | -0.261 |
Token | ", |
Token ID | 1600 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
urga | +0.382 |
ahi | +0.353 |
rika | +0.340 |
ordinate | +0.336 |
htar | +0.330 |
Neg logit contributions | |
Brief | -0.291 |
Learns | -0.282 |
loose | -0.279 |
Neutral | -0.267 |
consequential | -0.263 |
Token | required |
Token ID | 2672 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
urga | +2.049 |
ahi | +1.890 |
rika | +1.817 |
ordinate | +1.790 |
htar | +1.757 |
Neg logit contributions | |
Brief | -1.863 |
Learns | -1.813 |
loose | -1.792 |
Neutral | -1.721 |
consequential | -1.704 |
Token | = |
Token ID | 28 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
urga | +2.921 |
ahi | +2.679 |
rika | +2.596 |
ordinate | +2.555 |
htar | +2.497 |
Neg logit contributions | |
Brief | -2.532 |
Learns | -2.483 |
loose | -2.452 |
Neutral | -2.355 |
consequential | -2.319 |
Token | True |
Token ID | 17821 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
urga | +2.611 |
ahi | +2.434 |
rika | +2.362 |
ordinate | +2.329 |
htar | +2.287 |
Neg logit contributions | |
Brief | -1.760 |
Learns | -1.697 |
loose | -1.673 |
Neutral | -1.591 |
consequential | -1.576 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
urga | +4.123 |
ahi | +3.781 |
rika | +3.621 |
isy | +3.524 |
ordinate | +3.524 |
Neg logit contributions | |
Brief | -4.056 |
Learns | -3.993 |
loose | -3.924 |
Neutral | -3.788 |
consequential | -3.737 |
Token | help |
Token ID | 1037 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
urga | +1.474 |
ahi | +1.366 |
rika | +1.316 |
ordinate | +1.297 |
htar | +1.277 |
Neg logit contributions | |
Brief | -1.186 |
Learns | -1.156 |
loose | -1.136 |
Neutral | -1.095 |
consequential | -1.074 |
Token | =" |
Token ID | 2625 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
urga | +2.333 |
ahi | +2.154 |
rika | +2.085 |
ordinate | +2.041 |
htar | +2.021 |
Neg logit contributions | |
Brief | -1.985 |
Learns | -1.942 |
loose | -1.919 |
Neutral | -1.845 |
consequential | -1.814 |
Token | path |
Token ID | 6978 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
urga | +0.566 |
ahi | +0.519 |
rika | +0.501 |
ordinate | +0.492 |
htar | +0.486 |
Neg logit contributions | |
Brief | -0.507 |
Learns | -0.492 |
loose | -0.489 |
Neutral | -0.470 |
consequential | -0.463 |
Token | to |
Token ID | 284 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
urga | +0.682 |
ahi | +0.628 |
rika | +0.607 |
ordinate | +0.597 |
htar | +0.591 |
Neg logit contributions | |
Brief | -0.547 |
Learns | -0.530 |
loose | -0.526 |
Neutral | -0.504 |
consequential | -0.496 |
Token | ., |
Token ID | 1539 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
urga | +1.985 |
ahi | +1.797 |
rika | +1.726 |
ordinate | +1.682 |
htar | +1.658 |
Neg logit contributions | |
Brief | -2.314 |
Learns | -2.270 |
loose | -2.249 |
Neutral | -2.167 |
consequential | -2.144 |
Token | Al |
Token ID | 978 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
urga | +2.540 |
ahi | +2.348 |
rika | +2.265 |
ordinate | +2.206 |
htar | +2.191 |
Neg logit contributions | |
Brief | -2.013 |
loose | -1.975 |
Learns | -1.972 |
consequential | -1.882 |
Neutral | -1.861 |
Token | lee |
Token ID | 7197 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
urga | +0.854 |
ahi | +0.780 |
rika | +0.752 |
ordinate | +0.740 |
htar | +0.729 |
Neg logit contributions | |
Brief | -0.819 |
Learns | -0.795 |
loose | -0.789 |
Neutral | -0.760 |
consequential | -0.748 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Brief | +0.988 |
Learns | +0.941 |
loose | +0.931 |
Neutral | +0.907 |
camps | +0.884 |
Neg logit contributions | |
urga | -1.213 |
ahi | -1.104 |
rika | -1.073 |
ordinate | -1.068 |
htar | -1.045 |
Token | W |
Token ID | 370 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
urga | +1.150 |
ahi | +1.046 |
rika | +1.003 |
ordinate | +0.981 |
htar | +0.968 |
Neg logit contributions | |
Brief | -1.290 |
Learns | -1.259 |
loose | -1.251 |
Neutral | -1.205 |
consequential | -1.194 |
Token | . |
Token ID | 13 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
urga | +2.560 |
ahi | +2.332 |
rika | +2.241 |
ordinate | +2.164 |
htar | +2.145 |
Neg logit contributions | |
Brief | -2.924 |
Learns | -2.876 |
loose | -2.852 |
Neutral | -2.737 |
consequential | -2.714 |
Token | C |
Token ID | 327 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
urga | +3.556 |
ahi | +3.274 |
rika | +3.123 |
Ras | +3.051 |
ordinate | +3.002 |
Neg logit contributions | |
loose | -4.339 |
Brief | -4.326 |
Learns | -4.258 |
consequential | -4.214 |
camps | -4.117 |
Token | . |
Token ID | 13 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
urga | +1.253 |
ahi | +1.120 |
rika | +1.066 |
ordinate | +1.037 |
htar | +1.020 |
Neg logit contributions | |
Brief | -1.824 |
Learns | -1.789 |
loose | -1.776 |
Neutral | -1.719 |
consequential | -1.702 |
Token | ( |
Token ID | 357 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
urga | +2.642 |
ahi | +2.422 |
rika | +2.328 |
ordinate | +2.261 |
htar | +2.229 |
Neg logit contributions | |
Brief | -2.790 |
loose | -2.773 |
Learns | -2.753 |
consequential | -2.655 |
camps | -2.615 |
Token | 1934 |
Token ID | 29300 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
urga | +1.655 |
ahi | +1.520 |
rika | +1.466 |
ordinate | +1.439 |
htar | +1.414 |
Neg logit contributions | |
Brief | -1.526 |
Learns | -1.499 |
loose | -1.480 |
Neutral | -1.418 |
consequential | -1.413 |
Token | ). |
Token ID | 6739 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
urga | +3.461 |
ahi | +3.153 |
rika | +3.046 |
ordinate | +2.950 |
htar | +2.931 |
Neg logit contributions | |
Brief | -3.099 |
Learns | -3.092 |
loose | -3.040 |
consequential | -2.912 |
Neutral | -2.899 |
Token | m |
Token ID | 76 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
urga | +0.372 |
ahi | +0.340 |
rika | +0.327 |
ordinate | +0.321 |
htar | +0.317 |
Neg logit contributions | |
Brief | -0.369 |
Learns | -0.359 |
loose | -0.356 |
Neutral | -0.343 |
consequential | -0.338 |
Token | oves |
Token ID | 5241 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
urga | +1.734 |
ahi | +1.617 |
rika | +1.576 |
ordinate | +1.557 |
htar | +1.536 |
Neg logit contributions | |
Brief | -0.863 |
Learns | -0.823 |
loose | -0.806 |
Neutral | -0.767 |
consequential | -0.760 |
Token | , |
Token ID | 837 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
urga | +1.110 |
ahi | +1.015 |
rika | +0.978 |
ordinate | +0.959 |
htar | +0.948 |
Neg logit contributions | |
Brief | -1.056 |
Learns | -1.027 |
loose | -1.017 |
Neutral | -0.981 |
consequential | -0.968 |
Token | depth |
Token ID | 6795 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
urga | +0.666 |
ahi | +0.617 |
rika | +0.596 |
ordinate | +0.589 |
htar | +0.581 |
Neg logit contributions | |
Brief | -0.476 |
Learns | -0.461 |
loose | -0.455 |
Neutral | -0.436 |
consequential | -0.429 |
Token | : |
Token ID | 1058 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
urga | +2.368 |
ahi | +2.186 |
rika | +2.094 |
ordinate | +2.048 |
htar | +2.018 |
Neg logit contributions | |
Brief | -2.353 |
Learns | -2.299 |
loose | -2.265 |
consequential | -2.222 |
Neutral | -2.186 |
Token | self |
Token ID | 2116 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
urga | +2.209 |
ahi | +2.059 |
rika | +1.952 |
ordinate | +1.951 |
htar | +1.911 |
Neg logit contributions | |
Brief | -1.929 |
Learns | -1.894 |
loose | -1.838 |
Neutral | -1.785 |
consequential | -1.779 |
Token | . |
Token ID | 764 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
urga | +3.501 |
ahi | +3.248 |
rika | +3.115 |
ordinate | +3.058 |
htar | +2.943 |
Neg logit contributions | |
Brief | -4.242 |
Learns | -4.162 |
loose | -4.113 |
consequential | -4.094 |
Neutral | -3.983 |
Token | depth |
Token ID | 18053 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
urga | +2.922 |
ahi | +2.743 |
rika | +2.653 |
ordinate | +2.644 |
htar | +2.603 |
Neg logit contributions | |
Brief | -1.489 |
Learns | -1.429 |
loose | -1.407 |
Neutral | -1.340 |
consequential | -1.318 |
Token | , |
Token ID | 837 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
urga | +2.871 |
ahi | +2.610 |
rika | +2.504 |
ordinate | +2.459 |
htar | +2.429 |
Neg logit contributions | |
Brief | -2.872 |
Learns | -2.797 |
loose | -2.767 |
Neutral | -2.670 |
consequential | -2.651 |
Token | check |
Token ID | 2198 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
urga | +0.882 |
ahi | +0.819 |
rika | +0.790 |
ordinate | +0.782 |
htar | +0.771 |
Neg logit contributions | |
Brief | -0.607 |
Learns | -0.588 |
loose | -0.577 |
Neutral | -0.553 |
consequential | -0.544 |
Token | : |
Token ID | 1058 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
urga | +1.258 |
ahi | +1.154 |
rika | +1.116 |
ordinate | +1.091 |
htar | +1.078 |
Neg logit contributions | |
Brief | -1.142 |
Learns | -1.113 |
loose | -1.100 |
Neutral | -1.056 |
consequential | -1.050 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Brief | +1.201 |
loose | +1.158 |
Learns | +1.140 |
Neutral | +1.112 |
camps | +1.083 |
Neg logit contributions | |
urga | -1.359 |
ahi | -1.242 |
rika | -1.189 |
ordinate | -1.172 |
htar | -1.158 |
Token | M |
Token ID | 44 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
Brief | +1.020 |
loose | +0.983 |
Learns | +0.978 |
Neutral | +0.946 |
camps | +0.927 |
Neg logit contributions | |
urga | -1.052 |
ahi | -0.961 |
rika | -0.920 |
ordinate | -0.911 |
htar | -0.898 |
Token | asure |
Token ID | 5015 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
urga | +0.168 |
ahi | +0.154 |
rika | +0.148 |
ordinate | +0.146 |
htar | +0.144 |
Neg logit contributions | |
Brief | -0.163 |
Learns | -0.158 |
loose | -0.157 |
Neutral | -0.151 |
camps | -0.149 |
Token | , |
Token ID | 11 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
urga | +0.324 |
ahi | +0.296 |
rika | +0.285 |
ordinate | +0.280 |
htar | +0.276 |
Neg logit contributions | |
Brief | -0.315 |
Learns | -0.306 |
loose | -0.303 |
Neutral | -0.292 |
consequential | -0.288 |
Token | R |
Token ID | 371 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
urga | +0.973 |
ahi | +0.886 |
rika | +0.851 |
ordinate | +0.838 |
htar | +0.826 |
Neg logit contributions | |
Brief | -1.003 |
Learns | -0.975 |
loose | -0.966 |
Neutral | -0.934 |
consequential | -0.917 |
Token | . |
Token ID | 13 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
urga | +2.700 |
ahi | +2.460 |
rika | +2.371 |
ordinate | +2.312 |
htar | +2.286 |
Neg logit contributions | |
Brief | -2.741 |
Learns | -2.680 |
loose | -2.655 |
Neutral | -2.555 |
consequential | -2.526 |
Token | H |
Token ID | 367 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
urga | +3.595 |
ahi | +3.295 |
rika | +3.151 |
Ras | +3.022 |
Sus | +3.020 |
Neg logit contributions | |
Brief | -4.173 |
loose | -4.155 |
Learns | -4.130 |
consequential | -4.031 |
camps | -3.960 |
Token | ., |
Token ID | 1539 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
urga | +1.985 |
ahi | +1.797 |
rika | +1.726 |
ordinate | +1.682 |
htar | +1.658 |
Neg logit contributions | |
Brief | -2.314 |
Learns | -2.270 |
loose | -2.249 |
Neutral | -2.167 |
consequential | -2.144 |
Token | Al |
Token ID | 978 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
urga | +2.540 |
ahi | +2.348 |
rika | +2.265 |
ordinate | +2.206 |
htar | +2.191 |
Neg logit contributions | |
Brief | -2.013 |
loose | -1.975 |
Learns | -1.972 |
consequential | -1.882 |
Neutral | -1.861 |
Token | lee |
Token ID | 7197 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
urga | +0.854 |
ahi | +0.780 |
rika | +0.752 |
ordinate | +0.740 |
htar | +0.729 |
Neg logit contributions | |
Brief | -0.819 |
Learns | -0.795 |
loose | -0.789 |
Neutral | -0.760 |
consequential | -0.748 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Brief | +0.988 |
Learns | +0.941 |
loose | +0.931 |
Neutral | +0.907 |
camps | +0.884 |
Neg logit contributions | |
urga | -1.213 |
ahi | -1.104 |
rika | -1.073 |
ordinate | -1.068 |
htar | -1.045 |
Token | day |
Token ID | 1110 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Brief | +0.043 |
Learns | +0.042 |
loose | +0.041 |
Neutral | +0.039 |
consequential | +0.039 |
Neg logit contributions | |
urga | -0.068 |
ahi | -0.063 |
rika | -0.061 |
ordinate | -0.060 |
htar | -0.060 |
Token | a |
Token ID | 257 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
urga | +1.820 |
ahi | +1.675 |
rika | +1.613 |
ordinate | +1.583 |
htar | +1.565 |
Neg logit contributions | |
Brief | -1.605 |
Learns | -1.563 |
loose | -1.542 |
Neutral | -1.488 |
consequential | -1.465 |
Token | man |
Token ID | 582 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
urga | +0.023 |
ahi | +0.022 |
rika | +0.021 |
ordinate | +0.021 |
htar | +0.020 |
Neg logit contributions | |
Brief | -0.019 |
Learns | -0.018 |
loose | -0.018 |
Neutral | -0.017 |
consequential | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
urga | +0.639 |
ahi | +0.591 |
rika | +0.571 |
ordinate | +0.563 |
htar | +0.556 |
Neg logit contributions | |
Brief | -0.466 |
Learns | -0.451 |
loose | -0.447 |
Neutral | -0.428 |
consequential | -0.420 |
Token | pronounced |
Token ID | 16293 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
urga | +1.249 |
ahi | +1.134 |
rika | +1.083 |
ordinate | +1.063 |
htar | +1.045 |
Neg logit contributions | |
Brief | -1.503 |
Learns | -1.469 |
loose | -1.445 |
Neutral | -1.405 |
consequential | -1.385 |
Token | dead |
Token ID | 2636 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
urga | +3.671 |
ahi | +3.465 |
rika | +3.346 |
ordinate | +3.319 |
htar | +3.286 |
Neg logit contributions | |
Brief | -1.670 |
Learns | -1.585 |
loose | -1.529 |
Neutral | -1.464 |
consequential | -1.425 |
Token | after |
Token ID | 706 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
urga | +4.001 |
ahi | +3.693 |
rika | +3.535 |
ordinate | +3.495 |
isy | +3.436 |
Neg logit contributions | |
Brief | -3.822 |
Learns | -3.749 |
loose | -3.621 |
Neutral | -3.572 |
consequential | -3.486 |
Token | he |
Token ID | 339 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
urga | +0.976 |
ahi | +0.897 |
rika | +0.868 |
ordinate | +0.854 |
htar | +0.846 |
Neg logit contributions | |
Brief | -0.758 |
Learns | -0.734 |
loose | -0.730 |
Neutral | -0.698 |
consequential | -0.687 |
Token | was |
Token ID | 373 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
urga | +1.280 |
ahi | +1.186 |
rika | +1.149 |
ordinate | +1.131 |
htar | +1.120 |
Neg logit contributions | |
Brief | -0.858 |
Learns | -0.829 |
loose | -0.823 |
Neutral | -0.783 |
consequential | -0.770 |
Token | shot |
Token ID | 2823 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
urga | +1.212 |
ahi | +1.094 |
rika | +1.047 |
ordinate | +1.026 |
htar | +1.012 |
Neg logit contributions | |
Brief | -1.454 |
Learns | -1.417 |
loose | -1.411 |
Neutral | -1.362 |
consequential | -1.345 |
Token | outside |
Token ID | 2354 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
urga | +0.034 |
ahi | +0.031 |
rika | +0.031 |
ordinate | +0.030 |
htar | +0.030 |
Neg logit contributions | |
Brief | -0.023 |
loose | -0.022 |
Learns | -0.022 |
Neutral | -0.021 |
consequential | -0.021 |
Token | | |
Token ID | 930 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
urga | +0.868 |
ahi | +0.797 |
rika | +0.767 |
ordinate | +0.754 |
htar | +0.746 |
Neg logit contributions | |
Brief | -0.766 |
Learns | -0.744 |
loose | -0.736 |
Neutral | -0.708 |
consequential | -0.699 |
Token | prev |
Token ID | 8654 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Brief | +0.256 |
Learns | +0.247 |
loose | +0.247 |
Neutral | +0.236 |
consequential | +0.231 |
Neg logit contributions | |
urga | -0.328 |
ahi | -0.302 |
rika | -0.293 |
ordinate | -0.287 |
htar | -0.284 |
Token | _ |
Token ID | 62 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
urga | +0.803 |
ahi | +0.706 |
rika | +0.666 |
ordinate | +0.649 |
htar | +0.635 |
Neg logit contributions | |
Brief | -1.430 |
Learns | -1.401 |
loose | -1.391 |
Neutral | -1.352 |
consequential | -1.339 |
Token | state |
Token ID | 5219 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
urga | +0.887 |
ahi | +0.815 |
rika | +0.786 |
ordinate | +0.772 |
htar | +0.764 |
Neg logit contributions | |
Brief | -0.761 |
Learns | -0.739 |
loose | -0.733 |
Neutral | -0.704 |
consequential | -0.693 |
Token | : |
Token ID | 25 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
urga | +2.062 |
ahi | +1.894 |
rika | +1.817 |
ordinate | +1.793 |
htar | +1.768 |
Neg logit contributions | |
Brief | -1.820 |
Learns | -1.769 |
loose | -1.742 |
Neutral | -1.685 |
consequential | -1.666 |
Token | Option |
Token ID | 16018 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
urga | +0.801 |
ahi | +0.741 |
rika | +0.714 |
ordinate | +0.704 |
htar | +0.695 |
Neg logit contributions | |
Brief | -0.635 |
Learns | -0.617 |
loose | -0.610 |
Neutral | -0.586 |
consequential | -0.578 |
Token | < |
Token ID | 27 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
urga | +3.973 |
ahi | +3.707 |
ordinate | +3.493 |
rika | +3.469 |
isy | +3.427 |
Neg logit contributions | |
Brief | -3.732 |
Learns | -3.663 |
loose | -3.570 |
Neutral | -3.474 |
consequential | -3.449 |
Token | Board |
Token ID | 29828 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Brief | +0.289 |
Learns | +0.279 |
loose | +0.278 |
Neutral | +0.266 |
consequential | +0.260 |
Neg logit contributions | |
urga | -0.348 |
ahi | -0.317 |
rika | -0.308 |
ordinate | -0.302 |
htar | -0.300 |
Token | >, |
Token ID | 22330 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
urga | +1.130 |
ahi | +1.046 |
rika | +1.010 |
ordinate | +0.996 |
htar | +0.982 |
Neg logit contributions | |
Brief | -0.834 |
Learns | -0.807 |
loose | -0.799 |
Neutral | -0.764 |
consequential | -0.756 |
Token | // |
Token ID | 3373 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
urga | +1.309 |
ahi | +1.208 |
rika | +1.166 |
ordinate | +1.151 |
htar | +1.136 |
Neg logit contributions | |
Brief | -1.011 |
Learns | -0.980 |
loose | -0.970 |
Neutral | -0.930 |
consequential | -0.918 |
Token | The |
Token ID | 383 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
urga | +0.797 |
ahi | +0.735 |
rika | +0.709 |
ordinate | +0.699 |
htar | +0.690 |
Neg logit contributions | |
Brief | -0.635 |
Learns | -0.616 |
loose | -0.610 |
Neutral | -0.585 |
consequential | -0.576 |
Token |
|
Token ID | 198 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
urga | +0.349 |
ahi | +0.318 |
rika | +0.306 |
ordinate | +0.300 |
htar | +0.296 |
Neg logit contributions | |
Brief | -0.364 |
Learns | -0.356 |
loose | -0.352 |
Neutral | -0.339 |
consequential | -0.337 |
Token | La |
Token ID | 14772 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
urga | +0.302 |
ahi | +0.277 |
rika | +0.267 |
ordinate | +0.263 |
htar | +0.260 |
Neg logit contributions | |
Brief | -0.254 |
Learns | -0.246 |
loose | -0.244 |
Neutral | -0.234 |
consequential | -0.230 |
Token | uren |
Token ID | 23532 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
Brief | +0.493 |
loose | +0.467 |
Learns | +0.467 |
Neutral | +0.447 |
camps | +0.436 |
Neg logit contributions | |
urga | -0.686 |
ahi | -0.633 |
ordinate | -0.611 |
rika | -0.605 |
htar | -0.599 |
Token | Carter |
Token ID | 10831 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
urga | +0.675 |
ahi | +0.621 |
rika | +0.600 |
ordinate | +0.590 |
htar | +0.583 |
Neg logit contributions | |
Brief | -0.558 |
Learns | -0.541 |
loose | -0.537 |
Neutral | -0.515 |
consequential | -0.507 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Brief | +0.079 |
Learns | +0.077 |
loose | +0.076 |
Neutral | +0.073 |
camps | +0.072 |
Neg logit contributions | |
urga | -0.101 |
ahi | -0.093 |
rika | -0.090 |
ordinate | -0.089 |
htar | -0.088 |
Token | centre |
Token ID | 7372 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
urga | +1.181 |
ahi | +1.087 |
rika | +1.048 |
ordinate | +1.032 |
htar | +1.018 |
Neg logit contributions | |
Brief | -0.992 |
Learns | -0.966 |
loose | -0.953 |
Neutral | -0.916 |
consequential | -0.905 |
Token | , |
Token ID | 11 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
urga | +4.010 |
ahi | +3.640 |
rika | +3.531 |
ordinate | +3.431 |
htar | +3.416 |
Neg logit contributions | |
Brief | -3.804 |
Learns | -3.744 |
loose | -3.660 |
Neutral | -3.539 |
consequential | -3.520 |
Token | helped |
Token ID | 4193 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
urga | +0.625 |
ahi | +0.579 |
rika | +0.561 |
ordinate | +0.552 |
htar | +0.547 |
Neg logit contributions | |
Brief | -0.430 |
Learns | -0.417 |
loose | -0.413 |
Neutral | -0.394 |
camps | -0.388 |
Token | begin |
Token ID | 2221 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
urga | +0.696 |
ahi | +0.639 |
rika | +0.617 |
ordinate | +0.602 |
htar | +0.601 |
Neg logit contributions | |
Brief | -0.575 |
loose | -0.557 |
Learns | -0.556 |
Neutral | -0.531 |
camps | -0.523 |
Token | the |
Token ID | 262 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
Brief | +1.345 |
loose | +1.302 |
Learns | +1.298 |
Neutral | +1.230 |
camps | +1.213 |
Neg logit contributions | |
urga | -2.061 |
ahi | -1.912 |
rika | -1.852 |
ordinate | -1.812 |
htar | -1.810 |
Token | initiative |
Token ID | 10219 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
Brief | +0.515 |
Learns | +0.498 |
loose | +0.495 |
Neutral | +0.473 |
consequential | +0.464 |
Neg logit contributions | |
urga | -0.716 |
ahi | -0.662 |
rika | -0.641 |
ordinate | -0.631 |
htar | -0.624 |
Token | D |
Token ID | 360 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
urga | +2.720 |
ahi | +2.487 |
rika | +2.388 |
ordinate | +2.353 |
htar | +2.323 |
Neg logit contributions | |
Brief | -2.723 |
Learns | -2.644 |
loose | -2.643 |
Neutral | -2.528 |
consequential | -2.507 |
Token | ., |
Token ID | 1539 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
urga | +1.647 |
ahi | +1.454 |
rika | +1.382 |
ordinate | +1.325 |
htar | +1.312 |
Neg logit contributions | |
Brief | -2.696 |
Learns | -2.664 |
loose | -2.639 |
Neutral | -2.556 |
consequential | -2.537 |
Token | Long |
Token ID | 5882 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
urga | +1.541 |
ahi | +1.414 |
rika | +1.363 |
ordinate | +1.332 |
htar | +1.319 |
Neg logit contributions | |
Brief | -1.383 |
Learns | -1.350 |
loose | -1.346 |
Neutral | -1.286 |
consequential | -1.280 |
Token | , |
Token ID | 11 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
urga | +1.732 |
ahi | +1.581 |
rika | +1.515 |
ordinate | +1.484 |
htar | +1.467 |
Neg logit contributions | |
Brief | -1.816 |
Learns | -1.775 |
loose | -1.759 |
Neutral | -1.695 |
consequential | -1.675 |
Token | J |
Token ID | 449 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
urga | +1.490 |
ahi | +1.356 |
rika | +1.301 |
ordinate | +1.270 |
htar | +1.254 |
Neg logit contributions | |
Brief | -1.675 |
Learns | -1.637 |
loose | -1.627 |
Neutral | -1.565 |
consequential | -1.555 |
Token | . |
Token ID | 13 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
urga | +2.805 |
ahi | +2.554 |
rika | +2.438 |
ordinate | +2.357 |
htar | +2.331 |
Neg logit contributions | |
Brief | -3.364 |
Learns | -3.323 |
loose | -3.279 |
Neutral | -3.153 |
consequential | -3.140 |
Token | D |
Token ID | 360 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
urga | +3.381 |
ahi | +3.103 |
rika | +2.955 |
Ras | +2.860 |
ordinate | +2.849 |
Neg logit contributions | |
Brief | -4.236 |
loose | -4.217 |
Learns | -4.156 |
consequential | -4.080 |
camps | -4.002 |
Token | . |
Token ID | 13 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
urga | +2.330 |
ahi | +2.082 |
rika | +1.991 |
ordinate | +1.912 |
htar | +1.893 |
Neg logit contributions | |
Brief | -3.297 |
Learns | -3.268 |
loose | -3.232 |
Neutral | -3.113 |
consequential | -3.096 |
Token | ( |
Token ID | 357 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
urga | +2.116 |
ahi | +1.931 |
rika | +1.854 |
ordinate | +1.811 |
htar | +1.786 |
Neg logit contributions | |
Brief | -2.262 |
loose | -2.216 |
Learns | -2.206 |
consequential | -2.115 |
Neutral | -2.107 |
Token | 2002 |
Token ID | 6244 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
urga | +1.648 |
ahi | +1.515 |
rika | +1.456 |
ordinate | +1.428 |
htar | +1.410 |
Neg logit contributions | |
Brief | -1.576 |
Learns | -1.549 |
loose | -1.531 |
Neutral | -1.468 |
consequential | -1.463 |
Token | ). |
Token ID | 6739 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
urga | +1.076 |
ahi | +0.986 |
rika | +0.954 |
ordinate | +0.933 |
htar | +0.925 |
Neg logit contributions | |
Brief | -0.898 |
Learns | -0.877 |
loose | -0.868 |
Neutral | -0.832 |
consequential | -0.819 |
Token | discovered |
Token ID | 5071 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
urga | +0.539 |
ahi | +0.496 |
rika | +0.480 |
ordinate | +0.471 |
htar | +0.466 |
Neg logit contributions | |
Brief | -0.429 |
Learns | -0.415 |
loose | -0.413 |
Neutral | -0.395 |
consequential | -0.389 |
Token | by |
Token ID | 416 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
urga | +1.326 |
ahi | +1.230 |
rika | +1.191 |
ordinate | +1.174 |
htar | +1.161 |
Neg logit contributions | |
Brief | -0.887 |
Learns | -0.858 |
loose | -0.847 |
Neutral | -0.810 |
consequential | -0.795 |
Token | its |
Token ID | 663 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
urga | +0.352 |
ahi | +0.323 |
rika | +0.311 |
ordinate | +0.305 |
htar | +0.303 |
Neg logit contributions | |
Brief | -0.311 |
loose | -0.302 |
Learns | -0.301 |
Neutral | -0.289 |
consequential | -0.284 |
Token | owner |
Token ID | 4870 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
urga | +0.661 |
ahi | +0.603 |
rika | +0.581 |
ordinate | +0.570 |
htar | +0.563 |
Neg logit contributions | |
Brief | -0.646 |
Learns | -0.627 |
loose | -0.626 |
Neutral | -0.602 |
consequential | -0.593 |
Token | 's |
Token ID | 338 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
urga | +0.974 |
ahi | +0.898 |
rika | +0.867 |
ordinate | +0.854 |
htar | +0.844 |
Neg logit contributions | |
Brief | -0.773 |
Learns | -0.749 |
loose | -0.743 |
Neutral | -0.712 |
consequential | -0.701 |
Token | neighbour |
Token ID | 12250 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
urga | +1.614 |
ahi | +1.471 |
rika | +1.413 |
ordinate | +1.388 |
htar | +1.366 |
Neg logit contributions | |
Brief | -1.689 |
Learns | -1.651 |
loose | -1.627 |
Neutral | -1.573 |
consequential | -1.550 |
Token | in |
Token ID | 287 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
urga | +4.211 |
ahi | +3.902 |
rika | +3.783 |
ordinate | +3.669 |
htar | +3.658 |
Neg logit contributions | |
Brief | -3.500 |
Learns | -3.443 |
loose | -3.332 |
Neutral | -3.233 |
consequential | -3.217 |
Token | Tampa |
Token ID | 15528 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
urga | +0.867 |
ahi | +0.800 |
rika | +0.773 |
ordinate | +0.762 |
htar | +0.753 |
Neg logit contributions | |
Brief | -0.657 |
Learns | -0.637 |
loose | -0.631 |
Neutral | -0.604 |
consequential | -0.595 |
Token | five |
Token ID | 1936 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
urga | +1.644 |
ahi | +1.512 |
rika | +1.459 |
ordinate | +1.435 |
htar | +1.418 |
Neg logit contributions | |
Brief | -1.384 |
Learns | -1.343 |
loose | -1.332 |
Neutral | -1.279 |
consequential | -1.259 |
Token | days |
Token ID | 1528 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
urga | +0.711 |
ahi | +0.655 |
rika | +0.632 |
ordinate | +0.622 |
htar | +0.616 |
Neg logit contributions | |
Brief | -0.567 |
Learns | -0.549 |
loose | -0.546 |
Neutral | -0.522 |
consequential | -0.514 |
Token | after |
Token ID | 706 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
urga | +0.172 |
ahi | +0.158 |
rika | +0.153 |
ordinate | +0.150 |
htar | +0.148 |
Neg logit contributions | |
Brief | -0.136 |
Learns | -0.131 |
loose | -0.131 |
Neutral | -0.125 |
consequential | -0.123 |
Token | investigation |
Token ID | 3645 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Brief | +0.114 |
loose | +0.110 |
Learns | +0.109 |
Neutral | +0.105 |
camps | +0.103 |
Neg logit contributions | |
urga | -0.157 |
ahi | -0.145 |
rika | -0.140 |
ordinate | -0.138 |
htar | -0.137 |
Token | of |
Token ID | 286 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Brief | +0.298 |
loose | +0.287 |
Learns | +0.287 |
Neutral | +0.274 |
camps | +0.270 |
Neg logit contributions | |
urga | -0.410 |
ahi | -0.379 |
rika | -0.366 |
ordinate | -0.362 |
htar | -0.356 |
Token | the |
Token ID | 262 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
urga | +0.899 |
ahi | +0.831 |
rika | +0.805 |
ordinate | +0.793 |
htar | +0.784 |
Neg logit contributions | |
Brief | -0.644 |
Learns | -0.625 |
loose | -0.614 |
Neutral | -0.589 |
consequential | -0.579 |
Token | Las |
Token ID | 10123 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Brief | +0.140 |
Learns | +0.135 |
loose | +0.134 |
Neutral | +0.128 |
consequential | +0.126 |
Neg logit contributions | |
urga | -0.196 |
ahi | -0.181 |
rika | -0.175 |
ordinate | -0.173 |
htar | -0.171 |
Token | Vegas |
Token ID | 9621 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
Brief | +0.583 |
Learns | +0.557 |
loose | +0.554 |
Neutral | +0.530 |
camps | +0.516 |
Neg logit contributions | |
urga | -0.931 |
ahi | -0.864 |
rika | -0.835 |
ordinate | -0.826 |
htar | -0.821 |
Token | mass |
Token ID | 2347 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
urga | +0.663 |
ahi | +0.618 |
rika | +0.598 |
ordinate | +0.590 |
htar | +0.585 |
Neg logit contributions | |
Brief | -0.394 |
Learns | -0.387 |
loose | -0.378 |
Neutral | -0.358 |
consequential | -0.354 |
Token | shooting |
Token ID | 4395 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
Brief | +1.393 |
loose | +1.363 |
Learns | +1.284 |
Neutral | +1.243 |
camps | +1.216 |
Neg logit contributions | |
urga | -4.041 |
ahi | -3.731 |
rika | -3.689 |
ordinate | -3.646 |
htar | -3.604 |
Token | . |
Token ID | 13 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
Brief | +0.443 |
loose | +0.428 |
Learns | +0.427 |
Neutral | +0.408 |
consequential | +0.401 |
Neg logit contributions | |
urga | -0.555 |
ahi | -0.511 |
rika | -0.494 |
ordinate | -0.487 |
htar | -0.479 |
Token |
|
Token ID | 198 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
urga | +0.715 |
ahi | +0.658 |
rika | +0.634 |
ordinate | +0.623 |
htar | +0.616 |
Neg logit contributions | |
Brief | -0.616 |
Learns | -0.599 |
loose | -0.594 |
Neutral | -0.570 |
consequential | -0.563 |
Token |
|
Token ID | 198 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
urga | +0.437 |
ahi | +0.399 |
rika | +0.384 |
ordinate | +0.377 |
htar | +0.372 |
Neg logit contributions | |
Brief | -0.447 |
Learns | -0.436 |
loose | -0.432 |
Neutral | -0.416 |
consequential | -0.412 |
Token | Of |
Token ID | 5189 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
urga | +0.501 |
ahi | +0.463 |
rika | +0.449 |
ordinate | +0.442 |
htar | +0.437 |
Neg logit contributions | |
Brief | -0.349 |
Learns | -0.336 |
loose | -0.334 |
Neutral | -0.319 |
consequential | -0.313 |
Token | susceptible |
Token ID | 22084 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
urga | +0.077 |
ahi | +0.071 |
rika | +0.069 |
ordinate | +0.068 |
htar | +0.067 |
Neg logit contributions | |
Brief | -0.057 |
loose | -0.056 |
Learns | -0.055 |
Neutral | -0.053 |
consequential | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Brief | +0.507 |
loose | +0.492 |
Learns | +0.492 |
Neutral | +0.469 |
consequential | +0.461 |
Neg logit contributions | |
urga | -0.628 |
ahi | -0.579 |
rika | -0.558 |
ordinate | -0.549 |
htar | -0.543 |
Token | nausea |
Token ID | 32122 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
Brief | +1.380 |
loose | +1.350 |
Learns | +1.332 |
Neutral | +1.280 |
consequential | +1.263 |
Neg logit contributions | |
urga | -1.731 |
ahi | -1.579 |
rika | -1.532 |
ordinate | -1.494 |
htar | -1.491 |
Token | . |
Token ID | 13 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
urga | +0.011 |
ahi | +0.010 |
rika | +0.010 |
ordinate | +0.010 |
htar | +0.010 |
Neg logit contributions | |
Brief | -0.010 |
Learns | -0.010 |
loose | -0.010 |
Neutral | -0.009 |
consequential | -0.009 |
Token | Also |
Token ID | 4418 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Brief | +0.529 |
Learns | +0.509 |
loose | +0.506 |
Neutral | +0.488 |
consequential | +0.475 |
Neg logit contributions | |
urga | -0.677 |
ahi | -0.624 |
rika | -0.602 |
ordinate | -0.594 |
htar | -0.586 |
Token | note |
Token ID | 3465 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
Brief | +0.148 |
Learns | +0.143 |
loose | +0.142 |
Neutral | +0.136 |
consequential | +0.134 |
Neg logit contributions | |
urga | -0.188 |
ahi | -0.173 |
rika | -0.167 |
ordinate | -0.165 |
htar | -0.163 |
Token | , |
Token ID | 11 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Brief | +2.603 |
loose | +2.571 |
Learns | +2.460 |
Neutral | +2.387 |
consequential | +2.364 |
Neg logit contributions | |
urga | -4.027 |
ahi | -3.709 |
rika | -3.568 |
ordinate | -3.567 |
htar | -3.537 |
Token | that |
Token ID | 326 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
Brief | +1.134 |
loose | +1.102 |
Learns | +1.091 |
Neutral | +1.046 |
consequential | +1.027 |
Neg logit contributions | |
urga | -1.609 |
ahi | -1.487 |
rika | -1.440 |
ordinate | -1.419 |
htar | -1.405 |
Token | most |
Token ID | 749 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Brief | +0.449 |
loose | +0.434 |
Learns | +0.433 |
Neutral | +0.413 |
consequential | +0.406 |
Neg logit contributions | |
urga | -0.642 |
ahi | -0.594 |
rika | -0.575 |
ordinate | -0.566 |
htar | -0.560 |
Token | people |
Token ID | 661 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Brief | +0.911 |
loose | +0.887 |
Learns | +0.878 |
Neutral | +0.840 |
consequential | +0.829 |
Neg logit contributions | |
urga | -1.298 |
ahi | -1.200 |
rika | -1.163 |
ordinate | -1.145 |
htar | -1.138 |
Token | should |
Token ID | 815 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
Brief | +0.269 |
loose | +0.262 |
Learns | +0.261 |
Neutral | +0.248 |
camps | +0.244 |
Neg logit contributions | |
urga | -0.360 |
ahi | -0.332 |
rika | -0.320 |
ordinate | -0.315 |
htar | -0.313 |
Token | of |
Token ID | 286 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Brief | +1.468 |
Learns | +1.405 |
loose | +1.387 |
Neutral | +1.327 |
consequential | +1.295 |
Neg logit contributions | |
urga | -2.408 |
ahi | -2.213 |
rika | -2.158 |
ordinate | -2.141 |
htar | -2.122 |
Token | African |
Token ID | 5510 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Brief | +0.961 |
Learns | +0.922 |
loose | +0.919 |
Neutral | +0.894 |
consequential | +0.865 |
Neg logit contributions | |
urga | -1.154 |
ahi | -1.059 |
rika | -1.017 |
ordinate | -1.004 |
htar | -1.001 |
Token | American |
Token ID | 1605 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Brief | +0.885 |
Learns | +0.848 |
loose | +0.834 |
Neutral | +0.814 |
camps | +0.791 |
Neg logit contributions | |
urga | -1.100 |
ahi | -1.006 |
rika | -0.970 |
ordinate | -0.959 |
htar | -0.949 |
Token | History |
Token ID | 7443 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Brief | +0.865 |
Learns | +0.817 |
loose | +0.794 |
Neutral | +0.772 |
camps | +0.741 |
Neg logit contributions | |
urga | -1.510 |
ahi | -1.383 |
ordinate | -1.340 |
rika | -1.340 |
htar | -1.323 |
Token | and |
Token ID | 290 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Brief | +0.918 |
Learns | +0.879 |
loose | +0.871 |
Neutral | +0.839 |
consequential | +0.818 |
Neg logit contributions | |
urga | -1.258 |
ahi | -1.157 |
rika | -1.122 |
ordinate | -1.115 |
htar | -1.098 |
Token | Culture |
Token ID | 17346 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
urga | +0.279 |
ahi | +0.256 |
rika | +0.248 |
ordinate | +0.245 |
htar | +0.244 |
Neg logit contributions | |
Brief | -0.224 |
Learns | -0.214 |
loose | -0.209 |
Neutral | -0.206 |
consequential | -0.200 |
Token | instead |
Token ID | 2427 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Brief | +2.733 |
loose | +2.569 |
Learns | +2.551 |
Neutral | +2.468 |
camps | +2.416 |
Neg logit contributions | |
urga | -3.796 |
ahi | -3.460 |
ordinate | -3.375 |
rika | -3.357 |
htar | -3.319 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Brief | +1.599 |
loose | +1.542 |
Learns | +1.532 |
Neutral | +1.461 |
camps | +1.451 |
Neg logit contributions | |
urga | -1.978 |
ahi | -1.809 |
rika | -1.750 |
ordinate | -1.741 |
htar | -1.711 |
Token |
|
Token ID | 198 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
Brief | +0.761 |
Learns | +0.732 |
loose | +0.712 |
Neutral | +0.703 |
Proud | +0.678 |
Neg logit contributions | |
urga | -0.905 |
ahi | -0.831 |
rika | -0.805 |
ordinate | -0.796 |
htar | -0.781 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Brief | +0.245 |
Learns | +0.237 |
loose | +0.237 |
Neutral | +0.228 |
camps | +0.223 |
Neg logit contributions | |
urga | -0.254 |
ahi | -0.231 |
rika | -0.222 |
ordinate | -0.219 |
htar | -0.216 |
Token | Next |
Token ID | 10019 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
urga | +0.095 |
ahi | +0.087 |
rika | +0.084 |
ordinate | +0.083 |
htar | +0.082 |
Neg logit contributions | |
Brief | -0.082 |
Learns | -0.079 |
loose | -0.078 |
Neutral | -0.076 |
consequential | -0.074 |
Token | possible |
Token ID | 1744 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Brief | +1.243 |
loose | +1.214 |
Learns | +1.201 |
Neutral | +1.149 |
consequential | +1.142 |
Neg logit contributions | |
urga | -1.529 |
ahi | -1.403 |
rika | -1.360 |
ordinate | -1.326 |
htar | -1.320 |
Token | paths |
Token ID | 13532 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
Brief | +1.461 |
loose | +1.429 |
Learns | +1.416 |
Neutral | +1.355 |
camps | +1.346 |
Neg logit contributions | |
urga | -1.929 |
ahi | -1.775 |
rika | -1.722 |
ordinate | -1.675 |
htar | -1.662 |
Token | ? |
Token ID | 30 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
urga | +0.060 |
ahi | +0.055 |
rika | +0.054 |
ordinate | +0.053 |
htar | +0.052 |
Neg logit contributions | |
Brief | -0.042 |
Learns | -0.041 |
loose | -0.041 |
Neutral | -0.039 |
consequential | -0.038 |
Token | As |
Token ID | 1081 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
urga | +1.213 |
ahi | +1.117 |
rika | +1.069 |
ordinate | +1.049 |
htar | +1.041 |
Neg logit contributions | |
Brief | -1.112 |
Learns | -1.090 |
loose | -1.089 |
consequential | -1.039 |
Neutral | -1.031 |
Token | far |
Token ID | 1290 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
urga | +0.405 |
ahi | +0.376 |
rika | +0.361 |
ordinate | +0.357 |
htar | +0.353 |
Neg logit contributions | |
Brief | -0.293 |
Learns | -0.284 |
loose | -0.280 |
Neutral | -0.268 |
consequential | -0.264 |
Token | as |
Token ID | 355 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
urga | +0.548 |
ahi | +0.505 |
rika | +0.484 |
ordinate | +0.476 |
htar | +0.471 |
Neg logit contributions | |
Brief | -0.526 |
Learns | -0.513 |
loose | -0.503 |
Neutral | -0.488 |
consequential | -0.479 |
Token | I |
Token ID | 314 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Brief | +2.394 |
loose | +2.353 |
Learns | +2.298 |
Neutral | +2.208 |
camps | +2.188 |
Neg logit contributions | |
urga | -3.628 |
ahi | -3.314 |
rika | -3.268 |
ordinate | -3.166 |
htar | -3.156 |
Token | can |
Token ID | 460 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
Brief | +0.542 |
Learns | +0.521 |
loose | +0.520 |
Neutral | +0.488 |
camps | +0.479 |
Neg logit contributions | |
urga | -0.965 |
ahi | -0.899 |
rika | -0.872 |
ordinate | -0.857 |
htar | -0.850 |
Token | tell |
Token ID | 1560 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
Brief | +0.570 |
loose | +0.553 |
Learns | +0.547 |
Neutral | +0.520 |
camps | +0.513 |
Neg logit contributions | |
urga | -0.801 |
ahi | -0.741 |
rika | -0.720 |
ordinate | -0.700 |
htar | -0.694 |
Token | , |
Token ID | 11 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
urga | +0.719 |
ahi | +0.661 |
rika | +0.637 |
ordinate | +0.627 |
htar | +0.620 |
Neg logit contributions | |
Brief | -0.618 |
Learns | -0.601 |
loose | -0.595 |
Neutral | -0.571 |
consequential | -0.563 |
Token | there |
Token ID | 612 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
Brief | +0.113 |
Learns | +0.110 |
loose | +0.109 |
Neutral | +0.104 |
consequential | +0.102 |
Neg logit contributions | |
urga | -0.166 |
ahi | -0.153 |
rika | -0.149 |
ordinate | -0.146 |
htar | -0.145 |
Token | |
Token ID | 3907 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
Brief | +0.847 |
loose | +0.818 |
Learns | +0.810 |
Neutral | +0.774 |
camps | +0.771 |
Neg logit contributions | |
urga | -0.910 |
ahi | -0.823 |
rika | -0.790 |
ordinate | -0.787 |
htar | -0.768 |
Token | log |
Token ID | 6404 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Brief | +3.201 |
Learns | +3.091 |
loose | +3.066 |
conom | +2.956 |
camps | +2.931 |
Neg logit contributions | |
urga | -2.926 |
ahi | -2.605 |
rika | -2.464 |
ordinate | -2.453 |
isy | -2.409 |
Token | y |
Token ID | 88 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
Brief | +1.267 |
Learns | +1.231 |
loose | +1.226 |
Neutral | +1.191 |
camps | +1.176 |
Neg logit contributions | |
urga | -1.006 |
ahi | -0.903 |
rika | -0.861 |
ordinate | -0.854 |
htar | -0.829 |
Token | a |
Token ID | 257 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
urga | +0.080 |
ahi | +0.074 |
rika | +0.071 |
ordinate | +0.070 |
htar | +0.069 |
Neg logit contributions | |
Brief | -0.060 |
Learns | -0.058 |
loose | -0.058 |
Neutral | -0.055 |
consequential | -0.054 |
Token | ma |
Token ID | 17266 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
Brief | +0.454 |
loose | +0.440 |
Learns | +0.435 |
Neutral | +0.414 |
camps | +0.412 |
Neg logit contributions | |
urga | -0.568 |
ahi | -0.518 |
rika | -0.501 |
ordinate | -0.497 |
htar | -0.485 |
Token | |
Token ID | 3907 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
Brief | +0.682 |
loose | +0.663 |
Learns | +0.656 |
Neutral | +0.625 |
camps | +0.622 |
Neg logit contributions | |
urga | -0.733 |
ahi | -0.665 |
ordinate | -0.644 |
rika | -0.641 |
htar | -0.621 |
Token | j |
Token ID | 73 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
Brief | +3.245 |
Learns | +3.095 |
loose | +3.079 |
conom | +2.940 |
Neutral | +2.917 |
Neg logit contributions | |
urga | -3.554 |
ahi | -3.174 |
rika | -3.058 |
ordinate | -3.011 |
isy | -2.978 |
Token | or |
Token ID | 273 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Brief | +1.349 |
loose | +1.261 |
Learns | +1.249 |
Neutral | +1.165 |
camps | +1.147 |
Neg logit contributions | |
urga | -2.896 |
ahi | -2.705 |
rika | -2.667 |
ordinate | -2.611 |
htar | -2.595 |
Token | thrust |
Token ID | 14613 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Brief | +0.240 |
loose | +0.232 |
Learns | +0.231 |
Neutral | +0.221 |
consequential | +0.219 |
Neg logit contributions | |
urga | -0.284 |
ahi | -0.259 |
rika | -0.252 |
ordinate | -0.248 |
htar | -0.243 |
Token | of |
Token ID | 286 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
Brief | +0.092 |
loose | +0.090 |
Learns | +0.089 |
Neutral | +0.085 |
consequential | +0.084 |
Neg logit contributions | |
urga | -0.124 |
ahi | -0.114 |
rika | -0.111 |
ordinate | -0.109 |
htar | -0.107 |
Token | his |
Token ID | 465 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Brief | +0.270 |
loose | +0.262 |
Learns | +0.260 |
Neutral | +0.248 |
consequential | +0.245 |
Neg logit contributions | |
urga | -0.356 |
ahi | -0.327 |
rika | -0.318 |
ordinate | -0.312 |
htar | -0.308 |
Token | AR |
Token ID | 1503 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
Brief | +0.270 |
Learns | +0.259 |
loose | +0.256 |
Neutral | +0.242 |
consequential | +0.237 |
Neg logit contributions | |
urga | -0.525 |
ahi | -0.491 |
rika | -0.476 |
ordinate | -0.471 |
htar | -0.468 |
Token | ( |
Token ID | 357 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
urga | +0.783 |
ahi | +0.722 |
rika | +0.697 |
ordinate | +0.688 |
htar | +0.680 |
Neg logit contributions | |
Brief | -0.617 |
Learns | -0.597 |
loose | -0.594 |
Neutral | -0.569 |
consequential | -0.559 |
Token | total |
Token ID | 23350 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
urga | +0.435 |
ahi | +0.395 |
rika | +0.378 |
ordinate | +0.370 |
htar | +0.366 |
Neg logit contributions | |
Brief | -0.485 |
Learns | -0.473 |
loose | -0.470 |
Neutral | -0.453 |
consequential | -0.447 |
Token | value |
Token ID | 1988 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
urga | +0.732 |
ahi | +0.676 |
rika | +0.654 |
ordinate | +0.643 |
htar | +0.637 |
Neg logit contributions | |
Brief | -0.554 |
Learns | -0.537 |
loose | -0.533 |
Neutral | -0.510 |
consequential | -0.502 |
Token | at |
Token ID | 379 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
urga | +0.588 |
ahi | +0.543 |
rika | +0.526 |
ordinate | +0.518 |
htar | +0.512 |
Neg logit contributions | |
Brief | -0.428 |
Learns | -0.416 |
loose | -0.413 |
Neutral | -0.394 |
consequential | -0.388 |
Token | his |
Token ID | 465 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
Brief | +0.301 |
loose | +0.293 |
Learns | +0.292 |
Neutral | +0.280 |
camps | +0.276 |
Neg logit contributions | |
urga | -0.373 |
ahi | -0.346 |
rika | -0.332 |
ordinate | -0.325 |
htar | -0.323 |
Token | position |
Token ID | 2292 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Brief | +0.362 |
loose | +0.352 |
Learns | +0.348 |
Neutral | +0.334 |
camps | +0.329 |
Neg logit contributions | |
urga | -0.528 |
ahi | -0.492 |
rika | -0.476 |
ordinate | -0.465 |
htar | -0.463 |
Token | ), |
Token ID | 828 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Brief | +0.221 |
Learns | +0.214 |
loose | +0.213 |
Neutral | +0.204 |
consequential | +0.201 |
Neg logit contributions | |
urga | -0.265 |
ahi | -0.244 |
rika | -0.236 |
ordinate | -0.232 |
htar | -0.229 |
Token | third |
Token ID | 2368 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
urga | +0.978 |
ahi | +0.903 |
rika | +0.871 |
ordinate | +0.858 |
htar | +0.848 |
Neg logit contributions | |
Brief | -0.767 |
Learns | -0.746 |
loose | -0.734 |
Neutral | -0.706 |
consequential | -0.694 |
Token | in |
Token ID | 287 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
Brief | +0.087 |
Learns | +0.084 |
loose | +0.084 |
Neutral | +0.079 |
consequential | +0.078 |
Neg logit contributions | |
urga | -0.138 |
ahi | -0.128 |
rika | -0.124 |
ordinate | -0.122 |
htar | -0.121 |
Token | DV |
Token ID | 29854 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Brief | +0.535 |
Learns | +0.517 |
loose | +0.515 |
Neutral | +0.493 |
consequential | +0.483 |
Neg logit contributions | |
urga | -0.718 |
ahi | -0.664 |
rika | -0.642 |
ordinate | -0.630 |
htar | -0.626 |
Token | inn |
Token ID | 3527 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
urga | +0.059 |
ahi | +0.055 |
rika | +0.053 |
ordinate | +0.052 |
htar | +0.051 |
Neg logit contributions | |
Brief | -0.044 |
Learns | -0.042 |
loose | -0.042 |
Neutral | -0.040 |
consequential | -0.040 |
Token | ew |
Token ID | 413 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
Brief | +1.169 |
Learns | +1.138 |
loose | +1.138 |
Neutral | +1.100 |
camps | +1.090 |
Neg logit contributions | |
urga | -0.980 |
ahi | -0.874 |
rika | -0.847 |
ordinate | -0.827 |
htar | -0.821 |
Token | sp |
Token ID | 2777 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Brief | +0.038 |
Learns | +0.037 |
loose | +0.037 |
Neutral | +0.035 |
camps | +0.035 |
Neg logit contributions | |
urga | -0.037 |
ahi | -0.034 |
rika | -0.032 |
ordinate | -0.032 |
htar | -0.032 |
Token | aper |
Token ID | 2136 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
urga | +0.214 |
ahi | +0.195 |
rika | +0.188 |
ordinate | +0.185 |
htar | +0.182 |
Neg logit contributions | |
Brief | -0.201 |
Learns | -0.195 |
loose | -0.194 |
Neutral | -0.186 |
camps | -0.184 |
Token | ads |
Token ID | 9011 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
Brief | +0.011 |
Learns | +0.011 |
loose | +0.011 |
Neutral | +0.010 |
camps | +0.010 |
Neg logit contributions | |
urga | -0.014 |
ahi | -0.013 |
rika | -0.013 |
ordinate | -0.012 |
htar | -0.012 |
Token | that |
Token ID | 326 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Brief | +0.475 |
loose | +0.457 |
Learns | +0.456 |
Neutral | +0.433 |
consequential | +0.426 |
Neg logit contributions | |
urga | -0.685 |
ahi | -0.630 |
rika | -0.611 |
ordinate | -0.603 |
htar | -0.595 |
Token | no |
Token ID | 645 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Brief | +0.811 |
loose | +0.782 |
Learns | +0.782 |
Neutral | +0.745 |
camps | +0.734 |
Neg logit contributions | |
urga | -1.058 |
ahi | -0.969 |
rika | -0.942 |
ordinate | -0.928 |
htar | -0.913 |
Token | one |
Token ID | 530 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
urga | +0.955 |
ahi | +0.874 |
rika | +0.839 |
ordinate | +0.826 |
htar | +0.815 |
Neg logit contributions | |
Brief | -0.926 |
Learns | -0.903 |
loose | -0.893 |
Neutral | -0.861 |
consequential | -0.848 |
Token | would |
Token ID | 561 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Brief | +0.823 |
Learns | +0.796 |
loose | +0.788 |
Neutral | +0.752 |
consequential | +0.739 |
Neg logit contributions | |
urga | -1.219 |
ahi | -1.130 |
rika | -1.094 |
ordinate | -1.078 |
htar | -1.066 |
Token | be |
Token ID | 307 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
urga | +0.137 |
ahi | +0.127 |
rika | +0.123 |
ordinate | +0.121 |
htar | +0.120 |
Neg logit contributions | |
Brief | -0.094 |
Learns | -0.091 |
loose | -0.090 |
Neutral | -0.086 |
consequential | -0.085 |
Token | seated |
Token ID | 21639 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Brief | +0.264 |
Learns | +0.255 |
loose | +0.254 |
Neutral | +0.242 |
consequential | +0.238 |
Neg logit contributions | |
urga | -0.387 |
ahi | -0.359 |
rika | -0.348 |
ordinate | -0.342 |
htar | -0.338 |
Token | in |
Token ID | 287 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
urga | +0.837 |
ahi | +0.774 |
rika | +0.749 |
ordinate | +0.737 |
htar | +0.729 |
Neg logit contributions | |
Brief | -0.606 |
Learns | -0.587 |
loose | -0.581 |
Neutral | -0.556 |
consequential | -0.547 |
Token | the |
Token ID | 262 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
urga | +0.762 |
ahi | +0.692 |
rika | +0.663 |
ordinate | +0.652 |
htar | +0.641 |
Neg logit contributions | |
Brief | -0.848 |
Learns | -0.827 |
loose | -0.820 |
Neutral | -0.792 |
consequential | -0.781 |
Token | country |
Token ID | 1499 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
urga | +0.847 |
ahi | +0.785 |
rika | +0.761 |
ordinate | +0.750 |
htar | +0.740 |
Neg logit contributions | |
Brief | -0.535 |
Learns | -0.519 |
loose | -0.511 |
Neutral | -0.486 |
consequential | -0.478 |
Token | in |
Token ID | 287 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
urga | +0.936 |
ahi | +0.859 |
rika | +0.829 |
ordinate | +0.814 |
htar | +0.804 |
Neg logit contributions | |
Brief | -0.817 |
Learns | -0.794 |
loose | -0.786 |
Neutral | -0.756 |
consequential | -0.744 |
Token | which |
Token ID | 543 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Brief | +0.097 |
loose | +0.093 |
Learns | +0.093 |
Neutral | +0.089 |
consequential | +0.088 |
Neg logit contributions | |
urga | -0.111 |
ahi | -0.102 |
rika | -0.098 |
ordinate | -0.096 |
htar | -0.096 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
urga | +1.093 |
ahi | +1.011 |
rika | +0.978 |
ordinate | +0.962 |
htar | +0.951 |
Neg logit contributions | |
Brief | -0.811 |
Learns | -0.785 |
loose | -0.781 |
Neutral | -0.746 |
consequential | -0.735 |
Token | . |
Token ID | 13 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
Brief | +0.086 |
Learns | +0.084 |
loose | +0.083 |
Neutral | +0.080 |
consequential | +0.079 |
Neg logit contributions | |
urga | -0.097 |
ahi | -0.089 |
rika | -0.087 |
ordinate | -0.085 |
htar | -0.084 |
Token | 5 |
Token ID | 20 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
urga | +1.519 |
ahi | +1.373 |
rika | +1.313 |
ordinate | +1.283 |
htar | +1.266 |
Neg logit contributions | |
Brief | -1.828 |
Learns | -1.782 |
loose | -1.771 |
Neutral | -1.711 |
consequential | -1.697 |
Token | lakh |
Token ID | 29002 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
urga | +0.436 |
ahi | +0.399 |
rika | +0.387 |
ordinate | +0.378 |
htar | +0.374 |
Neg logit contributions | |
Brief | -0.405 |
Learns | -0.393 |
loose | -0.392 |
Neutral | -0.376 |
consequential | -0.372 |
Token | people |
Token ID | 661 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
urga | +1.472 |
ahi | +1.366 |
rika | +1.323 |
ordinate | +1.303 |
htar | +1.290 |
Neg logit contributions | |
Brief | -0.966 |
Learns | -0.933 |
loose | -0.924 |
Neutral | -0.881 |
consequential | -0.866 |
Token | lose |
Token ID | 4425 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
urga | +0.239 |
ahi | +0.221 |
rika | +0.214 |
ordinate | +0.210 |
htar | +0.208 |
Neg logit contributions | |
Brief | -0.186 |
loose | -0.182 |
Learns | -0.180 |
Neutral | -0.172 |
consequential | -0.170 |
Token | the |
Token ID | 262 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
urga | +0.896 |
ahi | +0.829 |
rika | +0.801 |
ordinate | +0.789 |
htar | +0.780 |
Neg logit contributions | |
Brief | -0.648 |
Learns | -0.628 |
loose | -0.622 |
Neutral | -0.595 |
consequential | -0.584 |
Token | remaining |
Token ID | 5637 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
urga | +0.720 |
ahi | +0.660 |
rika | +0.637 |
ordinate | +0.625 |
htar | +0.619 |
Neg logit contributions | |
Brief | -0.657 |
Learns | -0.637 |
loose | -0.634 |
Neutral | -0.610 |
consequential | -0.601 |
Token | 5 |
Token ID | 642 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
urga | +0.900 |
ahi | +0.835 |
rika | +0.810 |
ordinate | +0.797 |
htar | +0.790 |
Neg logit contributions | |
Brief | -0.582 |
Learns | -0.561 |
loose | -0.557 |
Neutral | -0.530 |
consequential | -0.521 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
urga | +0.245 |
ahi | +0.225 |
rika | +0.219 |
ordinate | +0.215 |
htar | +0.213 |
Neg logit contributions | |
Brief | -0.194 |
Learns | -0.189 |
loose | -0.188 |
Neutral | -0.179 |
camps | -0.177 |
Token | 5 |
Token ID | 20 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
urga | +1.067 |
ahi | +0.969 |
rika | +0.928 |
ordinate | +0.909 |
htar | +0.897 |
Neg logit contributions | |
Brief | -1.199 |
Learns | -1.169 |
loose | -1.162 |
Neutral | -1.120 |
consequential | -1.110 |
Token | acres |
Token ID | 16051 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
urga | +0.601 |
ahi | +0.558 |
rika | +0.542 |
ordinate | +0.533 |
htar | +0.528 |
Neg logit contributions | |
Brief | -0.381 |
Learns | -0.368 |
loose | -0.365 |
Neutral | -0.346 |
consequential | -0.341 |
Token | , |
Token ID | 11 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
Brief | +0.770 |
loose | +0.749 |
Learns | +0.737 |
Neutral | +0.708 |
consequential | +0.702 |
Neg logit contributions | |
urga | -1.072 |
ahi | -0.987 |
rika | -0.961 |
ordinate | -0.944 |
htar | -0.938 |
Token | where |
Token ID | 810 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
urga | +0.545 |
ahi | +0.502 |
rika | +0.486 |
ordinate | +0.478 |
htar | +0.472 |
Neg logit contributions | |
Brief | -0.425 |
Learns | -0.411 |
loose | -0.408 |
Neutral | -0.391 |
consequential | -0.385 |
Token | the |
Token ID | 262 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
urga | +2.126 |
ahi | +1.946 |
rika | +1.874 |
ordinate | +1.847 |
htar | +1.826 |
Neg logit contributions | |
Brief | -1.963 |
Learns | -1.910 |
loose | -1.874 |
Neutral | -1.809 |
consequential | -1.770 |
Token | institute |
Token ID | 24224 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
urga | +0.166 |
ahi | +0.153 |
rika | +0.149 |
ordinate | +0.146 |
htar | +0.145 |
Neg logit contributions | |
Brief | -0.114 |
loose | -0.110 |
Learns | -0.110 |
Neutral | -0.104 |
consequential | -0.103 |
Token | is |
Token ID | 318 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
urga | +1.609 |
ahi | +1.493 |
rika | +1.435 |
ordinate | +1.417 |
htar | +1.401 |
Neg logit contributions | |
Brief | -1.102 |
Learns | -1.067 |
loose | -1.045 |
Neutral | -1.008 |
consequential | -0.984 |
Token | Privacy |
Token ID | 16777 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
Brief | +0.538 |
Learns | +0.526 |
loose | +0.521 |
Neutral | +0.490 |
consequential | +0.486 |
Neg logit contributions | |
urga | -0.872 |
ahi | -0.814 |
rika | -0.792 |
ordinate | -0.776 |
htar | -0.770 |
Token | Policy |
Token ID | 7820 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
Brief | +0.319 |
Learns | +0.309 |
loose | +0.305 |
Neutral | +0.288 |
consequential | +0.284 |
Neg logit contributions | |
urga | -0.595 |
ahi | -0.556 |
rika | -0.540 |
ordinate | -0.531 |
htar | -0.527 |
Token | here |
Token ID | 994 |
Feature activation | +5.65e-03 |
Pos logit contributions | |
urga | +1.661 |
ahi | +1.529 |
rika | +1.473 |
htar | +1.443 |
ordinate | +1.429 |
Neg logit contributions | |
Brief | -1.781 |
Learns | -1.765 |
loose | -1.714 |
Neutral | -1.679 |
consequential | -1.658 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Brief | +0.004 |
Learns | +0.004 |
loose | +0.004 |
Neutral | +0.004 |
consequential | +0.004 |
Neg logit contributions | |
urga | -0.004 |
ahi | -0.004 |
rika | -0.004 |
ordinate | -0.004 |
htar | -0.003 |
Token | Sign |
Token ID | 5865 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
Brief | +1.167 |
Learns | +1.135 |
loose | +1.123 |
Neutral | +1.092 |
consequential | +1.068 |
Neg logit contributions | |
urga | -0.948 |
ahi | -0.852 |
rika | -0.814 |
ordinate | -0.799 |
htar | -0.784 |
Token | up |
Token ID | 510 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Brief | +2.212 |
loose | +2.193 |
Learns | +2.132 |
Neutral | +2.082 |
camps | +2.067 |
Neg logit contributions | |
urga | -1.994 |
ahi | -1.809 |
rika | -1.724 |
ordinate | -1.695 |
htar | -1.658 |
Token | for |
Token ID | 329 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Brief | +0.666 |
Learns | +0.645 |
loose | +0.635 |
Neutral | +0.607 |
consequential | +0.598 |
Neg logit contributions | |
urga | -1.027 |
ahi | -0.954 |
rika | -0.924 |
ordinate | -0.910 |
htar | -0.902 |
Token | Take |
Token ID | 7214 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Brief | +1.563 |
Learns | +1.510 |
loose | +1.500 |
Neutral | +1.449 |
camps | +1.418 |
Neg logit contributions | |
urga | -1.581 |
ahi | -1.425 |
rika | -1.382 |
ordinate | -1.358 |
htar | -1.338 |
Token | Action |
Token ID | 7561 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
Brief | +0.079 |
Learns | +0.076 |
loose | +0.075 |
Neutral | +0.070 |
consequential | +0.069 |
Neg logit contributions | |
urga | -0.168 |
ahi | -0.157 |
rika | -0.153 |
ordinate | -0.151 |
htar | -0.150 |
Token | Now |
Token ID | 2735 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
Brief | +1.538 |
Learns | +1.441 |
loose | +1.391 |
Neutral | +1.364 |
Proud | +1.305 |
Neg logit contributions | |
urga | -3.051 |
ahi | -2.839 |
rika | -2.758 |
ordinate | -2.753 |
htar | -2.682 |
Token | and |
Token ID | 290 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
Brief | +0.251 |
Learns | +0.243 |
loose | +0.240 |
Neutral | +0.230 |
consequential | +0.226 |
Neg logit contributions | |
urga | -0.361 |
ahi | -0.335 |
rika | -0.324 |
ordinate | -0.319 |
htar | -0.315 |
Token | Captain |
Token ID | 8599 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Brief | +1.030 |
Learns | +0.987 |
loose | +0.976 |
Neutral | +0.943 |
camps | +0.919 |
Neg logit contributions | |
urga | -1.382 |
ahi | -1.273 |
rika | -1.228 |
ordinate | -1.207 |
htar | -1.203 |
Token | " |
Token ID | 1 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Brief | +0.781 |
Learns | +0.751 |
loose | +0.739 |
Neutral | +0.715 |
camps | +0.697 |
Neg logit contributions | |
urga | -1.004 |
ahi | -0.918 |
rika | -0.893 |
ordinate | -0.880 |
htar | -0.872 |
Token | ( |
Token ID | 357 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Brief | +0.154 |
Learns | +0.149 |
loose | +0.148 |
Neutral | +0.141 |
consequential | +0.138 |
Neg logit contributions | |
urga | -0.214 |
ahi | -0.198 |
rika | -0.191 |
ordinate | -0.188 |
htar | -0.186 |
Token | 1972 |
Token ID | 41023 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
urga | +1.175 |
ahi | +1.062 |
rika | +1.014 |
ordinate | +0.995 |
htar | +0.980 |
Neg logit contributions | |
Brief | -1.463 |
Learns | -1.429 |
loose | -1.416 |
Neutral | -1.371 |
consequential | -1.354 |
Token | ) |
Token ID | 8 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
urga | +2.313 |
ahi | +2.130 |
rika | +2.044 |
ordinate | +1.999 |
htar | +1.988 |
Neg logit contributions | |
Brief | -2.148 |
Learns | -2.101 |
loose | -2.062 |
Neutral | -1.997 |
consequential | -1.967 |
Token | and |
Token ID | 290 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Brief | +0.116 |
Learns | +0.112 |
loose | +0.111 |
Neutral | +0.106 |
consequential | +0.104 |
Neg logit contributions | |
urga | -0.170 |
ahi | -0.158 |
rika | -0.153 |
ordinate | -0.151 |
htar | -0.149 |
Token | " |
Token ID | 366 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
urga | +1.640 |
ahi | +1.507 |
rika | +1.450 |
ordinate | +1.429 |
htar | +1.411 |
Neg logit contributions | |
Brief | -1.478 |
Learns | -1.448 |
loose | -1.423 |
Neutral | -1.371 |
consequential | -1.351 |
Token | H |
Token ID | 39 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
urga | +1.476 |
ahi | +1.356 |
rika | +1.307 |
ordinate | +1.285 |
htar | +1.269 |
Neg logit contributions | |
Brief | -1.304 |
Learns | -1.271 |
loose | -1.260 |
Neutral | -1.207 |
consequential | -1.194 |
Token | . |
Token ID | 13 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
Brief | +0.462 |
Learns | +0.444 |
loose | +0.443 |
Neutral | +0.426 |
camps | +0.419 |
Neg logit contributions | |
urga | -0.502 |
ahi | -0.457 |
rika | -0.441 |
ordinate | -0.436 |
htar | -0.431 |
Token | M |
Token ID | 44 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
urga | +0.484 |
ahi | +0.441 |
rika | +0.423 |
ordinate | +0.415 |
htar | +0.409 |
Neg logit contributions | |
Brief | -0.510 |
Learns | -0.497 |
loose | -0.494 |
Neutral | -0.475 |
consequential | -0.470 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
urga | +1.248 |
ahi | +1.140 |
rika | +1.089 |
ordinate | +1.067 |
htar | +1.055 |
Neg logit contributions | |
Brief | -1.280 |
Learns | -1.252 |
loose | -1.246 |
Neutral | -1.195 |
consequential | -1.183 |
Token | front |
Token ID | 2166 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Brief | +0.432 |
Learns | +0.417 |
loose | +0.413 |
Neutral | +0.394 |
consequential | +0.386 |
Neg logit contributions | |
urga | -0.666 |
ahi | -0.618 |
rika | -0.599 |
ordinate | -0.590 |
htar | -0.584 |
Token | and |
Token ID | 290 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
Brief | +1.136 |
loose | +1.104 |
Learns | +1.090 |
Neutral | +1.041 |
camps | +1.020 |
Neg logit contributions | |
urga | -1.757 |
ahi | -1.624 |
rika | -1.572 |
ordinate | -1.550 |
htar | -1.536 |
Token | back |
Token ID | 736 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Brief | +0.600 |
Learns | +0.580 |
loose | +0.578 |
Neutral | +0.552 |
consequential | +0.541 |
Neg logit contributions | |
urga | -0.830 |
ahi | -0.767 |
rika | -0.742 |
ordinate | -0.730 |
htar | -0.723 |
Token | of |
Token ID | 286 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Brief | +0.792 |
loose | +0.764 |
Learns | +0.764 |
Neutral | +0.726 |
consequential | +0.712 |
Neg logit contributions | |
urga | -1.169 |
ahi | -1.082 |
rika | -1.047 |
ordinate | -1.032 |
htar | -1.021 |
Token | the |
Token ID | 262 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
Brief | +0.954 |
Learns | +0.918 |
loose | +0.916 |
Neutral | +0.869 |
consequential | +0.851 |
Neg logit contributions | |
urga | -1.568 |
ahi | -1.457 |
rika | -1.412 |
ordinate | -1.391 |
htar | -1.378 |
Token | shif |
Token ID | 7143 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
Brief | +0.407 |
Learns | +0.388 |
loose | +0.385 |
Neutral | +0.361 |
consequential | +0.352 |
Neg logit contributions | |
urga | -0.934 |
ahi | -0.875 |
rika | -0.852 |
ordinate | -0.841 |
htar | -0.834 |
Token | ter |
Token ID | 353 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
urga | +0.386 |
ahi | +0.360 |
rika | +0.349 |
ordinate | +0.345 |
htar | +0.342 |
Neg logit contributions | |
Brief | -0.218 |
Learns | -0.210 |
loose | -0.207 |
Neutral | -0.197 |
consequential | -0.193 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
urga | +0.221 |
ahi | +0.203 |
rika | +0.196 |
ordinate | +0.193 |
htar | +0.191 |
Neg logit contributions | |
Brief | -0.182 |
Learns | -0.177 |
loose | -0.175 |
Neutral | -0.168 |
consequential | -0.165 |
Token | I |
Token ID | 314 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Brief | +0.760 |
Learns | +0.732 |
loose | +0.726 |
Neutral | +0.696 |
consequential | +0.674 |
Neg logit contributions | |
urga | -1.080 |
ahi | -0.999 |
rika | -0.965 |
ordinate | -0.952 |
htar | -0.941 |
Token | j |
Token ID | 474 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Brief | +0.830 |
loose | +0.802 |
Learns | +0.800 |
Neutral | +0.760 |
consequential | +0.745 |
Neg logit contributions | |
urga | -1.181 |
ahi | -1.092 |
rika | -1.055 |
ordinate | -1.040 |
htar | -1.027 |
Token | imm |
Token ID | 8608 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Brief | +1.273 |
loose | +1.245 |
Learns | +1.233 |
Neutral | +1.182 |
camps | +1.160 |
Neg logit contributions | |
urga | -1.481 |
ahi | -1.358 |
rika | -1.309 |
ordinate | -1.286 |
htar | -1.273 |
Token | record |
Token ID | 1700 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
Brief | +0.304 |
Learns | +0.293 |
loose | +0.292 |
Neutral | +0.280 |
camps | +0.275 |
Neg logit contributions | |
urga | -0.418 |
ahi | -0.386 |
rika | -0.374 |
ordinate | -0.369 |
htar | -0.365 |
Token | in |
Token ID | 287 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
urga | +0.349 |
ahi | +0.320 |
rika | +0.309 |
ordinate | +0.304 |
htar | +0.300 |
Neg logit contributions | |
Brief | -0.298 |
Learns | -0.290 |
loose | -0.287 |
Neutral | -0.276 |
consequential | -0.271 |
Token | particular |
Token ID | 1948 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
urga | +0.842 |
ahi | +0.782 |
rika | +0.757 |
ordinate | +0.747 |
htar | +0.739 |
Neg logit contributions | |
Brief | -0.540 |
Learns | -0.521 |
loose | -0.516 |
Neutral | -0.492 |
consequential | -0.483 |
Token | . |
Token ID | 13 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
urga | +1.766 |
ahi | +1.609 |
rika | +1.554 |
ordinate | +1.516 |
htar | +1.503 |
Neg logit contributions | |
Brief | -1.652 |
Learns | -1.609 |
loose | -1.593 |
Neutral | -1.533 |
consequential | -1.509 |
Token | This |
Token ID | 770 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
urga | +0.181 |
ahi | +0.166 |
rika | +0.161 |
ordinate | +0.158 |
htar | +0.156 |
Neg logit contributions | |
Brief | -0.146 |
Learns | -0.142 |
loose | -0.141 |
Neutral | -0.135 |
consequential | -0.133 |
Token | record |
Token ID | 1700 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
urga | +1.050 |
ahi | +0.973 |
rika | +0.935 |
ordinate | +0.922 |
htar | +0.909 |
Neg logit contributions | |
Brief | -0.781 |
Learns | -0.758 |
loose | -0.745 |
Neutral | -0.714 |
consequential | -0.703 |
Token | will |
Token ID | 481 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
urga | +0.415 |
ahi | +0.385 |
rika | +0.373 |
ordinate | +0.366 |
htar | +0.362 |
Neg logit contributions | |
Brief | -0.283 |
Learns | -0.274 |
loose | -0.271 |
Neutral | -0.258 |
consequential | -0.254 |
Token | regain |
Token ID | 21509 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
urga | +0.231 |
ahi | +0.213 |
rika | +0.206 |
ordinate | +0.203 |
htar | +0.201 |
Neg logit contributions | |
Brief | -0.170 |
Learns | -0.165 |
loose | -0.162 |
Neutral | -0.156 |
consequential | -0.154 |
Token | its |
Token ID | 663 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
urga | +0.943 |
ahi | +0.875 |
rika | +0.845 |
ordinate | +0.834 |
htar | +0.824 |
Neg logit contributions | |
Brief | -0.663 |
Learns | -0.642 |
loose | -0.633 |
Neutral | -0.606 |
consequential | -0.595 |
Token | attraction |
Token ID | 17416 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
urga | +0.450 |
ahi | +0.415 |
rika | +0.401 |
ordinate | +0.395 |
htar | +0.390 |
Neg logit contributions | |
Brief | -0.353 |
Learns | -0.342 |
loose | -0.339 |
Neutral | -0.325 |
consequential | -0.320 |
Token | for |
Token ID | 329 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
urga | +0.326 |
ahi | +0.301 |
rika | +0.292 |
ordinate | +0.287 |
htar | +0.284 |
Neg logit contributions | |
Brief | -0.244 |
Learns | -0.237 |
loose | -0.235 |
Neutral | -0.225 |
consequential | -0.221 |
Token | through |
Token ID | 832 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
Brief | +0.078 |
Learns | +0.075 |
loose | +0.075 |
Neutral | +0.072 |
consequential | +0.071 |
Neg logit contributions | |
urga | -0.100 |
ahi | -0.092 |
rika | -0.089 |
ordinate | -0.088 |
htar | -0.087 |
Token | in |
Token ID | 287 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
urga | +0.048 |
ahi | +0.045 |
rika | +0.043 |
ordinate | +0.042 |
htar | +0.042 |
Neg logit contributions | |
Brief | -0.041 |
Learns | -0.040 |
loose | -0.040 |
Neutral | -0.038 |
consequential | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
Brief | +0.422 |
loose | +0.405 |
Learns | +0.404 |
Neutral | +0.386 |
consequential | +0.379 |
Neg logit contributions | |
urga | -0.566 |
ahi | -0.523 |
rika | -0.506 |
ordinate | -0.493 |
htar | -0.492 |
Token | exact |
Token ID | 2748 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Brief | +0.362 |
loose | +0.349 |
Learns | +0.349 |
Neutral | +0.334 |
consequential | +0.328 |
Neg logit contributions | |
urga | -0.451 |
ahi | -0.416 |
rika | -0.402 |
ordinate | -0.395 |
htar | -0.390 |
Token | manner |
Token ID | 5642 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
urga | +0.838 |
ahi | +0.772 |
rika | +0.741 |
ordinate | +0.726 |
htar | +0.720 |
Neg logit contributions | |
Brief | -0.732 |
loose | -0.709 |
Learns | -0.707 |
Neutral | -0.679 |
consequential | -0.669 |
Token | . |
Token ID | 13 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
urga | +1.124 |
ahi | +1.038 |
rika | +1.002 |
ordinate | +0.987 |
htar | +0.976 |
Neg logit contributions | |
Brief | -0.866 |
Learns | -0.840 |
loose | -0.831 |
Neutral | -0.796 |
consequential | -0.783 |
Token | � |
Token ID | 447 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
urga | +0.637 |
ahi | +0.585 |
rika | +0.565 |
ordinate | +0.555 |
htar | +0.549 |
Neg logit contributions | |
Brief | -0.539 |
Learns | -0.524 |
loose | -0.520 |
Neutral | -0.498 |
consequential | -0.492 |
Token | � |
Token ID | 247 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
urga | +1.005 |
ahi | +0.929 |
rika | +0.900 |
ordinate | +0.883 |
htar | +0.873 |
Neg logit contributions | |
Brief | -0.731 |
Learns | -0.708 |
loose | -0.704 |
Neutral | -0.673 |
consequential | -0.663 |
Token | It |
Token ID | 632 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
urga | +0.337 |
ahi | +0.309 |
rika | +0.299 |
ordinate | +0.294 |
htar | +0.290 |
Neg logit contributions | |
Brief | -0.294 |
Learns | -0.285 |
loose | -0.282 |
Neutral | -0.272 |
consequential | -0.266 |
Token | has |
Token ID | 468 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
urga | +0.534 |
ahi | +0.494 |
rika | +0.479 |
ordinate | +0.472 |
htar | +0.466 |
Neg logit contributions | |
Brief | -0.366 |
Learns | -0.354 |
loose | -0.352 |
Neutral | -0.335 |
consequential | -0.329 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
urga | +1.408 |
ahi | +1.298 |
rika | +1.253 |
ordinate | +1.233 |
htar | +1.219 |
Neg logit contributions | |
Brief | -1.115 |
Learns | -1.082 |
loose | -1.071 |
Neutral | -1.028 |
consequential | -1.010 |
Token | teachers |
Token ID | 7799 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
Brief | +0.785 |
loose | +0.763 |
Learns | +0.760 |
Neutral | +0.726 |
camps | +0.721 |
Neg logit contributions | |
urga | -0.998 |
ahi | -0.921 |
rika | -0.887 |
ordinate | -0.876 |
htar | -0.865 |
Token | , |
Token ID | 11 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
urga | +0.650 |
ahi | +0.598 |
rika | +0.578 |
ordinate | +0.568 |
htar | +0.562 |
Neg logit contributions | |
Brief | -0.526 |
Learns | -0.510 |
loose | -0.509 |
Neutral | -0.486 |
consequential | -0.479 |
Token | math |
Token ID | 10688 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
urga | +1.829 |
ahi | +1.691 |
rika | +1.635 |
ordinate | +1.610 |
htar | +1.591 |
Neg logit contributions | |
Brief | -1.357 |
Learns | -1.315 |
loose | -1.300 |
Neutral | -1.246 |
consequential | -1.224 |
Token | " |
Token ID | 366 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
urga | +0.450 |
ahi | +0.417 |
rika | +0.403 |
ordinate | +0.397 |
htar | +0.393 |
Neg logit contributions | |
Brief | -0.321 |
Learns | -0.311 |
loose | -0.308 |
Neutral | -0.294 |
consequential | -0.289 |
Token | bec |
Token ID | 9423 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
Brief | +0.327 |
Learns | +0.321 |
loose | +0.317 |
Neutral | +0.304 |
camps | +0.301 |
Neg logit contributions | |
urga | -0.357 |
ahi | -0.328 |
rika | -0.315 |
ordinate | -0.309 |
htar | -0.306 |
Token | omes |
Token ID | 2586 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
Brief | +0.583 |
Learns | +0.571 |
loose | +0.567 |
Neutral | +0.539 |
camps | +0.533 |
Neg logit contributions | |
urga | -0.617 |
ahi | -0.560 |
rika | -0.539 |
ordinate | -0.528 |
htar | -0.526 |
Token | an |
Token ID | 281 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Brief | +0.017 |
Learns | +0.016 |
loose | +0.016 |
Neutral | +0.015 |
consequential | +0.015 |
Neg logit contributions | |
urga | -0.023 |
ahi | -0.021 |
rika | -0.021 |
ordinate | -0.020 |
htar | -0.020 |
Token | analytic |
Token ID | 49166 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
urga | +0.205 |
ahi | +0.190 |
rika | +0.184 |
ordinate | +0.181 |
htar | +0.180 |
Neg logit contributions | |
Brief | -0.140 |
Learns | -0.136 |
loose | -0.135 |
Neutral | -0.128 |
consequential | -0.127 |
Token | tool |
Token ID | 2891 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Brief | +1.706 |
loose | +1.670 |
Learns | +1.620 |
camps | +1.565 |
consequential | +1.563 |
Neg logit contributions | |
urga | -2.554 |
ahi | -2.364 |
rika | -2.250 |
ordinate | -2.237 |
htar | -2.227 |
Token | to |
Token ID | 284 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Brief | +1.030 |
loose | +0.997 |
Learns | +0.997 |
Neutral | +0.939 |
consequential | +0.932 |
Neg logit contributions | |
urga | -1.468 |
ahi | -1.354 |
rika | -1.314 |
ordinate | -1.300 |
htar | -1.280 |
Token | bring |
Token ID | 2222 |
Feature activation | +6.44e-03 |
Pos logit contributions | |
Brief | +0.701 |
Learns | +0.678 |
loose | +0.676 |
Neutral | +0.645 |
consequential | +0.637 |
Neg logit contributions | |
urga | -0.858 |
ahi | -0.787 |
rika | -0.760 |
ordinate | -0.745 |
htar | -0.742 |
Token | the |
Token ID | 262 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
Brief | +0.332 |
Learns | +0.321 |
loose | +0.319 |
Neutral | +0.303 |
consequential | +0.299 |
Neg logit contributions | |
urga | -0.490 |
ahi | -0.452 |
rika | -0.440 |
ordinate | -0.432 |
htar | -0.427 |
Token | server |
Token ID | 4382 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
Brief | +0.047 |
Learns | +0.046 |
loose | +0.046 |
Neutral | +0.044 |
consequential | +0.043 |
Neg logit contributions | |
urga | -0.054 |
ahi | -0.049 |
rika | -0.048 |
ordinate | -0.047 |
htar | -0.046 |
Token | would |
Token ID | 561 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
urga | +0.598 |
ahi | +0.555 |
rika | +0.538 |
ordinate | +0.530 |
htar | +0.524 |
Neg logit contributions | |
Brief | -0.387 |
Learns | -0.375 |
loose | -0.371 |
Neutral | -0.353 |
consequential | -0.347 |
Token | have |
Token ID | 423 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
Brief | +0.170 |
loose | +0.164 |
Learns | +0.163 |
Neutral | +0.155 |
camps | +0.152 |
Neg logit contributions | |
urga | -0.258 |
ahi | -0.239 |
rika | -0.232 |
ordinate | -0.227 |
htar | -0.225 |
Token | to |
Token ID | 284 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
Brief | +0.234 |
loose | +0.229 |
Learns | +0.227 |
Neutral | +0.216 |
consequential | +0.213 |
Neg logit contributions | |
urga | -0.336 |
ahi | -0.308 |
rika | -0.302 |
ordinate | -0.295 |
htar | -0.292 |
Token | stay |
Token ID | 2652 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
urga | +0.447 |
ahi | +0.413 |
rika | +0.400 |
ordinate | +0.392 |
htar | +0.388 |
Neg logit contributions | |
Brief | -0.337 |
Learns | -0.326 |
loose | -0.324 |
Neutral | -0.309 |
consequential | -0.304 |
Token | blocked |
Token ID | 10226 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
urga | +3.047 |
ahi | +2.821 |
rika | +2.710 |
ordinate | +2.683 |
htar | +2.651 |
Neg logit contributions | |
Brief | -2.354 |
Learns | -2.288 |
loose | -2.246 |
Neutral | -2.160 |
consequential | -2.130 |
Token | while |
Token ID | 981 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
urga | +0.797 |
ahi | +0.735 |
rika | +0.713 |
ordinate | +0.700 |
htar | +0.691 |
Neg logit contributions | |
Brief | -0.600 |
Learns | -0.580 |
loose | -0.579 |
Neutral | -0.552 |
consequential | -0.542 |
Token | the |
Token ID | 262 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
urga | +0.426 |
ahi | +0.394 |
rika | +0.383 |
ordinate | +0.377 |
htar | +0.373 |
Neg logit contributions | |
Brief | -0.276 |
Learns | -0.266 |
loose | -0.265 |
Neutral | -0.252 |
consequential | -0.248 |
Token | client |
Token ID | 5456 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
urga | +0.785 |
ahi | +0.720 |
rika | +0.696 |
ordinate | +0.683 |
htar | +0.675 |
Neg logit contributions | |
Brief | -0.687 |
Learns | -0.667 |
loose | -0.663 |
Neutral | -0.636 |
consequential | -0.627 |
Token | processes |
Token ID | 7767 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
urga | +1.338 |
ahi | +1.239 |
rika | +1.195 |
ordinate | +1.178 |
htar | +1.165 |
Neg logit contributions | |
Brief | -0.970 |
Learns | -0.936 |
loose | -0.928 |
Neutral | -0.890 |
consequential | -0.874 |
Token | their |
Token ID | 511 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
urga | +0.417 |
ahi | +0.388 |
rika | +0.375 |
ordinate | +0.368 |
htar | +0.368 |
Neg logit contributions | |
Brief | -0.255 |
Learns | -0.245 |
loose | -0.245 |
Neutral | -0.231 |
camps | -0.228 |
Token | lifetime |
Token ID | 10869 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
urga | +0.379 |
ahi | +0.349 |
rika | +0.337 |
ordinate | +0.332 |
htar | +0.328 |
Neg logit contributions | |
Brief | -0.301 |
Learns | -0.292 |
loose | -0.290 |
Neutral | -0.278 |
consequential | -0.273 |
Token | , |
Token ID | 11 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
urga | +1.728 |
ahi | +1.580 |
rika | +1.525 |
ordinate | +1.492 |
htar | +1.477 |
Neg logit contributions | |
Brief | -1.629 |
Learns | -1.588 |
loose | -1.569 |
Neutral | -1.514 |
consequential | -1.491 |
Token | according |
Token ID | 1864 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
urga | +0.394 |
ahi | +0.362 |
rika | +0.348 |
ordinate | +0.343 |
htar | +0.338 |
Neg logit contributions | |
Brief | -0.356 |
Learns | -0.346 |
loose | -0.343 |
Neutral | -0.330 |
consequential | -0.325 |
Token | to |
Token ID | 284 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
urga | +0.056 |
ahi | +0.052 |
rika | +0.050 |
ordinate | +0.049 |
htar | +0.049 |
Neg logit contributions | |
Brief | -0.046 |
Learns | -0.045 |
loose | -0.044 |
Neutral | -0.043 |
consequential | -0.042 |
Token | nonprofit |
Token ID | 15346 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
Brief | +0.138 |
Learns | +0.133 |
loose | +0.132 |
Neutral | +0.127 |
camps | +0.124 |
Neg logit contributions | |
urga | -0.199 |
ahi | -0.184 |
rika | -0.178 |
ordinate | -0.176 |
htar | -0.174 |
Token | Stop |
Token ID | 13707 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
urga | +3.145 |
ahi | +2.919 |
rika | +2.838 |
ordinate | +2.787 |
htar | +2.743 |
Neg logit contributions | |
Brief | -2.249 |
Learns | -2.191 |
loose | -2.168 |
Neutral | -2.058 |
consequential | -2.056 |
Token | Street |
Token ID | 3530 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
Brief | +1.982 |
Learns | +1.884 |
loose | +1.868 |
Neutral | +1.816 |
Proud | +1.747 |
Neg logit contributions | |
urga | -2.549 |
ahi | -2.375 |
rika | -2.267 |
ordinate | -2.232 |
htar | -2.203 |
Token | Har |
Token ID | 2113 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Brief | +1.412 |
Learns | +1.343 |
loose | +1.298 |
Neutral | +1.297 |
camps | +1.235 |
Neg logit contributions | |
urga | -2.155 |
ahi | -2.007 |
rika | -1.917 |
ordinate | -1.904 |
htar | -1.881 |
Token | assment |
Token ID | 45312 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
Brief | +0.623 |
Learns | +0.600 |
loose | +0.592 |
Neutral | +0.569 |
camps | +0.559 |
Neg logit contributions | |
urga | -0.903 |
ahi | -0.833 |
rika | -0.797 |
ordinate | -0.795 |
htar | -0.788 |
Token | . |
Token ID | 13 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Brief | +2.265 |
Learns | +2.150 |
loose | +2.108 |
Neutral | +2.070 |
camps | +2.028 |
Neg logit contributions | |
urga | -2.816 |
ahi | -2.593 |
ordinate | -2.518 |
rika | -2.494 |
htar | -2.441 |
Token | , |
Token ID | 11 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
urga | +0.194 |
ahi | +0.178 |
rika | +0.171 |
ordinate | +0.169 |
htar | +0.166 |
Neg logit contributions | |
Brief | -0.170 |
loose | -0.165 |
Learns | -0.164 |
Neutral | -0.157 |
camps | -0.155 |
Token | � |
Token ID | 447 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
urga | +0.050 |
ahi | +0.046 |
rika | +0.045 |
ordinate | +0.044 |
htar | +0.043 |
Neg logit contributions | |
Brief | -0.039 |
Learns | -0.038 |
loose | -0.037 |
Neutral | -0.036 |
consequential | -0.035 |
Token | � |
Token ID | 251 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
Brief | +0.201 |
Learns | +0.193 |
loose | +0.191 |
Neutral | +0.182 |
consequential | +0.178 |
Neg logit contributions | |
urga | -0.334 |
ahi | -0.311 |
rika | -0.302 |
ordinate | -0.297 |
htar | -0.294 |
Token | Kaine |
Token ID | 37193 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Brief | +0.605 |
Learns | +0.582 |
loose | +0.581 |
Neutral | +0.555 |
consequential | +0.547 |
Neg logit contributions | |
urga | -0.798 |
ahi | -0.735 |
rika | -0.712 |
ordinate | -0.700 |
htar | -0.690 |
Token | said |
Token ID | 531 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Brief | +0.991 |
Learns | +0.956 |
loose | +0.953 |
Neutral | +0.909 |
camps | +0.898 |
Neg logit contributions | |
urga | -1.273 |
ahi | -1.168 |
rika | -1.133 |
ordinate | -1.122 |
htar | -1.096 |
Token | toward |
Token ID | 3812 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
urga | +0.162 |
ahi | +0.148 |
rika | +0.143 |
ordinate | +0.141 |
htar | +0.139 |
Neg logit contributions | |
Brief | -0.137 |
loose | -0.133 |
Learns | -0.132 |
Neutral | -0.127 |
consequential | -0.125 |
Token | the |
Token ID | 262 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
urga | +3.716 |
ahi | +3.469 |
rika | +3.375 |
ordinate | +3.320 |
htar | +3.259 |
Neg logit contributions | |
Brief | -2.642 |
Learns | -2.626 |
loose | -2.490 |
Neutral | -2.395 |
camps | -2.353 |
Token | end |
Token ID | 886 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Brief | +0.100 |
loose | +0.097 |
Learns | +0.097 |
Neutral | +0.093 |
consequential | +0.092 |
Neg logit contributions | |
urga | -0.089 |
ahi | -0.080 |
rika | -0.077 |
ordinate | -0.076 |
htar | -0.075 |
Token | of |
Token ID | 286 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Brief | +0.641 |
loose | +0.617 |
Learns | +0.614 |
Neutral | +0.588 |
consequential | +0.579 |
Neg logit contributions | |
urga | -0.870 |
ahi | -0.801 |
rika | -0.775 |
ordinate | -0.767 |
htar | -0.755 |
Token | the |
Token ID | 262 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Brief | +0.912 |
loose | +0.870 |
Learns | +0.862 |
Neutral | +0.828 |
consequential | +0.812 |
Neg logit contributions | |
urga | -1.371 |
ahi | -1.265 |
rika | -1.227 |
ordinate | -1.204 |
htar | -1.198 |
Token | debate |
Token ID | 4384 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
Brief | +0.653 |
loose | +0.626 |
Learns | +0.623 |
Neutral | +0.596 |
consequential | +0.586 |
Neg logit contributions | |
urga | -0.987 |
ahi | -0.912 |
rika | -0.884 |
ordinate | -0.872 |
htar | -0.864 |
Token | bum |
Token ID | 4435 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
Brief | +0.837 |
Learns | +0.810 |
loose | +0.801 |
Neutral | +0.773 |
camps | +0.757 |
Neg logit contributions | |
urga | -0.911 |
ahi | -0.834 |
rika | -0.801 |
ordinate | -0.794 |
htar | -0.786 |
Token | [ |
Token ID | 685 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
urga | +0.635 |
ahi | +0.585 |
rika | +0.565 |
ordinate | +0.557 |
htar | +0.550 |
Neg logit contributions | |
Brief | -0.499 |
Learns | -0.483 |
loose | -0.479 |
Neutral | -0.459 |
consequential | -0.451 |
Token | edit |
Token ID | 4370 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
urga | +1.244 |
ahi | +1.115 |
rika | +1.065 |
ordinate | +1.036 |
htar | +1.018 |
Neg logit contributions | |
Brief | -1.830 |
Learns | -1.794 |
loose | -1.764 |
Neutral | -1.720 |
consequential | -1.703 |
Token | ] |
Token ID | 2361 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
urga | +1.922 |
ahi | +1.783 |
rika | +1.728 |
ordinate | +1.686 |
htar | +1.670 |
Neg logit contributions | |
Brief | -1.539 |
Learns | -1.504 |
loose | -1.475 |
consequential | -1.439 |
Neutral | -1.424 |
Token |
|
Token ID | 198 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
urga | +2.296 |
ahi | +2.110 |
rika | +2.004 |
ordinate | +1.965 |
htar | +1.951 |
Neg logit contributions | |
Brief | -2.549 |
Learns | -2.526 |
loose | -2.481 |
Neutral | -2.385 |
consequential | -2.378 |
Token |
|
Token ID | 198 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
urga | +2.067 |
ahi | +1.890 |
rika | +1.821 |
ordinate | +1.784 |
htar | +1.750 |
Neg logit contributions | |
Brief | -2.476 |
Learns | -2.472 |
loose | -2.393 |
consequential | -2.358 |
Neutral | -2.316 |
Token | A |
Token ID | 32 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
urga | +2.897 |
ahi | +2.667 |
rika | +2.568 |
ordinate | +2.537 |
htar | +2.485 |
Neg logit contributions | |
Brief | -2.622 |
Learns | -2.584 |
loose | -2.525 |
Neutral | -2.438 |
consequential | -2.429 |
Token | solo |
Token ID | 12199 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
Brief | +0.024 |
Learns | +0.023 |
loose | +0.023 |
Neutral | +0.022 |
consequential | +0.021 |
Neg logit contributions | |
urga | -0.032 |
ahi | -0.029 |
rika | -0.028 |
ordinate | -0.028 |
htar | -0.028 |
Token | album |
Token ID | 5062 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
urga | +2.488 |
ahi | +2.309 |
rika | +2.221 |
ordinate | +2.192 |
htar | +2.152 |
Neg logit contributions | |
Brief | -2.025 |
Learns | -1.994 |
loose | -1.942 |
Neutral | -1.866 |
consequential | -1.848 |
Token | titled |
Token ID | 11946 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
urga | +0.333 |
ahi | +0.308 |
rika | +0.298 |
ordinate | +0.293 |
htar | +0.290 |
Neg logit contributions | |
Brief | -0.249 |
Learns | -0.241 |
loose | -0.239 |
Neutral | -0.229 |
consequential | -0.225 |
Token | Ol |
Token ID | 6544 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
urga | +1.111 |
ahi | +1.021 |
rika | +0.984 |
ordinate | +0.967 |
htar | +0.955 |
Neg logit contributions | |
Brief | -0.957 |
Learns | -0.931 |
loose | -0.924 |
Neutral | -0.886 |
consequential | -0.877 |
Token | less |
Token ID | 1342 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
urga | +1.639 |
ahi | +1.519 |
rika | +1.472 |
ordinate | +1.448 |
htar | +1.434 |
Neg logit contributions | |
Brief | -1.098 |
Learns | -1.061 |
loose | -1.053 |
Neutral | -1.004 |
consequential | -0.987 |
Token | . |
Token ID | 13 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
Brief | +0.159 |
loose | +0.156 |
Learns | +0.155 |
Neutral | +0.146 |
consequential | +0.145 |
Neg logit contributions | |
urga | -0.248 |
ahi | -0.231 |
rika | -0.225 |
ordinate | -0.220 |
htar | -0.217 |
Token | For |
Token ID | 1114 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
urga | +0.400 |
ahi | +0.368 |
rika | +0.356 |
ordinate | +0.350 |
htar | +0.346 |
Neg logit contributions | |
Brief | -0.322 |
Learns | -0.312 |
loose | -0.309 |
Neutral | -0.297 |
consequential | -0.292 |
Token | many |
Token ID | 867 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
Brief | +0.057 |
loose | +0.056 |
Learns | +0.055 |
Neutral | +0.053 |
consequential | +0.053 |
Neg logit contributions | |
urga | -0.060 |
ahi | -0.055 |
rika | -0.053 |
ordinate | -0.052 |
htar | -0.051 |
Token | seniors |
Token ID | 23481 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
Brief | +0.621 |
loose | +0.600 |
Learns | +0.600 |
Neutral | +0.569 |
consequential | +0.566 |
Neg logit contributions | |
urga | -0.839 |
ahi | -0.776 |
rika | -0.754 |
ordinate | -0.739 |
htar | -0.734 |
Token | , |
Token ID | 11 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
urga | +0.071 |
ahi | +0.065 |
rika | +0.063 |
ordinate | +0.062 |
htar | +0.061 |
Neg logit contributions | |
Brief | -0.059 |
Learns | -0.058 |
loose | -0.057 |
Neutral | -0.055 |
consequential | -0.054 |
Token | the |
Token ID | 262 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
urga | +3.220 |
ahi | +2.999 |
ordinate | +2.855 |
rika | +2.848 |
htar | +2.801 |
Neg logit contributions | |
Brief | -2.454 |
Learns | -2.358 |
loose | -2.319 |
Neutral | -2.251 |
consequential | -2.191 |
Token | marketing |
Token ID | 7124 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
urga | +0.448 |
ahi | +0.414 |
rika | +0.400 |
ordinate | +0.394 |
htar | +0.390 |
Neg logit contributions | |
Brief | -0.327 |
Learns | -0.317 |
loose | -0.313 |
Neutral | -0.301 |
consequential | -0.295 |
Token | is |
Token ID | 318 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
Brief | +0.695 |
Learns | +0.673 |
loose | +0.670 |
Neutral | +0.635 |
camps | +0.632 |
Neg logit contributions | |
urga | -0.983 |
ahi | -0.909 |
rika | -0.877 |
ordinate | -0.866 |
htar | -0.855 |
Token | irresistible |
Token ID | 45420 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Brief | +0.046 |
loose | +0.045 |
Learns | +0.045 |
Neutral | +0.042 |
consequential | +0.042 |
Neg logit contributions | |
urga | -0.063 |
ahi | -0.058 |
rika | -0.056 |
ordinate | -0.055 |
htar | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
Brief | +1.109 |
loose | +1.078 |
Learns | +1.077 |
Neutral | +1.025 |
camps | +1.018 |
Neg logit contributions | |
urga | -1.323 |
ahi | -1.220 |
rika | -1.180 |
ordinate | -1.163 |
htar | -1.140 |