Token |
|
Token ID | 198 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
xit | +0.003 |
Uni | +0.003 |
ctors | +0.003 |
Honour | +0.003 |
culosis | +0.002 |
Neg logit contributions | |
ramid | -0.003 |
axter | -0.003 |
itect | -0.003 |
eele | -0.003 |
hare | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
xit | +0.134 |
Uni | +0.131 |
ctors | +0.124 |
Honour | +0.116 |
culosis | +0.103 |
Neg logit contributions | |
ramid | -0.156 |
axter | -0.151 |
eele | -0.149 |
itect | -0.149 |
hare | -0.145 |
Token | COM |
Token ID | 9858 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ramid | +0.334 |
itect | +0.319 |
axter | +0.319 |
eele | +0.318 |
hare | +0.309 |
Neg logit contributions | |
xit | -0.385 |
Uni | -0.375 |
ctors | -0.358 |
Honour | -0.337 |
culosis | -0.310 |
Token | IC |
Token ID | 2149 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
xit | +0.608 |
Uni | +0.597 |
ctors | +0.554 |
Honour | +0.518 |
culosis | +0.469 |
Neg logit contributions | |
ramid | -0.699 |
axter | -0.678 |
eele | -0.665 |
itect | -0.664 |
hare | -0.651 |
Token | V |
Token ID | 569 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
xit | +0.677 |
Uni | +0.664 |
ctors | +0.619 |
Honour | +0.574 |
culosis | +0.517 |
Neg logit contributions | |
ramid | -0.910 |
axter | -0.883 |
eele | -0.874 |
itect | -0.873 |
hare | -0.853 |
Token | INE |
Token ID | 8881 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
xit | +0.064 |
Uni | +0.063 |
ctors | +0.059 |
Honour | +0.055 |
culosis | +0.051 |
Neg logit contributions | |
ramid | -0.066 |
axter | -0.063 |
itect | -0.063 |
eele | -0.063 |
hare | -0.062 |
Token | : |
Token ID | 25 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Uni | +6.823 |
xit | +6.813 |
ctors | +6.292 |
Honour | +5.776 |
CV | +5.371 |
Neg logit contributions | |
ramid | -8.778 |
axter | -8.473 |
eele | -8.375 |
itect | -8.302 |
ippi | -8.139 |
Token | When |
Token ID | 1649 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ramid | +2.241 |
itect | +2.151 |
axter | +2.147 |
eele | +2.137 |
hare | +2.095 |
Neg logit contributions | |
xit | -2.297 |
Uni | -2.250 |
ctors | -2.133 |
Honour | -1.994 |
culosis | -1.844 |
Token | you |
Token ID | 345 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ramid | +0.341 |
itect | +0.328 |
axter | +0.326 |
eele | +0.326 |
hare | +0.318 |
Neg logit contributions | |
xit | -0.321 |
Uni | -0.317 |
ctors | -0.298 |
Honour | -0.279 |
culosis | -0.253 |
Token | think |
Token ID | 892 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
ramid | +0.410 |
eele | +0.398 |
axter | +0.395 |
itect | +0.395 |
hare | +0.383 |
Neg logit contributions | |
xit | -0.374 |
Uni | -0.371 |
ctors | -0.351 |
Honour | -0.326 |
culosis | -0.297 |
Token | of |
Token ID | 286 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
xit | +0.600 |
Uni | +0.587 |
ctors | +0.551 |
Honour | +0.510 |
culosis | +0.458 |
Neg logit contributions | |
ramid | -0.787 |
itect | -0.756 |
axter | -0.754 |
eele | -0.752 |
hare | -0.734 |
Token | over |
Token ID | 625 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ramid | +0.532 |
axter | +0.513 |
itect | +0.511 |
eele | +0.509 |
hare | +0.498 |
Neg logit contributions | |
xit | -0.418 |
Uni | -0.411 |
ctors | -0.384 |
Honour | -0.357 |
culosis | -0.322 |
Token | 21 |
Token ID | 2310 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
ramid | +2.651 |
itect | +2.555 |
axter | +2.544 |
eele | +2.539 |
hare | +2.501 |
Neg logit contributions | |
xit | -2.302 |
Uni | -2.241 |
ctors | -2.124 |
Honour | -1.962 |
culosis | -1.812 |
Token | million |
Token ID | 1510 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
xit | +2.454 |
Uni | +2.426 |
ctors | +2.322 |
Honour | +2.161 |
culosis | +2.018 |
Neg logit contributions | |
ramid | -1.920 |
axter | -1.826 |
itect | -1.799 |
eele | -1.798 |
olyn | -1.734 |
Token | with |
Token ID | 351 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
xit | +0.027 |
Uni | +0.026 |
ctors | +0.025 |
Honour | +0.023 |
culosis | +0.021 |
Neg logit contributions | |
ramid | -0.027 |
axter | -0.026 |
itect | -0.026 |
eele | -0.025 |
hare | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
xit | +1.764 |
Uni | +1.754 |
ctors | +1.615 |
Honour | +1.517 |
culosis | +1.353 |
Neg logit contributions | |
ramid | -2.188 |
axter | -2.110 |
itect | -2.098 |
eele | -2.095 |
hare | -2.040 |
Token | Gross |
Token ID | 21796 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
ramid | +0.237 |
axter | +0.228 |
itect | +0.228 |
eele | +0.226 |
hare | +0.221 |
Neg logit contributions | |
xit | -0.228 |
Uni | -0.225 |
ctors | -0.213 |
Honour | -0.197 |
culosis | -0.181 |
Token | National |
Token ID | 2351 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
xit | +6.280 |
Uni | +6.192 |
ctors | +5.386 |
Honour | +5.054 |
CV | +4.432 |
Neg logit contributions | |
ramid | -9.472 |
axter | -9.452 |
eele | -9.207 |
itect | -8.931 |
hare | -8.884 |
Token | Product |
Token ID | 8721 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
ramid | +0.490 |
itect | +0.471 |
axter | +0.469 |
eele | +0.467 |
hare | +0.459 |
Neg logit contributions | |
xit | -0.484 |
Uni | -0.473 |
ctors | -0.449 |
Honour | -0.418 |
culosis | -0.387 |
Token | of |
Token ID | 286 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
xit | +0.946 |
Uni | +0.927 |
ctors | +0.863 |
Honour | +0.815 |
culosis | +0.734 |
Neg logit contributions | |
ramid | -1.131 |
axter | -1.095 |
itect | -1.084 |
eele | -1.083 |
olyn | -1.055 |
Token | $ |
Token ID | 720 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
ramid | +0.078 |
axter | +0.075 |
itect | +0.075 |
eele | +0.074 |
hare | +0.073 |
Neg logit contributions | |
xit | -0.063 |
Uni | -0.062 |
ctors | -0.058 |
Honour | -0.054 |
culosis | -0.049 |
Token | 20 |
Token ID | 1238 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
xit | +0.101 |
Uni | +0.099 |
ctors | +0.094 |
Honour | +0.088 |
culosis | +0.080 |
Neg logit contributions | |
ramid | -0.091 |
axter | -0.087 |
eele | -0.087 |
itect | -0.086 |
hare | -0.084 |
Token | While |
Token ID | 2893 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
xit | +0.612 |
Uni | +0.606 |
ctors | +0.568 |
Honour | +0.532 |
culosis | +0.481 |
Neg logit contributions | |
ramid | -0.686 |
axter | -0.660 |
itect | -0.651 |
eele | -0.649 |
hare | -0.639 |
Token | this |
Token ID | 428 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
ramid | +0.839 |
itect | +0.807 |
axter | +0.801 |
eele | +0.797 |
hare | +0.783 |
Neg logit contributions | |
xit | -0.799 |
Uni | -0.787 |
ctors | -0.742 |
Honour | -0.691 |
culosis | -0.635 |
Token | capture |
Token ID | 8006 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ramid | +1.155 |
itect | +1.112 |
axter | +1.108 |
eele | +1.102 |
hare | +1.081 |
Neg logit contributions | |
xit | -1.091 |
Uni | -1.070 |
ctors | -1.011 |
Honour | -0.942 |
culosis | -0.868 |
Token | may |
Token ID | 743 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
xit | +0.293 |
Uni | +0.289 |
ctors | +0.272 |
Honour | +0.254 |
culosis | +0.234 |
Neg logit contributions | |
ramid | -0.315 |
axter | -0.302 |
itect | -0.302 |
eele | -0.298 |
hare | -0.294 |
Token | set |
Token ID | 900 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
xit | +1.045 |
Uni | +1.030 |
ctors | +0.997 |
Honour | +0.935 |
culosis | +0.850 |
Neg logit contributions | |
ramid | -0.938 |
itect | -0.906 |
axter | -0.905 |
eele | -0.890 |
olyn | -0.871 |
Token | Guinness |
Token ID | 41559 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
xit | +0.097 |
Uni | +0.096 |
ctors | +0.090 |
Honour | +0.084 |
culosis | +0.077 |
Neg logit contributions | |
ramid | -0.104 |
itect | -0.100 |
axter | -0.099 |
eele | -0.099 |
hare | -0.097 |
Token | Book |
Token ID | 4897 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
Uni | +5.417 |
xit | +4.984 |
ctors | +4.771 |
Honour | +4.477 |
culosis | +3.896 |
Neg logit contributions | |
ramid | -8.688 |
eele | -8.289 |
axter | -8.265 |
itect | -8.186 |
olyn | -8.001 |
Token | records |
Token ID | 4406 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Uni | +1.458 |
xit | +1.453 |
ctors | +1.370 |
Honour | +1.285 |
culosis | +1.140 |
Neg logit contributions | |
ramid | -1.911 |
axter | -1.850 |
eele | -1.835 |
itect | -1.818 |
hare | -1.793 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
xit | +2.650 |
Uni | +2.639 |
ctors | +2.470 |
Honour | +2.312 |
culosis | +2.138 |
Neg logit contributions | |
ramid | -2.798 |
itect | -2.648 |
axter | -2.635 |
eele | -2.628 |
olyn | -2.564 |
Token | there |
Token ID | 612 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
xit | +0.371 |
Uni | +0.370 |
ctors | +0.347 |
Honour | +0.326 |
culosis | +0.300 |
Neg logit contributions | |
ramid | -0.374 |
itect | -0.359 |
axter | -0.357 |
eele | -0.354 |
hare | -0.347 |
Token | are |
Token ID | 389 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
xit | +0.356 |
Uni | +0.352 |
ctors | +0.335 |
Honour | +0.311 |
culosis | +0.290 |
Neg logit contributions | |
ramid | -0.342 |
itect | -0.328 |
axter | -0.326 |
eele | -0.324 |
hare | -0.317 |
Token | p |
Token ID | 79 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
ramid | +0.273 |
itect | +0.262 |
axter | +0.261 |
eele | +0.259 |
hare | +0.253 |
Neg logit contributions | |
xit | -0.306 |
Uni | -0.297 |
ctors | -0.284 |
Honour | -0.265 |
culosis | -0.245 |
Token | DM |
Token ID | 23127 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
ramid | +1.591 |
itect | +1.523 |
axter | +1.519 |
eele | +1.512 |
hare | +1.479 |
Neg logit contributions | |
xit | -1.867 |
Uni | -1.826 |
ctors | -1.739 |
Honour | -1.630 |
culosis | -1.516 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ramid | +1.455 |
itect | +1.392 |
axter | +1.389 |
eele | +1.381 |
hare | +1.351 |
Neg logit contributions | |
xit | -1.671 |
Uni | -1.633 |
ctors | -1.554 |
Honour | -1.457 |
culosis | -1.353 |
Token | — |
Token ID | 851 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ramid | +0.548 |
axter | +0.518 |
itect | +0.517 |
eele | +0.512 |
hare | +0.498 |
Neg logit contributions | |
xit | -0.729 |
Uni | -0.715 |
ctors | -0.677 |
Honour | -0.643 |
culosis | -0.599 |
Token | V |
Token ID | 569 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
ramid | +0.334 |
itect | +0.321 |
axter | +0.319 |
eele | +0.317 |
hare | +0.312 |
Neg logit contributions | |
xit | -0.302 |
Uni | -0.297 |
ctors | -0.278 |
Honour | -0.260 |
culosis | -0.239 |
Token | INE |
Token ID | 8881 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
xit | +1.220 |
Uni | +1.193 |
ctors | +1.130 |
Honour | +1.055 |
culosis | +0.979 |
Neg logit contributions | |
ramid | -1.115 |
axter | -1.066 |
itect | -1.062 |
eele | -1.047 |
hare | -1.036 |
Token | : |
Token ID | 25 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
xit | +7.273 |
Uni | +7.007 |
ctors | +6.538 |
Honour | +6.052 |
culosis | +5.720 |
Neg logit contributions | |
ramid | -6.646 |
axter | -6.300 |
eele | -6.205 |
itect | -6.029 |
ippi | -5.987 |
Token | Im |
Token ID | 1846 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
ramid | +0.732 |
axter | +0.702 |
itect | +0.702 |
eele | +0.697 |
hare | +0.683 |
Neg logit contributions | |
xit | -0.686 |
Uni | -0.672 |
ctors | -0.633 |
Honour | -0.591 |
culosis | -0.546 |
Token | Justin |
Token ID | 33229 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
ramid | +0.155 |
itect | +0.147 |
axter | +0.146 |
eele | +0.146 |
hare | +0.142 |
Neg logit contributions | |
xit | -0.211 |
Uni | -0.207 |
ctors | -0.197 |
Honour | -0.186 |
culosis | -0.175 |
Token | Ray |
Token ID | 19591 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
xit | +1.953 |
Uni | +1.919 |
ctors | +1.800 |
Honour | +1.702 |
culosis | +1.587 |
Neg logit contributions | |
ramid | -1.745 |
axter | -1.641 |
itect | -1.640 |
eele | -1.623 |
hare | -1.588 |
Token | (@ |
Token ID | 4275 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
xit | +0.455 |
Uni | +0.447 |
ctors | +0.423 |
Honour | +0.396 |
culosis | +0.369 |
Neg logit contributions | |
ramid | -0.402 |
axter | -0.383 |
itect | -0.382 |
eele | -0.379 |
hare | -0.372 |
Token | the |
Token ID | 262 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
Uni | +2.083 |
xit | +2.047 |
ctors | +1.933 |
Honour | +1.827 |
CV | +1.611 |
Neg logit contributions | |
ramid | -2.413 |
eele | -2.310 |
axter | -2.309 |
itect | -2.257 |
azo | -2.245 |
Token | Early |
Token ID | 12556 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ramid | +1.325 |
axter | +1.264 |
eele | +1.262 |
itect | +1.260 |
hare | +1.229 |
Neg logit contributions | |
xit | -1.319 |
Uni | -1.303 |
ctors | -1.225 |
Honour | -1.158 |
culosis | -1.057 |
Token | Access |
Token ID | 8798 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
xit | +1.895 |
Uni | +1.866 |
ctors | +1.625 |
Honour | +1.491 |
culosis | +1.212 |
Neg logit contributions | |
ramid | -4.498 |
axter | -4.364 |
eele | -4.342 |
itect | -4.327 |
hare | -4.249 |
Token | version |
Token ID | 2196 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
Uni | +2.056 |
xit | +2.052 |
ctors | +1.890 |
Honour | +1.788 |
culosis | +1.600 |
Neg logit contributions | |
ramid | -2.535 |
eele | -2.426 |
axter | -2.418 |
itect | -2.385 |
olyn | -2.353 |
Token | on |
Token ID | 319 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
xit | +1.606 |
Uni | +1.599 |
ctors | +1.469 |
Honour | +1.398 |
culosis | +1.248 |
Neg logit contributions | |
ramid | -1.859 |
eele | -1.764 |
axter | -1.761 |
itect | -1.737 |
olyn | -1.705 |
Token | Steam |
Token ID | 9094 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
xit | +0.221 |
Uni | +0.220 |
ctors | +0.204 |
Honour | +0.191 |
culosis | +0.172 |
Neg logit contributions | |
ramid | -0.280 |
axter | -0.270 |
eele | -0.268 |
itect | -0.268 |
hare | -0.261 |
Token | and |
Token ID | 290 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Uni | +5.972 |
xit | +5.743 |
ctors | +5.368 |
Honour | +5.158 |
CV | +4.650 |
Neg logit contributions | |
ramid | -7.121 |
axter | -6.851 |
eele | -6.823 |
itect | -6.663 |
azo | -6.585 |
Token | you |
Token ID | 345 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Uni | +0.938 |
xit | +0.934 |
ctors | +0.869 |
Honour | +0.822 |
culosis | +0.744 |
Neg logit contributions | |
ramid | -0.988 |
eele | -0.944 |
axter | -0.940 |
itect | -0.936 |
olyn | -0.909 |
Token | 'll |
Token ID | 1183 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
ramid | +0.525 |
eele | +0.505 |
itect | +0.503 |
axter | +0.503 |
hare | +0.486 |
Neg logit contributions | |
xit | -0.493 |
Uni | -0.488 |
ctors | -0.462 |
Honour | -0.430 |
culosis | -0.393 |
Token | soon |
Token ID | 2582 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
xit | +1.099 |
Uni | +1.082 |
ctors | +1.034 |
Honour | +0.950 |
culosis | +0.854 |
Neg logit contributions | |
ramid | -1.337 |
eele | -1.281 |
itect | -1.274 |
axter | -1.270 |
olyn | -1.244 |
Token | be |
Token ID | 307 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
xit | +0.262 |
Uni | +0.257 |
ctors | +0.245 |
Honour | +0.226 |
culosis | +0.208 |
Neg logit contributions | |
ramid | -0.287 |
eele | -0.275 |
itect | -0.274 |
axter | -0.274 |
olyn | -0.266 |
Token | was |
Token ID | 373 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
xit | +0.942 |
Uni | +0.929 |
ctors | +0.875 |
Honour | +0.816 |
culosis | +0.741 |
Neg logit contributions | |
ramid | -0.994 |
itect | -0.951 |
axter | -0.950 |
eele | -0.942 |
hare | -0.921 |
Token | eventually |
Token ID | 4191 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
xit | +0.101 |
Uni | +0.100 |
ctors | +0.094 |
Honour | +0.088 |
culosis | +0.080 |
Neg logit contributions | |
ramid | -0.105 |
itect | -0.101 |
eele | -0.100 |
axter | -0.099 |
hare | -0.097 |
Token | taken |
Token ID | 2077 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
ramid | +0.318 |
itect | +0.306 |
eele | +0.304 |
axter | +0.302 |
hare | +0.295 |
Neg logit contributions | |
xit | -0.315 |
Uni | -0.310 |
ctors | -0.293 |
Honour | -0.274 |
culosis | -0.250 |
Token | to |
Token ID | 284 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
ramid | +0.206 |
itect | +0.198 |
eele | +0.196 |
axter | +0.195 |
hare | +0.191 |
Neg logit contributions | |
xit | -0.209 |
Uni | -0.207 |
ctors | -0.195 |
Honour | -0.182 |
culosis | -0.168 |
Token | the |
Token ID | 262 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ramid | +1.652 |
itect | +1.588 |
axter | +1.587 |
eele | +1.579 |
hare | +1.549 |
Neg logit contributions | |
xit | -1.621 |
Uni | -1.581 |
ctors | -1.502 |
Honour | -1.399 |
culosis | -1.295 |
Token | Gross |
Token ID | 21796 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
ramid | +0.628 |
itect | +0.600 |
axter | +0.596 |
eele | +0.594 |
hare | +0.581 |
Neg logit contributions | |
xit | -0.780 |
Uni | -0.775 |
ctors | -0.732 |
Honour | -0.692 |
culosis | -0.642 |
Token | man |
Token ID | 805 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Uni | +7.108 |
xit | +7.048 |
ctors | +6.825 |
Honour | +6.231 |
culosis | +5.870 |
Neg logit contributions | |
ramid | -5.881 |
axter | -5.604 |
hare | -5.390 |
eele | -5.380 |
itect | -5.356 |
Token | Burn |
Token ID | 8942 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ramid | +0.250 |
itect | +0.240 |
axter | +0.238 |
eele | +0.237 |
hare | +0.233 |
Neg logit contributions | |
xit | -0.292 |
Uni | -0.290 |
ctors | -0.275 |
Honour | -0.258 |
culosis | -0.241 |
Token | Center |
Token ID | 3337 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
xit | +0.465 |
Uni | +0.461 |
ctors | +0.433 |
Honour | +0.405 |
culosis | +0.374 |
Neg logit contributions | |
ramid | -0.501 |
itect | -0.479 |
axter | -0.478 |
eele | -0.477 |
hare | -0.467 |
Token | at |
Token ID | 379 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
xit | +0.710 |
Uni | +0.706 |
ctors | +0.661 |
Honour | +0.619 |
culosis | +0.574 |
Neg logit contributions | |
ramid | -0.719 |
itect | -0.689 |
eele | -0.686 |
axter | -0.685 |
hare | -0.667 |
Token | the |
Token ID | 262 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Uni | +0.836 |
xit | +0.835 |
ctors | +0.776 |
Honour | +0.727 |
culosis | +0.662 |
Neg logit contributions | |
ramid | -0.942 |
itect | -0.905 |
axter | -0.901 |
eele | -0.892 |
hare | -0.882 |
Token | 27 |
Token ID | 1983 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
xit | +0.591 |
Uni | +0.584 |
ctors | +0.551 |
Honour | +0.514 |
culosis | +0.472 |
Neg logit contributions | |
ramid | -0.567 |
itect | -0.542 |
axter | -0.541 |
eele | -0.539 |
hare | -0.531 |
Token | 70 |
Token ID | 2154 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
ramid | +0.905 |
itect | +0.867 |
axter | +0.865 |
eele | +0.859 |
hare | +0.842 |
Neg logit contributions | |
xit | -1.060 |
Uni | -1.042 |
ctors | -0.989 |
Honour | -0.930 |
culosis | -0.863 |
Token | - |
Token ID | 12 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
ramid | +0.971 |
axter | +0.932 |
itect | +0.932 |
eele | +0.925 |
hare | +0.908 |
Neg logit contributions | |
xit | -1.071 |
Uni | -1.055 |
ctors | -0.996 |
Honour | -0.937 |
culosis | -0.865 |
Token | LED |
Token ID | 30465 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
ramid | +0.765 |
axter | +0.733 |
itect | +0.732 |
eele | +0.728 |
hare | +0.712 |
Neg logit contributions | |
xit | -0.912 |
Uni | -0.897 |
ctors | -0.852 |
Honour | -0.799 |
culosis | -0.742 |
Token | and |
Token ID | 290 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
xit | +0.118 |
Uni | +0.118 |
ctors | +0.110 |
Honour | +0.103 |
culosis | +0.093 |
Neg logit contributions | |
ramid | -0.125 |
axter | -0.121 |
itect | -0.121 |
eele | -0.120 |
hare | -0.118 |
Token | Dell |
Token ID | 23617 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Uni | +0.453 |
xit | +0.452 |
ctors | +0.417 |
Honour | +0.394 |
culosis | +0.351 |
Neg logit contributions | |
ramid | -0.524 |
axter | -0.507 |
itect | -0.505 |
eele | -0.504 |
hare | -0.494 |
Token | U |
Token ID | 471 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
Uni | +6.047 |
xit | +5.645 |
ctors | +5.280 |
Honour | +5.128 |
CV | +4.643 |
Neg logit contributions | |
ramid | -7.199 |
axter | -7.083 |
eele | -7.032 |
itect | -6.927 |
olyn | -6.835 |
Token | 27 |
Token ID | 1983 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
xit | +0.117 |
Uni | +0.115 |
ctors | +0.109 |
Honour | +0.102 |
culosis | +0.095 |
Neg logit contributions | |
ramid | -0.097 |
itect | -0.093 |
axter | -0.093 |
eele | -0.092 |
hare | -0.090 |
Token | 15 |
Token ID | 1314 |
Feature activation | -8.65e-02 |
Pos logit contributions | |
xit | +0.538 |
Uni | +0.533 |
ctors | +0.501 |
Honour | +0.476 |
culosis | +0.436 |
Neg logit contributions | |
ramid | -0.449 |
itect | -0.429 |
axter | -0.428 |
eele | -0.424 |
hare | -0.414 |
Token | H |
Token ID | 39 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
ramid | +0.177 |
itect | +0.170 |
axter | +0.170 |
eele | +0.168 |
hare | +0.165 |
Neg logit contributions | |
xit | -0.205 |
Uni | -0.202 |
ctors | -0.190 |
Honour | -0.180 |
culosis | -0.166 |
Token | which |
Token ID | 543 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ramid | +0.781 |
itect | +0.746 |
axter | +0.746 |
eele | +0.741 |
hare | +0.727 |
Neg logit contributions | |
xit | -0.996 |
Uni | -0.984 |
ctors | -0.932 |
Honour | -0.879 |
culosis | -0.819 |
Token | all |
Token ID | 477 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ramid | +0.344 |
itect | +0.330 |
axter | +0.329 |
eele | +0.328 |
hare | +0.320 |
Neg logit contributions | |
xit | -0.325 |
Uni | -0.318 |
ctors | -0.300 |
Honour | -0.281 |
culosis | -0.256 |
Token | Yog |
Token ID | 31604 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ramid | +2.364 |
itect | +2.267 |
axter | +2.264 |
eele | +2.253 |
hare | +2.208 |
Neg logit contributions | |
xit | -2.485 |
Uni | -2.435 |
ctors | -2.310 |
Honour | -2.162 |
culosis | -2.000 |
Token | venture |
Token ID | 5388 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ramid | +0.566 |
itect | +0.546 |
axter | +0.544 |
eele | +0.542 |
hare | +0.533 |
Neg logit contributions | |
xit | -0.474 |
Uni | -0.461 |
ctors | -0.438 |
Honour | -0.404 |
culosis | -0.370 |
Token | backers |
Token ID | 18917 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
xit | +2.899 |
Uni | +2.845 |
ctors | +2.725 |
Honour | +2.536 |
culosis | +2.310 |
Neg logit contributions | |
ramid | -2.937 |
axter | -2.824 |
eele | -2.804 |
itect | -2.780 |
azo | -2.726 |
Token | a |
Token ID | 257 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
ramid | +0.513 |
itect | +0.491 |
axter | +0.490 |
eele | +0.489 |
hare | +0.476 |
Neg logit contributions | |
xit | -0.465 |
Uni | -0.459 |
ctors | -0.428 |
Honour | -0.403 |
culosis | -0.365 |
Token | Steam |
Token ID | 9094 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
xit | +0.536 |
Uni | +0.536 |
ctors | +0.494 |
Honour | +0.449 |
culosis | +0.395 |
Neg logit contributions | |
ramid | -0.851 |
axter | -0.828 |
itect | -0.828 |
eele | -0.819 |
hare | -0.800 |
Token | Early |
Token ID | 12556 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
Uni | +4.800 |
xit | +4.608 |
ctors | +4.192 |
Honour | +4.062 |
CV | +3.533 |
Neg logit contributions | |
ramid | -7.957 |
itect | -7.717 |
axter | -7.695 |
ippi | -7.565 |
eele | -7.545 |
Token | Access |
Token ID | 8798 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Uni | +2.734 |
xit | +2.692 |
ctors | +2.274 |
Honour | +2.224 |
CV | +1.773 |
Neg logit contributions | |
ramid | -6.604 |
axter | -6.476 |
eele | -6.446 |
itect | -6.423 |
ippi | -6.238 |
Token | key |
Token ID | 1994 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
Uni | +2.458 |
xit | +2.450 |
ctors | +2.241 |
Honour | +2.152 |
culosis | +1.885 |
Neg logit contributions | |
ramid | -3.349 |
axter | -3.235 |
itect | -3.216 |
eele | -3.207 |
ippi | -3.125 |
Token | for |
Token ID | 329 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
xit | +0.155 |
Uni | +0.153 |
ctors | +0.144 |
Honour | +0.135 |
culosis | +0.122 |
Neg logit contributions | |
ramid | -0.158 |
itect | -0.150 |
axter | -0.150 |
eele | -0.149 |
olyn | -0.144 |
Token | T |
Token ID | 309 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Uni | +1.616 |
xit | +1.599 |
ctors | +1.486 |
Honour | +1.429 |
culosis | +1.263 |
Neg logit contributions | |
ramid | -1.667 |
itect | -1.578 |
axter | -1.578 |
eele | -1.562 |
hare | -1.532 |
Token | border |
Token ID | 4865 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
xit | +1.368 |
Uni | +1.355 |
ctors | +1.266 |
Honour | +1.179 |
culosis | +1.066 |
Neg logit contributions | |
ramid | -1.561 |
itect | -1.511 |
axter | -1.511 |
eele | -1.489 |
hare | -1.469 |
Token | , |
Token ID | 11 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
xit | +1.498 |
Uni | +1.491 |
ctors | +1.388 |
Honour | +1.302 |
culosis | +1.195 |
Neg logit contributions | |
ramid | -1.606 |
axter | -1.533 |
itect | -1.529 |
eele | -1.508 |
hare | -1.485 |
Token | and |
Token ID | 290 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
xit | +1.195 |
Uni | +1.185 |
ctors | +1.102 |
Honour | +1.029 |
culosis | +0.928 |
Neg logit contributions | |
ramid | -1.392 |
axter | -1.323 |
itect | -1.320 |
eele | -1.318 |
hare | -1.294 |
Token | pro |
Token ID | 386 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
xit | +0.574 |
Uni | +0.563 |
ctors | +0.530 |
Honour | +0.493 |
culosis | +0.449 |
Neg logit contributions | |
ramid | -0.642 |
itect | -0.613 |
axter | -0.611 |
eele | -0.607 |
hare | -0.599 |
Token | - |
Token ID | 12 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
xit | +1.763 |
Uni | +1.729 |
ctors | +1.652 |
Honour | +1.535 |
culosis | +1.429 |
Neg logit contributions | |
ramid | -1.589 |
itect | -1.520 |
axter | -1.514 |
eele | -1.510 |
hare | -1.481 |
Token | Russia |
Token ID | 16347 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
xit | +3.799 |
Uni | +3.646 |
ctors | +3.373 |
Honour | +3.031 |
chance | +2.872 |
Neg logit contributions | |
ramid | -5.075 |
itect | -4.875 |
eele | -4.837 |
axter | -4.816 |
ippi | -4.761 |
Token | militias |
Token ID | 28195 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Uni | +5.973 |
xit | +5.761 |
ctors | +5.333 |
Honour | +5.118 |
CV | +4.597 |
Neg logit contributions | |
ramid | -7.135 |
itect | -6.819 |
eele | -6.569 |
axter | -6.564 |
azo | -6.461 |
Token | are |
Token ID | 389 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
ramid | +0.452 |
axter | +0.433 |
itect | +0.433 |
eele | +0.431 |
hare | +0.420 |
Neg logit contributions | |
xit | -0.472 |
Uni | -0.465 |
ctors | -0.442 |
Honour | -0.413 |
culosis | -0.381 |
Token | operating |
Token ID | 5361 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
xit | +0.021 |
Uni | +0.021 |
ctors | +0.020 |
Honour | +0.018 |
culosis | +0.017 |
Neg logit contributions | |
ramid | -0.023 |
itect | -0.023 |
axter | -0.022 |
eele | -0.022 |
hare | -0.022 |
Token | in |
Token ID | 287 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
xit | +0.933 |
Uni | +0.929 |
ctors | +0.862 |
Honour | +0.808 |
culosis | +0.728 |
Neg logit contributions | |
ramid | -1.076 |
itect | -1.032 |
axter | -1.031 |
eele | -1.024 |
azo | -0.994 |
Token | many |
Token ID | 867 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ramid | +0.384 |
itect | +0.368 |
axter | +0.367 |
eele | +0.364 |
hare | +0.358 |
Neg logit contributions | |
xit | -0.361 |
Uni | -0.355 |
ctors | -0.333 |
Honour | -0.313 |
culosis | -0.283 |
Token | s |
Token ID | 82 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
ramid | +0.099 |
axter | +0.094 |
itect | +0.094 |
eele | +0.093 |
hare | +0.091 |
Neg logit contributions | |
xit | -0.153 |
Uni | -0.151 |
ctors | -0.145 |
Honour | -0.136 |
culosis | -0.128 |
Token | – |
Token ID | 784 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
xit | +0.081 |
Uni | +0.080 |
ctors | +0.076 |
Honour | +0.070 |
culosis | +0.065 |
Neg logit contributions | |
ramid | -0.080 |
axter | -0.077 |
itect | -0.077 |
eele | -0.076 |
hare | -0.074 |
Token | in |
Token ID | 287 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
ramid | +0.007 |
axter | +0.006 |
itect | +0.006 |
eele | +0.006 |
hare | +0.006 |
Neg logit contributions | |
xit | -0.006 |
Uni | -0.006 |
ctors | -0.006 |
Honour | -0.006 |
culosis | -0.005 |
Token | effect |
Token ID | 1245 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
xit | +1.255 |
Uni | +1.252 |
ctors | +1.172 |
Honour | +1.106 |
culosis | +1.005 |
Neg logit contributions | |
ramid | -1.276 |
axter | -1.219 |
eele | -1.216 |
itect | -1.210 |
hare | -1.186 |
Token | , |
Token ID | 11 |
Feature activation | +3.10e-03 |
Pos logit contributions | |
xit | +0.795 |
Uni | +0.791 |
ctors | +0.739 |
Honour | +0.689 |
culosis | +0.626 |
Neg logit contributions | |
ramid | -0.814 |
itect | -0.782 |
axter | -0.782 |
eele | -0.775 |
hare | -0.759 |
Token | forc |
Token ID | 24686 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
xit | +0.007 |
Uni | +0.007 |
ctors | +0.006 |
Honour | +0.006 |
culosis | +0.005 |
Neg logit contributions | |
ramid | -0.007 |
itect | -0.007 |
axter | -0.007 |
eele | -0.007 |
hare | -0.007 |
Token | ings |
Token ID | 654 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
xit | +5.220 |
ctors | +5.154 |
Uni | +5.145 |
Honour | +4.531 |
nces | +4.114 |
Neg logit contributions | |
ramid | -7.245 |
axter | -7.121 |
hare | -7.000 |
itect | -6.843 |
eele | -6.798 |
Token | that |
Token ID | 326 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
xit | +0.677 |
Uni | +0.668 |
ctors | +0.629 |
Honour | +0.587 |
culosis | +0.536 |
Neg logit contributions | |
ramid | -0.676 |
axter | -0.650 |
itect | -0.648 |
eele | -0.646 |
hare | -0.626 |
Token | occur |
Token ID | 3051 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
ramid | +0.041 |
itect | +0.039 |
axter | +0.039 |
eele | +0.039 |
hare | +0.038 |
Neg logit contributions | |
xit | -0.042 |
Uni | -0.042 |
ctors | -0.040 |
Honour | -0.037 |
culosis | -0.034 |
Token | because |
Token ID | 780 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
xit | +0.104 |
Uni | +0.102 |
ctors | +0.096 |
Honour | +0.089 |
culosis | +0.082 |
Neg logit contributions | |
ramid | -0.108 |
axter | -0.104 |
itect | -0.103 |
eele | -0.103 |
hare | -0.100 |
Token | a |
Token ID | 257 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
ramid | +0.698 |
itect | +0.670 |
axter | +0.670 |
eele | +0.667 |
hare | +0.655 |
Neg logit contributions | |
xit | -0.620 |
Uni | -0.607 |
ctors | -0.573 |
Honour | -0.532 |
culosis | -0.488 |
Token | support |
Token ID | 1104 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
ramid | +0.798 |
axter | +0.764 |
itect | +0.763 |
eele | +0.758 |
hare | +0.741 |
Neg logit contributions | |
xit | -0.921 |
Uni | -0.913 |
ctors | -0.869 |
Honour | -0.816 |
culosis | -0.755 |
Token | Civil |
Token ID | 7511 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ramid | +2.223 |
itect | +2.136 |
axter | +2.132 |
eele | +2.122 |
hare | +2.082 |
Neg logit contributions | |
xit | -2.179 |
Uni | -2.132 |
ctors | -2.020 |
Honour | -1.883 |
culosis | -1.740 |
Token | Rights |
Token ID | 6923 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
ramid | +2.723 |
itect | +2.639 |
axter | +2.604 |
eele | +2.601 |
hare | +2.543 |
Neg logit contributions | |
xit | -3.132 |
Uni | -3.042 |
ctors | -2.922 |
Honour | -2.698 |
culosis | -2.538 |
Token | Director |
Token ID | 5890 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
ramid | +1.111 |
axter | +1.062 |
itect | +1.059 |
eele | +1.058 |
hare | +1.037 |
Neg logit contributions | |
xit | -1.117 |
Uni | -1.101 |
ctors | -1.041 |
Honour | -0.979 |
culosis | -0.898 |
Token | V |
Token ID | 569 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
xit | +1.696 |
Uni | +1.690 |
ctors | +1.578 |
Honour | +1.500 |
culosis | +1.371 |
Neg logit contributions | |
ramid | -1.735 |
itect | -1.638 |
axter | -1.623 |
eele | -1.606 |
hare | -1.579 |
Token | elve |
Token ID | 9954 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
xit | +0.467 |
Uni | +0.457 |
ctors | +0.435 |
Honour | +0.408 |
culosis | +0.378 |
Neg logit contributions | |
ramid | -0.362 |
axter | -0.346 |
itect | -0.344 |
eele | -0.339 |
hare | -0.335 |
Token | ta |
Token ID | 8326 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
xit | +6.315 |
Uni | +5.999 |
ctors | +5.816 |
Honour | +5.254 |
nces | +4.909 |
Neg logit contributions | |
ramid | -6.535 |
axter | -6.224 |
itect | -6.187 |
hare | -6.043 |
eele | -6.033 |
Token | Gol |
Token ID | 26849 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ramid | +0.652 |
itect | +0.623 |
axter | +0.623 |
eele | +0.617 |
hare | +0.607 |
Neg logit contributions | |
xit | -0.606 |
Uni | -0.597 |
ctors | -0.560 |
Honour | -0.524 |
culosis | -0.479 |
Token | ight |
Token ID | 432 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
xit | +0.383 |
Uni | +0.375 |
ctors | +0.360 |
Honour | +0.336 |
culosis | +0.316 |
Neg logit contributions | |
ramid | -0.281 |
itect | -0.268 |
axter | -0.266 |
eele | -0.264 |
hare | -0.259 |
Token | ly |
Token ID | 306 |
Feature activation | +7.29e-03 |
Pos logit contributions | |
ramid | +0.778 |
itect | +0.755 |
axter | +0.754 |
eele | +0.747 |
hare | +0.738 |
Neg logit contributions | |
xit | -0.451 |
Uni | -0.438 |
ctors | -0.404 |
Honour | -0.370 |
culosis | -0.322 |
Token | - |
Token ID | 12 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
xit | +0.017 |
Uni | +0.017 |
ctors | +0.016 |
Honour | +0.015 |
culosis | +0.014 |
Neg logit contributions | |
ramid | -0.015 |
axter | -0.015 |
itect | -0.015 |
eele | -0.014 |
hare | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
ramid | +1.250 |
itect | +1.198 |
axter | +1.197 |
eele | +1.193 |
hare | +1.168 |
Neg logit contributions | |
xit | -1.172 |
Uni | -1.152 |
ctors | -1.088 |
Honour | -1.013 |
culosis | -0.929 |
Token |
|
Token ID | 198 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
ramid | +0.432 |
axter | +0.417 |
eele | +0.414 |
itect | +0.414 |
hare | +0.403 |
Neg logit contributions | |
xit | -0.380 |
Uni | -0.372 |
ctors | -0.352 |
Honour | -0.328 |
culosis | -0.296 |
Token | impl |
Token ID | 23928 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ramid | +0.886 |
axter | +0.850 |
itect | +0.847 |
eele | +0.845 |
hare | +0.823 |
Neg logit contributions | |
xit | -0.930 |
Uni | -0.907 |
ctors | -0.866 |
Honour | -0.805 |
culosis | -0.746 |
Token | Board |
Token ID | 5926 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
Uni | +2.523 |
xit | +2.493 |
ctors | +2.362 |
Honour | +2.216 |
CV | +1.987 |
Neg logit contributions | |
ramid | -2.316 |
axter | -2.213 |
itect | -2.175 |
eele | -2.171 |
hare | -2.123 |
Token | { |
Token ID | 1391 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ramid | +0.171 |
itect | +0.163 |
axter | +0.163 |
eele | +0.162 |
hare | +0.157 |
Neg logit contributions | |
xit | -0.247 |
Uni | -0.243 |
ctors | -0.231 |
Honour | -0.218 |
culosis | -0.204 |
Token | pub |
Token ID | 2240 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
xit | +0.229 |
Uni | +0.225 |
ctors | +0.212 |
Honour | +0.198 |
culosis | +0.182 |
Neg logit contributions | |
ramid | -0.233 |
axter | -0.222 |
itect | -0.222 |
eele | -0.221 |
hare | -0.216 |
Token | fn |
Token ID | 24714 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
Uni | +5.950 |
xit | +5.731 |
ctors | +5.421 |
Honour | +4.885 |
CV | +4.519 |
Neg logit contributions | |
ramid | -6.862 |
axter | -6.599 |
eele | -6.582 |
ippi | -6.569 |
itect | -6.478 |
Token | copy |
Token ID | 4866 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
xit | +1.794 |
Uni | +1.794 |
ctors | +1.676 |
Honour | +1.548 |
culosis | +1.397 |
Neg logit contributions | |
ramid | -1.937 |
itect | -1.855 |
axter | -1.829 |
eele | -1.827 |
ippi | -1.804 |
Token | _ |
Token ID | 62 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
xit | +0.528 |
Uni | +0.516 |
ctors | +0.492 |
Honour | +0.459 |
culosis | +0.425 |
Neg logit contributions | |
ramid | -0.478 |
itect | -0.458 |
axter | -0.456 |
eele | -0.455 |
hare | -0.444 |
Token | board |
Token ID | 3526 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
xit | +0.292 |
Uni | +0.282 |
ctors | +0.270 |
Honour | +0.248 |
culosis | +0.230 |
Neg logit contributions | |
ramid | -0.304 |
itect | -0.291 |
axter | -0.291 |
eele | -0.290 |
hare | -0.281 |
Token | ( |
Token ID | 357 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
xit | +1.682 |
Uni | +1.633 |
ctors | +1.561 |
Honour | +1.448 |
culosis | +1.334 |
Neg logit contributions | |
ramid | -1.570 |
itect | -1.501 |
eele | -1.494 |
axter | -1.493 |
hare | -1.451 |
Token | prime |
Token ID | 6994 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
ramid | +0.798 |
itect | +0.768 |
axter | +0.763 |
eele | +0.761 |
hare | +0.741 |
Neg logit contributions | |
xit | -0.764 |
Uni | -0.755 |
ctors | -0.707 |
Honour | -0.664 |
culosis | -0.606 |
Token | measure |
Token ID | 3953 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ramid | +1.545 |
itect | +1.479 |
axter | +1.478 |
eele | +1.470 |
hare | +1.442 |
Neg logit contributions | |
xit | -1.805 |
Uni | -1.768 |
ctors | -1.683 |
Honour | -1.579 |
culosis | -1.474 |
Token | of |
Token ID | 286 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
ramid | +0.553 |
itect | +0.533 |
axter | +0.530 |
eele | +0.527 |
hare | +0.515 |
Neg logit contributions | |
xit | -0.522 |
Uni | -0.513 |
ctors | -0.483 |
Honour | -0.451 |
culosis | -0.413 |
Token | activity |
Token ID | 3842 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
ramid | +0.930 |
itect | +0.894 |
axter | +0.888 |
eele | +0.885 |
hare | +0.866 |
Neg logit contributions | |
xit | -0.939 |
Uni | -0.922 |
ctors | -0.870 |
Honour | -0.815 |
culosis | -0.750 |
Token | - |
Token ID | 532 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
ramid | +0.856 |
itect | +0.821 |
axter | +0.820 |
eele | +0.815 |
hare | +0.794 |
Neg logit contributions | |
xit | -0.851 |
Uni | -0.839 |
ctors | -0.792 |
Honour | -0.741 |
culosis | -0.678 |
Token | gross |
Token ID | 10319 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
xit | +0.656 |
Uni | +0.647 |
ctors | +0.608 |
Honour | +0.569 |
culosis | +0.519 |
Neg logit contributions | |
ramid | -0.668 |
itect | -0.641 |
axter | -0.637 |
eele | -0.637 |
hare | -0.621 |
Token | domestic |
Token ID | 5928 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
Uni | +5.579 |
xit | +5.475 |
ctors | +4.905 |
Honour | +4.545 |
CV | +4.086 |
Neg logit contributions | |
ramid | -7.486 |
itect | -7.200 |
axter | -7.083 |
eele | -7.081 |
azo | -6.882 |
Token | product |
Token ID | 1720 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Uni | +1.699 |
xit | +1.678 |
ctors | +1.587 |
Honour | +1.512 |
culosis | +1.369 |
Neg logit contributions | |
ramid | -1.465 |
itect | -1.383 |
axter | -1.379 |
eele | -1.363 |
olyn | -1.336 |
Token | - |
Token ID | 532 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
xit | +0.666 |
Uni | +0.656 |
ctors | +0.622 |
Honour | +0.582 |
culosis | +0.540 |
Neg logit contributions | |
ramid | -0.601 |
itect | -0.579 |
axter | -0.576 |
eele | -0.574 |
hare | -0.557 |
Token | due |
Token ID | 2233 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
xit | +1.128 |
Uni | +1.114 |
ctors | +1.047 |
Honour | +0.983 |
culosis | +0.889 |
Neg logit contributions | |
ramid | -1.212 |
axter | -1.159 |
itect | -1.158 |
eele | -1.147 |
hare | -1.120 |
Token | to |
Token ID | 284 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ramid | +0.315 |
itect | +0.302 |
axter | +0.301 |
eele | +0.299 |
hare | +0.293 |
Neg logit contributions | |
xit | -0.333 |
Uni | -0.326 |
ctors | -0.309 |
Honour | -0.290 |
culosis | -0.268 |
Token | snow |
Token ID | 6729 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
Uni | +4.077 |
xit | +3.978 |
ctors | +3.723 |
Honour | +3.434 |
CV | +3.154 |
Neg logit contributions | |
ramid | -5.561 |
eele | -5.387 |
itect | -5.358 |
axter | -5.343 |
hare | -5.214 |
Token | fall |
Token ID | 7207 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
xit | +0.128 |
Uni | +0.126 |
ctors | +0.119 |
Honour | +0.109 |
culosis | +0.101 |
Neg logit contributions | |
ramid | -0.154 |
axter | -0.149 |
itect | -0.148 |
eele | -0.148 |
hare | -0.145 |
Token | and |
Token ID | 290 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
ramid | +0.230 |
axter | +0.222 |
eele | +0.220 |
itect | +0.220 |
hare | +0.214 |
Neg logit contributions | |
xit | -0.225 |
Uni | -0.222 |
ctors | -0.210 |
Honour | -0.195 |
culosis | -0.180 |
Token | above |
Token ID | 2029 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
xit | +0.630 |
Uni | +0.622 |
ctors | +0.582 |
Honour | +0.541 |
culosis | +0.489 |
Neg logit contributions | |
ramid | -0.804 |
itect | -0.781 |
eele | -0.778 |
axter | -0.776 |
hare | -0.759 |
Token | - |
Token ID | 12 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
xit | +0.865 |
Uni | +0.850 |
ctors | +0.807 |
Honour | +0.755 |
culosis | +0.700 |
Neg logit contributions | |
ramid | -0.776 |
itect | -0.744 |
axter | -0.742 |
eele | -0.740 |
hare | -0.723 |
Token | average |
Token ID | 23913 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
xit | +2.862 |
Uni | +2.790 |
ctors | +2.719 |
Honour | +2.532 |
chance | +2.421 |
Neg logit contributions | |
ramid | -1.733 |
eele | -1.639 |
itect | -1.638 |
axter | -1.638 |
olyn | -1.566 |
Token | temperatures |
Token ID | 10101 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
Uni | +5.191 |
xit | +5.005 |
ctors | +4.643 |
Honour | +4.436 |
CV | +4.114 |
Neg logit contributions | |
ramid | -7.338 |
itect | -7.173 |
eele | -7.062 |
axter | -6.913 |
alez | -6.860 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
xit | +1.726 |
Uni | +1.700 |
ctors | +1.587 |
Honour | +1.485 |
culosis | +1.372 |
Neg logit contributions | |
ramid | -1.697 |
axter | -1.631 |
eele | -1.619 |
itect | -1.606 |
olyn | -1.551 |
Token |
|
Token ID | 198 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
xit | +0.253 |
Uni | +0.252 |
ctors | +0.235 |
Honour | +0.219 |
culosis | +0.199 |
Neg logit contributions | |
ramid | -0.286 |
axter | -0.276 |
eele | -0.273 |
itect | -0.272 |
hare | -0.267 |
Token |
|
Token ID | 198 |
Feature activation | +2.93e-03 |
Pos logit contributions | |
xit | +0.496 |
Uni | +0.485 |
ctors | +0.457 |
Honour | +0.426 |
culosis | +0.378 |
Neg logit contributions | |
ramid | -0.599 |
axter | -0.579 |
eele | -0.573 |
itect | -0.570 |
hare | -0.556 |
Token | The |
Token ID | 464 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
xit | +0.007 |
Uni | +0.007 |
ctors | +0.006 |
Honour | +0.006 |
culosis | +0.006 |
Neg logit contributions | |
ramid | -0.006 |
axter | -0.006 |
eele | -0.006 |
itect | -0.006 |
hare | -0.006 |
Token | 's |
Token ID | 338 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
ramid | +1.599 |
itect | +1.541 |
axter | +1.535 |
eele | +1.531 |
hare | +1.500 |
Neg logit contributions | |
xit | -1.702 |
Uni | -1.665 |
ctors | -1.584 |
Honour | -1.478 |
culosis | -1.377 |
Token | subsequent |
Token ID | 8840 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ramid | +1.203 |
itect | +1.154 |
axter | +1.150 |
eele | +1.143 |
hare | +1.122 |
Neg logit contributions | |
xit | -1.181 |
Uni | -1.159 |
ctors | -1.094 |
Honour | -1.027 |
culosis | -0.940 |
Token | offer |
Token ID | 2897 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
ramid | +3.091 |
itect | +2.977 |
axter | +2.975 |
eele | +2.970 |
hare | +2.916 |
Neg logit contributions | |
xit | -2.932 |
Uni | -2.854 |
ctors | -2.726 |
Honour | -2.504 |
culosis | -2.350 |
Token | of |
Token ID | 286 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
ramid | +1.826 |
itect | +1.753 |
axter | +1.750 |
eele | +1.743 |
hare | +1.712 |
Neg logit contributions | |
xit | -1.915 |
Uni | -1.877 |
ctors | -1.784 |
Honour | -1.664 |
culosis | -1.548 |
Token | a |
Token ID | 257 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
ramid | +1.187 |
itect | +1.141 |
axter | +1.137 |
eele | +1.130 |
hare | +1.108 |
Neg logit contributions | |
xit | -1.106 |
Uni | -1.087 |
ctors | -1.021 |
Honour | -0.957 |
culosis | -0.873 |
Token | Steam |
Token ID | 9094 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
ramid | +0.524 |
itect | +0.504 |
axter | +0.504 |
eele | +0.499 |
hare | +0.488 |
Neg logit contributions | |
xit | -0.477 |
Uni | -0.471 |
ctors | -0.443 |
Honour | -0.413 |
culosis | -0.375 |
Token | key |
Token ID | 1994 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
Uni | +5.782 |
xit | +5.687 |
ctors | +5.192 |
Honour | +5.116 |
culosis | +4.542 |
Neg logit contributions | |
ramid | -6.671 |
axter | -6.532 |
eele | -6.429 |
itect | -6.420 |
ippi | -6.367 |
Token | for |
Token ID | 329 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
ramid | +0.186 |
itect | +0.178 |
axter | +0.177 |
eele | +0.175 |
ippi | +0.171 |
Neg logit contributions | |
xit | -0.195 |
Uni | -0.192 |
ctors | -0.181 |
Honour | -0.171 |
culosis | -0.156 |
Token | open |
Token ID | 1280 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
xit | +1.208 |
Uni | +1.200 |
ctors | +1.111 |
Honour | +1.058 |
culosis | +0.935 |
Neg logit contributions | |
ramid | -1.374 |
itect | -1.313 |
axter | -1.302 |
eele | -1.294 |
hare | -1.269 |
Token | - |
Token ID | 12 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
xit | +0.516 |
Uni | +0.509 |
ctors | +0.482 |
Honour | +0.449 |
culosis | +0.413 |
Neg logit contributions | |
ramid | -0.529 |
axter | -0.508 |
itect | -0.506 |
eele | -0.504 |
hare | -0.492 |
Token | world |
Token ID | 6894 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
xit | +1.017 |
Uni | +0.993 |
ctors | +0.933 |
Honour | +0.834 |
culosis | +0.754 |
Neg logit contributions | |
ramid | -1.698 |
axter | -1.644 |
itect | -1.638 |
eele | -1.636 |
olyn | -1.592 |
Token | heads |
Token ID | 6665 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ramid | +0.769 |
itect | +0.745 |
axter | +0.744 |
eele | +0.741 |
hare | +0.730 |
Neg logit contributions | |
xit | -0.467 |
Uni | -0.454 |
ctors | -0.422 |
Honour | -0.384 |
culosis | -0.344 |
Token | at |
Token ID | 379 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
xit | +1.975 |
Uni | +1.958 |
ctors | +1.807 |
Honour | +1.707 |
culosis | +1.524 |
Neg logit contributions | |
ramid | -2.473 |
eele | -2.371 |
axter | -2.365 |
itect | -2.342 |
olyn | -2.296 |
Token | the |
Token ID | 262 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
xit | +0.989 |
Uni | +0.982 |
ctors | +0.905 |
Honour | +0.859 |
culosis | +0.773 |
Neg logit contributions | |
ramid | -1.029 |
itect | -0.996 |
axter | -0.985 |
eele | -0.983 |
hare | -0.953 |
Token | irrational |
Token ID | 25086 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
xit | +0.599 |
Uni | +0.596 |
ctors | +0.545 |
Honour | +0.520 |
culosis | +0.462 |
Neg logit contributions | |
ramid | -0.704 |
itect | -0.678 |
axter | -0.674 |
eele | -0.673 |
hare | -0.656 |
Token | ex |
Token ID | 409 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ramid | +3.576 |
itect | +3.461 |
axter | +3.455 |
eele | +3.427 |
hare | +3.393 |
Neg logit contributions | |
xit | -3.562 |
Uni | -3.456 |
ctors | -3.318 |
Honour | -3.063 |
culosis | -2.870 |
Token | uber |
Token ID | 18478 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
ramid | +0.273 |
axter | +0.261 |
itect | +0.260 |
eele | +0.260 |
hare | +0.253 |
Neg logit contributions | |
xit | -0.281 |
Uni | -0.274 |
ctors | -0.261 |
Honour | -0.242 |
culosis | -0.225 |
Token | ance |
Token ID | 590 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
xit | +6.894 |
Uni | +6.757 |
ctors | +6.540 |
culosis | +6.020 |
Honour | +5.994 |
Neg logit contributions | |
ramid | -5.713 |
eele | -5.394 |
axter | -5.393 |
olyn | -5.248 |
itect | -5.225 |
Token | that |
Token ID | 326 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
xit | +0.559 |
Uni | +0.549 |
ctors | +0.513 |
Honour | +0.477 |
culosis | +0.434 |
Neg logit contributions | |
ramid | -0.636 |
itect | -0.608 |
eele | -0.608 |
axter | -0.608 |
hare | -0.591 |
Token | once |
Token ID | 1752 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ramid | +0.292 |
itect | +0.281 |
axter | +0.278 |
eele | +0.277 |
hare | +0.273 |
Neg logit contributions | |
xit | -0.284 |
Uni | -0.279 |
ctors | -0.262 |
Honour | -0.246 |
culosis | -0.225 |
Token | valued |
Token ID | 17560 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
ramid | +0.611 |
itect | +0.585 |
axter | +0.584 |
eele | +0.581 |
hare | +0.568 |
Neg logit contributions | |
xit | -0.632 |
Uni | -0.621 |
ctors | -0.587 |
Honour | -0.550 |
culosis | -0.508 |
Token | a |
Token ID | 257 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
ramid | +2.170 |
axter | +2.092 |
itect | +2.090 |
eele | +2.081 |
hare | +2.052 |
Neg logit contributions | |
xit | -1.920 |
Uni | -1.872 |
ctors | -1.779 |
Honour | -1.644 |
culosis | -1.520 |
Token | work |
Token ID | 670 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
xit | +0.052 |
Uni | +0.052 |
ctors | +0.049 |
Honour | +0.045 |
culosis | +0.041 |
Neg logit contributions | |
ramid | -0.055 |
axter | -0.052 |
eele | -0.052 |
itect | -0.051 |
hare | -0.051 |
Token | ! |
Token ID | 0 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
ramid | +0.995 |
axter | +0.950 |
itect | +0.949 |
eele | +0.947 |
hare | +0.924 |
Neg logit contributions | |
xit | -1.120 |
Uni | -1.101 |
ctors | -1.045 |
Honour | -0.979 |
culosis | -0.909 |
Token |
|
Token ID | 198 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
ramid | +1.197 |
axter | +1.146 |
itect | +1.143 |
eele | +1.140 |
hare | +1.115 |
Neg logit contributions | |
xit | -1.095 |
Uni | -1.080 |
ctors | -1.016 |
Honour | -0.949 |
culosis | -0.866 |
Token |
|
Token ID | 198 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
ramid | +0.579 |
axter | +0.558 |
itect | +0.555 |
eele | +0.554 |
hare | +0.541 |
Neg logit contributions | |
xit | -0.518 |
Uni | -0.507 |
ctors | -0.479 |
Honour | -0.447 |
culosis | -0.405 |
Token | The |
Token ID | 464 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ramid | +0.799 |
axter | +0.764 |
eele | +0.762 |
itect | +0.761 |
hare | +0.737 |
Neg logit contributions | |
xit | -0.895 |
Uni | -0.871 |
ctors | -0.836 |
Honour | -0.778 |
culosis | -0.720 |
Token | Basics |
Token ID | 45884 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
ramid | +0.381 |
axter | +0.366 |
eele | +0.365 |
itect | +0.363 |
hare | +0.355 |
Neg logit contributions | |
xit | -0.367 |
Uni | -0.366 |
ctors | -0.343 |
Honour | -0.322 |
culosis | -0.290 |
Token | of |
Token ID | 286 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Uni | +5.324 |
xit | +5.225 |
ctors | +4.893 |
Honour | +4.570 |
culosis | +3.964 |
Neg logit contributions | |
ramid | -7.142 |
eele | -6.782 |
axter | -6.771 |
olyn | -6.617 |
itect | -6.605 |
Token | a |
Token ID | 257 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
Uni | +0.843 |
xit | +0.838 |
ctors | +0.778 |
Honour | +0.734 |
culosis | +0.649 |
Neg logit contributions | |
ramid | -0.988 |
axter | -0.947 |
eele | -0.941 |
itect | -0.941 |
ippi | -0.915 |
Token | Board |
Token ID | 5926 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
xit | +0.716 |
Uni | +0.713 |
ctors | +0.668 |
Honour | +0.622 |
culosis | +0.557 |
Neg logit contributions | |
ramid | -0.803 |
axter | -0.779 |
itect | -0.773 |
eele | -0.769 |
hare | -0.745 |
Token |
|
Token ID | 198 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
xit | +0.325 |
Uni | +0.320 |
ctors | +0.301 |
Honour | +0.281 |
culosis | +0.255 |
Neg logit contributions | |
ramid | -0.353 |
axter | -0.340 |
itect | -0.337 |
eele | -0.337 |
hare | -0.328 |
Token |
|
Token ID | 198 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
ramid | +0.617 |
axter | +0.594 |
itect | +0.590 |
eele | +0.590 |
hare | +0.576 |
Neg logit contributions | |
xit | -0.547 |
Uni | -0.535 |
ctors | -0.506 |
Honour | -0.471 |
culosis | -0.426 |
Token | Campbell |
Token ID | 14327 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
ramid | +0.789 |
itect | +0.758 |
axter | +0.756 |
eele | +0.752 |
hare | +0.739 |
Neg logit contributions | |
xit | -0.735 |
Uni | -0.722 |
ctors | -0.681 |
Honour | -0.636 |
culosis | -0.583 |
Token | himself |
Token ID | 2241 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
xit | +1.683 |
Uni | +1.663 |
ctors | +1.541 |
Honour | +1.464 |
culosis | +1.339 |
Neg logit contributions | |
ramid | -1.739 |
axter | -1.664 |
itect | -1.647 |
eele | -1.639 |
hare | -1.614 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
xit | +2.066 |
Uni | +2.041 |
ctors | +1.909 |
Honour | +1.827 |
culosis | +1.642 |
Neg logit contributions | |
ramid | -2.049 |
itect | -1.947 |
eele | -1.938 |
axter | -1.933 |
hare | -1.877 |
Token | His |
Token ID | 2399 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
xit | +0.284 |
Uni | +0.282 |
ctors | +0.263 |
Honour | +0.249 |
culosis | +0.222 |
Neg logit contributions | |
ramid | -0.319 |
axter | -0.305 |
itect | -0.303 |
eele | -0.302 |
hare | -0.297 |
Token | ex |
Token ID | 409 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Uni | +0.987 |
xit | +0.986 |
ctors | +0.922 |
Honour | +0.876 |
culosis | +0.777 |
Neg logit contributions | |
ramid | -1.089 |
itect | -1.050 |
eele | -1.039 |
axter | -1.038 |
hare | -1.015 |
Token | uber |
Token ID | 18478 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
xit | +0.485 |
Uni | +0.474 |
ctors | +0.451 |
Honour | +0.420 |
culosis | +0.387 |
Neg logit contributions | |
ramid | -0.476 |
eele | -0.452 |
axter | -0.452 |
itect | -0.452 |
hare | -0.442 |
Token | ant |
Token ID | 415 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
xit | +6.889 |
Uni | +6.711 |
ctors | +6.497 |
Honour | +6.007 |
culosis | +5.909 |
Neg logit contributions | |
ramid | -5.551 |
axter | -5.219 |
eele | -5.150 |
itect | -5.049 |
hare | -5.045 |
Token | praise |
Token ID | 13463 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
xit | +0.174 |
Uni | +0.172 |
ctors | +0.162 |
Honour | +0.151 |
culosis | +0.137 |
Neg logit contributions | |
ramid | -0.203 |
itect | -0.195 |
axter | -0.194 |
eele | -0.194 |
hare | -0.189 |
Token | of |
Token ID | 286 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
xit | +1.334 |
Uni | +1.309 |
ctors | +1.228 |
Honour | +1.157 |
culosis | +1.040 |
Neg logit contributions | |
ramid | -1.508 |
itect | -1.437 |
axter | -1.421 |
eele | -1.417 |
hare | -1.395 |
Token | myth |
Token ID | 7918 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
xit | +0.129 |
Uni | +0.127 |
ctors | +0.119 |
Honour | +0.112 |
culosis | +0.102 |
Neg logit contributions | |
ramid | -0.141 |
itect | -0.135 |
axter | -0.134 |
eele | -0.134 |
hare | -0.131 |
Token | is |
Token ID | 318 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ramid | +0.643 |
itect | +0.616 |
axter | +0.615 |
eele | +0.612 |
hare | +0.600 |
Neg logit contributions | |
xit | -0.699 |
Uni | -0.685 |
ctors | -0.652 |
Honour | -0.610 |
culosis | -0.566 |
Token | Def |
Token ID | 2896 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
ramid | +0.859 |
axter | +0.823 |
itect | +0.823 |
eele | +0.819 |
hare | +0.804 |
Neg logit contributions | |
xit | -0.791 |
Uni | -0.779 |
ctors | -0.732 |
Honour | -0.687 |
culosis | -0.628 |
Token | ending |
Token ID | 1571 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
xit | +1.465 |
Uni | +1.437 |
ctors | +1.342 |
Honour | +1.265 |
culosis | +1.166 |
Neg logit contributions | |
ramid | -1.665 |
axter | -1.615 |
itect | -1.611 |
eele | -1.597 |
olyn | -1.552 |
Token | battered |
Token ID | 33613 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Uni | +1.024 |
xit | +1.023 |
ctors | +0.939 |
Honour | +0.911 |
culosis | +0.794 |
Neg logit contributions | |
ramid | -1.239 |
eele | -1.185 |
axter | -1.184 |
itect | -1.180 |
hare | -1.148 |
Token | Women |
Token ID | 6926 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
xit | +0.644 |
Uni | +0.637 |
ctors | +0.600 |
Honour | +0.564 |
culosis | +0.509 |
Neg logit contributions | |
ramid | -0.705 |
axter | -0.676 |
itect | -0.675 |
eele | -0.673 |
hare | -0.656 |
Token | on |
Token ID | 319 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
xit | +2.619 |
Uni | +2.597 |
ctors | +2.461 |
Honour | +2.309 |
culosis | +2.054 |
Neg logit contributions | |
ramid | -2.802 |
axter | -2.643 |
itect | -2.642 |
eele | -2.642 |
hare | -2.604 |
Token | Trial |
Token ID | 21960 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
xit | +0.618 |
Uni | +0.610 |
ctors | +0.569 |
Honour | +0.532 |
culosis | +0.481 |
Neg logit contributions | |
ramid | -0.767 |
axter | -0.739 |
itect | -0.738 |
eele | -0.734 |
hare | -0.721 |
Token | , |
Token ID | 11 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Uni | +5.609 |
xit | +5.577 |
ctors | +5.260 |
Honour | +5.016 |
culosis | +4.484 |
Neg logit contributions | |
ramid | -6.545 |
eele | -6.268 |
itect | -6.252 |
axter | -6.234 |
azo | -6.118 |
Token | will |
Token ID | 481 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
Uni | +1.254 |
xit | +1.253 |
ctors | +1.176 |
Honour | +1.103 |
culosis | +1.000 |
Neg logit contributions | |
ramid | -1.401 |
itect | -1.335 |
eele | -1.335 |
axter | -1.335 |
hare | -1.313 |
Token | be |
Token ID | 307 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
Uni | +1.091 |
xit | +1.089 |
ctors | +1.028 |
Honour | +0.967 |
culosis | +0.868 |
Neg logit contributions | |
ramid | -1.168 |
itect | -1.123 |
axter | -1.115 |
eele | -1.113 |
olyn | -1.083 |
Token | released |
Token ID | 2716 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
Uni | +1.352 |
xit | +1.338 |
ctors | +1.251 |
Honour | +1.193 |
culosis | +1.049 |
Neg logit contributions | |
ramid | -1.450 |
itect | -1.389 |
axter | -1.378 |
eele | -1.378 |
hare | -1.340 |
Token | Dec |
Token ID | 4280 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Uni | +1.098 |
xit | +1.093 |
ctors | +1.009 |
Honour | +0.953 |
culosis | +0.851 |
Neg logit contributions | |
ramid | -1.281 |
itect | -1.229 |
axter | -1.223 |
eele | -1.222 |
azo | -1.186 |
Token | noticeable |
Token ID | 19787 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
xit | +0.787 |
Uni | +0.781 |
ctors | +0.732 |
Honour | +0.689 |
culosis | +0.620 |
Neg logit contributions | |
ramid | -0.806 |
axter | -0.782 |
itect | -0.776 |
eele | -0.773 |
hare | -0.756 |
Token | blurred |
Token ID | 38258 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
ramid | +0.207 |
axter | +0.200 |
itect | +0.200 |
eele | +0.198 |
hare | +0.195 |
Neg logit contributions | |
xit | -0.187 |
Uni | -0.185 |
ctors | -0.173 |
Honour | -0.162 |
culosis | -0.147 |
Token | image |
Token ID | 2939 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
Uni | +1.379 |
xit | +1.359 |
ctors | +1.251 |
Honour | +1.178 |
culosis | +1.027 |
Neg logit contributions | |
ramid | -1.777 |
axter | -1.739 |
itect | -1.725 |
eele | -1.722 |
hare | -1.695 |
Token | . |
Token ID | 13 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
Uni | +1.620 |
xit | +1.597 |
ctors | +1.497 |
Honour | +1.412 |
nces | +1.264 |
Neg logit contributions | |
ramid | -1.699 |
axter | -1.651 |
itect | -1.639 |
eele | -1.631 |
olyn | -1.592 |
Token | The |
Token ID | 383 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ramid | +0.096 |
axter | +0.093 |
itect | +0.092 |
eele | +0.092 |
hare | +0.090 |
Neg logit contributions | |
xit | -0.086 |
Uni | -0.085 |
ctors | -0.079 |
Honour | -0.074 |
culosis | -0.067 |
Token | Dell |
Token ID | 23617 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ramid | +0.390 |
axter | +0.377 |
itect | +0.377 |
eele | +0.374 |
hare | +0.368 |
Neg logit contributions | |
xit | -0.332 |
Uni | -0.329 |
ctors | -0.306 |
Honour | -0.285 |
culosis | -0.259 |
Token | U |
Token ID | 471 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Uni | +5.828 |
xit | +5.382 |
ctors | +4.966 |
Honour | +4.865 |
CV | +4.448 |
Neg logit contributions | |
ramid | -6.678 |
axter | -6.428 |
itect | -6.350 |
eele | -6.303 |
olyn | -6.224 |
Token | 27 |
Token ID | 1983 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
xit | +0.286 |
Uni | +0.282 |
ctors | +0.268 |
Honour | +0.251 |
culosis | +0.234 |
Neg logit contributions | |
ramid | -0.235 |
itect | -0.226 |
axter | -0.225 |
eele | -0.223 |
hare | -0.218 |
Token | 13 |
Token ID | 1485 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
xit | +0.265 |
Uni | +0.260 |
ctors | +0.249 |
Honour | +0.236 |
culosis | +0.220 |
Neg logit contributions | |
ramid | -0.179 |
itect | -0.170 |
axter | -0.170 |
eele | -0.168 |
hare | -0.164 |
Token | HM |
Token ID | 36905 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
ramid | +1.061 |
itect | +1.011 |
axter | +1.011 |
eele | +1.002 |
hare | +0.978 |
Neg logit contributions | |
xit | -1.463 |
Uni | -1.442 |
ctors | -1.370 |
Honour | -1.298 |
culosis | -1.209 |
Token | is |
Token ID | 318 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
ramid | +1.029 |
axter | +0.988 |
itect | +0.988 |
eele | +0.982 |
hare | +0.963 |
Neg logit contributions | |
xit | -1.029 |
Uni | -1.013 |
ctors | -0.955 |
Honour | -0.894 |
culosis | -0.824 |
Token | O |
Token ID | 46 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ramid | +0.008 |
itect | +0.008 |
axter | +0.008 |
eele | +0.008 |
olyn | +0.007 |
Neg logit contributions | |
xit | -0.009 |
Uni | -0.009 |
ctors | -0.009 |
Honour | -0.008 |
culosis | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
xit | +0.229 |
Uni | +0.223 |
ctors | +0.212 |
Honour | +0.197 |
culosis | +0.181 |
Neg logit contributions | |
ramid | -0.239 |
itect | -0.230 |
axter | -0.230 |
eele | -0.228 |
hare | -0.224 |
Token | � |
Token ID | 247 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ramid | +0.802 |
itect | +0.771 |
axter | +0.770 |
eele | +0.766 |
hare | +0.753 |
Neg logit contributions | |
xit | -0.671 |
Uni | -0.654 |
ctors | -0.617 |
Honour | -0.571 |
culosis | -0.525 |
Token | Malley |
Token ID | 33776 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
ramid | +0.420 |
itect | +0.401 |
axter | +0.400 |
eele | +0.397 |
hare | +0.389 |
Neg logit contributions | |
xit | -0.486 |
Uni | -0.475 |
ctors | -0.452 |
Honour | -0.424 |
culosis | -0.395 |
Token | also |
Token ID | 635 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
ramid | +0.154 |
axter | +0.148 |
itect | +0.147 |
eele | +0.146 |
hare | +0.144 |
Neg logit contributions | |
xit | -0.152 |
Uni | -0.149 |
ctors | -0.141 |
Honour | -0.132 |
culosis | -0.121 |
Token | responded |
Token ID | 7082 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
ramid | +1.715 |
itect | +1.645 |
axter | +1.645 |
eele | +1.634 |
hare | +1.600 |
Neg logit contributions | |
xit | -1.595 |
Uni | -1.565 |
ctors | -1.479 |
Honour | -1.379 |
culosis | -1.265 |
Token | to |
Token ID | 284 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
ramid | +5.427 |
eele | +5.249 |
axter | +5.186 |
hare | +5.131 |
itect | +5.131 |
Neg logit contributions | |
xit | -7.297 |
Uni | -7.045 |
ctors | -6.985 |
Honour | -6.399 |
culosis | -6.062 |
Token | President |
Token ID | 1992 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
ramid | +0.829 |
itect | +0.800 |
axter | +0.792 |
eele | +0.786 |
hare | +0.773 |
Neg logit contributions | |
xit | -0.752 |
Uni | -0.744 |
ctors | -0.693 |
Honour | -0.649 |
culosis | -0.596 |
Token | Obama |
Token ID | 2486 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
ramid | +0.151 |
itect | +0.145 |
axter | +0.145 |
eele | +0.144 |
hare | +0.142 |
Neg logit contributions | |
xit | -0.129 |
Uni | -0.127 |
ctors | -0.119 |
Honour | -0.111 |
culosis | -0.101 |
Token | � |
Token ID | 447 |
Feature activation | +8.91e-02 |
Pos logit contributions | |
xit | +0.060 |
Uni | +0.059 |
ctors | +0.056 |
Honour | +0.053 |
culosis | +0.049 |
Neg logit contributions | |
ramid | -0.053 |
axter | -0.050 |
itect | -0.050 |
eele | -0.050 |
hare | -0.049 |
Token | � |
Token ID | 247 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
xit | +0.178 |
Uni | +0.173 |
ctors | +0.162 |
Honour | +0.151 |
culosis | +0.137 |
Neg logit contributions | |
ramid | -0.218 |
itect | -0.209 |
axter | -0.208 |
eele | -0.208 |
hare | -0.205 |
Token | if |
Token ID | 611 |
Feature activation | +9.82e-03 |
Pos logit contributions | |
ramid | +1.351 |
itect | +1.293 |
axter | +1.291 |
eele | +1.280 |
hare | +1.251 |
Neg logit contributions | |
xit | -1.395 |
Uni | -1.380 |
ctors | -1.302 |
Honour | -1.221 |
culosis | -1.121 |
Token | that |
Token ID | 326 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
xit | +0.022 |
Uni | +0.021 |
ctors | +0.020 |
Honour | +0.019 |
culosis | +0.017 |
Neg logit contributions | |
ramid | -0.022 |
itect | -0.021 |
axter | -0.021 |
eele | -0.021 |
olyn | -0.020 |
Token | closer |
Token ID | 5699 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ramid | +0.361 |
itect | +0.348 |
eele | +0.345 |
axter | +0.343 |
hare | +0.334 |
Neg logit contributions | |
xit | -0.382 |
Uni | -0.378 |
ctors | -0.354 |
Honour | -0.335 |
culosis | -0.308 |
Token | was |
Token ID | 373 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
xit | +0.245 |
Uni | +0.244 |
ctors | +0.229 |
Honour | +0.214 |
culosis | +0.196 |
Neg logit contributions | |
ramid | -0.257 |
axter | -0.247 |
eele | -0.246 |
itect | -0.246 |
hare | -0.239 |
Token | Craig |
Token ID | 13854 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ramid | +0.218 |
itect | +0.209 |
eele | +0.206 |
axter | +0.206 |
ippi | +0.200 |
Neg logit contributions | |
xit | -0.199 |
Uni | -0.197 |
ctors | -0.184 |
Honour | -0.174 |
culosis | -0.156 |
Token | Kim |
Token ID | 6502 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
xit | +2.410 |
Uni | +2.353 |
ctors | +2.231 |
Honour | +2.011 |
culosis | +1.905 |
Neg logit contributions | |
ramid | -2.239 |
itect | -2.170 |
axter | -2.149 |
hare | -2.147 |
eele | -2.124 |
Token | b |
Token ID | 65 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
ramid | +5.512 |
axter | +5.237 |
itect | +5.187 |
eele | +5.154 |
azo | +5.047 |
Neg logit contributions | |
xit | -7.433 |
Uni | -7.395 |
ctors | -6.990 |
Honour | -6.651 |
culosis | -6.303 |
Token | rel |
Token ID | 2411 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ramid | +1.245 |
itect | +1.173 |
axter | +1.164 |
eele | +1.161 |
hare | +1.124 |
Neg logit contributions | |
xit | -2.399 |
Uni | -2.355 |
ctors | -2.259 |
Honour | -2.145 |
culosis | -2.030 |
Token | . |
Token ID | 13 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
ramid | +2.136 |
itect | +2.043 |
axter | +2.039 |
eele | +2.029 |
hare | +1.986 |
Neg logit contributions | |
xit | -2.541 |
Uni | -2.492 |
ctors | -2.373 |
Honour | -2.228 |
culosis | -2.076 |
Token | Kim |
Token ID | 6502 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ramid | +1.448 |
axter | +1.387 |
itect | +1.376 |
eele | +1.373 |
hare | +1.344 |
Neg logit contributions | |
xit | -1.365 |
Uni | -1.350 |
ctors | -1.269 |
Honour | -1.189 |
culosis | -1.079 |
Token | b |
Token ID | 65 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
ramid | +3.848 |
itect | +3.664 |
axter | +3.656 |
eele | +3.632 |
hare | +3.570 |
Neg logit contributions | |
xit | -4.775 |
Uni | -4.701 |
ctors | -4.457 |
Honour | -4.216 |
culosis | -3.919 |
Token | on |
Token ID | 319 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
ramid | +1.469 |
itect | +1.407 |
axter | +1.403 |
eele | +1.397 |
hare | +1.361 |
Neg logit contributions | |
xit | -1.600 |
Uni | -1.574 |
ctors | -1.494 |
Honour | -1.401 |
culosis | -1.295 |
Token | Monday |
Token ID | 3321 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ramid | +0.150 |
itect | +0.145 |
axter | +0.144 |
eele | +0.143 |
hare | +0.140 |
Neg logit contributions | |
xit | -0.146 |
Uni | -0.144 |
ctors | -0.136 |
Honour | -0.127 |
culosis | -0.117 |
Token | afternoon |
Token ID | 6672 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
ramid | +1.113 |
itect | +1.073 |
axter | +1.066 |
eele | +1.061 |
hare | +1.032 |
Neg logit contributions | |
xit | -1.149 |
Uni | -1.140 |
ctors | -1.079 |
Honour | -1.011 |
culosis | -0.921 |
Token | shifted |
Token ID | 14869 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
ramid | +0.215 |
itect | +0.207 |
axter | +0.207 |
eele | +0.205 |
hare | +0.199 |
Neg logit contributions | |
xit | -0.220 |
Uni | -0.219 |
ctors | -0.207 |
Honour | -0.195 |
culosis | -0.177 |
Token | in |
Token ID | 287 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
xit | +0.049 |
Uni | +0.049 |
ctors | +0.045 |
Honour | +0.043 |
culosis | +0.038 |
Neg logit contributions | |
ramid | -0.055 |
itect | -0.052 |
axter | -0.052 |
eele | -0.052 |
hare | -0.050 |
Token | response |
Token ID | 2882 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
xit | +0.311 |
Uni | +0.307 |
ctors | +0.288 |
Honour | +0.273 |
culosis | +0.243 |
Neg logit contributions | |
ramid | -0.330 |
itect | -0.316 |
axter | -0.313 |
eele | -0.311 |
hare | -0.304 |
Token | to |
Token ID | 284 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ramid | +4.971 |
axter | +4.779 |
eele | +4.773 |
itect | +4.773 |
hare | +4.720 |
Neg logit contributions | |
xit | -7.494 |
Uni | -7.279 |
ctors | -7.094 |
Honour | -6.646 |
culosis | -6.372 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ramid | +0.456 |
itect | +0.438 |
axter | +0.435 |
eele | +0.433 |
hare | +0.424 |
Neg logit contributions | |
xit | -0.414 |
Uni | -0.409 |
ctors | -0.383 |
Honour | -0.359 |
culosis | -0.326 |
Token | strengthening |
Token ID | 24175 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
xit | +0.342 |
Uni | +0.340 |
ctors | +0.319 |
Honour | +0.305 |
culosis | +0.277 |
Neg logit contributions | |
ramid | -0.279 |
itect | -0.266 |
axter | -0.265 |
eele | -0.263 |
hare | -0.255 |
Token | of |
Token ID | 286 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
Uni | +1.738 |
xit | +1.710 |
ctors | +1.597 |
Honour | +1.545 |
CV | +1.405 |
Neg logit contributions | |
ramid | -1.539 |
itect | -1.462 |
axter | -1.460 |
eele | -1.450 |
olyn | -1.392 |
Token | a |
Token ID | 257 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
ramid | +0.087 |
itect | +0.084 |
axter | +0.083 |
eele | +0.083 |
hare | +0.081 |
Neg logit contributions | |
xit | -0.078 |
Uni | -0.078 |
ctors | -0.072 |
Honour | -0.068 |
culosis | -0.062 |
Token | de |
Token ID | 390 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
ramid | +1.859 |
itect | +1.788 |
axter | +1.784 |
eele | +1.776 |
hare | +1.745 |
Neg logit contributions | |
xit | -1.780 |
Uni | -1.741 |
ctors | -1.649 |
Honour | -1.538 |
culosis | -1.421 |
Token | jar |
Token ID | 9491 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
xit | +0.826 |
Uni | +0.808 |
ctors | +0.764 |
Honour | +0.705 |
culosis | +0.649 |
Neg logit contributions | |
ramid | -0.895 |
axter | -0.859 |
itect | -0.858 |
eele | -0.857 |
hare | -0.835 |
Token | ía |
Token ID | 29690 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
xit | +1.192 |
Uni | +1.181 |
ctors | +1.108 |
Honour | +1.024 |
culosis | +0.951 |
Neg logit contributions | |
ramid | -1.214 |
axter | -1.173 |
eele | -1.161 |
itect | -1.156 |
hare | -1.135 |
Token | que |
Token ID | 8358 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
ramid | +1.103 |
axter | +1.059 |
itect | +1.059 |
eele | +1.054 |
hare | +1.032 |
Neg logit contributions | |
xit | -1.039 |
Uni | -1.019 |
ctors | -0.960 |
Honour | -0.895 |
culosis | -0.824 |
Token | mi |
Token ID | 21504 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ramid | +1.168 |
itect | +1.122 |
axter | +1.121 |
eele | +1.116 |
hare | +1.094 |
Neg logit contributions | |
xit | -1.082 |
Uni | -1.062 |
ctors | -1.000 |
Honour | -0.931 |
culosis | -0.856 |
Token | hij |
Token ID | 16836 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
ramid | +2.561 |
itect | +2.472 |
axter | +2.457 |
eele | +2.447 |
hare | +2.407 |
Neg logit contributions | |
xit | -2.417 |
Uni | -2.352 |
ctors | -2.242 |
Honour | -2.086 |
culosis | -1.932 |
Token | a |
Token ID | 64 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
ramid | +5.623 |
itect | +5.569 |
axter | +5.417 |
azo | +5.314 |
eele | +5.280 |
Neg logit contributions | |
xit | -7.069 |
Uni | -6.767 |
ctors | -6.582 |
Honour | -6.214 |
culosis | -5.969 |
Token | jug |
Token ID | 45808 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
ramid | +0.156 |
axter | +0.149 |
itect | +0.149 |
eele | +0.149 |
hare | +0.146 |
Neg logit contributions | |
xit | -0.149 |
Uni | -0.147 |
ctors | -0.138 |
Honour | -0.128 |
culosis | -0.118 |
Token | ara |
Token ID | 3301 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
ramid | +1.054 |
axter | +1.005 |
itect | +1.005 |
eele | +0.999 |
hare | +0.979 |
Neg logit contributions | |
xit | -1.310 |
Uni | -1.287 |
ctors | -1.224 |
Honour | -1.148 |
culosis | -1.072 |
Token | con |
Token ID | 369 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
ramid | +1.310 |
itect | +1.258 |
axter | +1.257 |
eele | +1.251 |
hare | +1.227 |
Neg logit contributions | |
xit | -1.248 |
Uni | -1.222 |
ctors | -1.155 |
Honour | -1.076 |
culosis | -0.992 |
Token | e |
Token ID | 304 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
xit | +0.645 |
Uni | +0.637 |
ctors | +0.599 |
Honour | +0.554 |
culosis | +0.511 |
Neg logit contributions | |
ramid | -0.669 |
axter | -0.643 |
eele | -0.639 |
itect | -0.639 |
hare | -0.623 |
Token | Richard |
Token ID | 6219 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
ramid | +5.087 |
itect | +4.933 |
axter | +4.931 |
eele | +4.909 |
hare | +4.841 |
Neg logit contributions | |
xit | -5.491 |
Uni | -5.236 |
ctors | -5.095 |
Honour | -4.662 |
culosis | -4.463 |
Token | Mull |
Token ID | 19574 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
ramid | +1.361 |
itect | +1.308 |
axter | +1.306 |
eele | +1.300 |
hare | +1.276 |
Neg logit contributions | |
xit | -1.272 |
Uni | -1.246 |
ctors | -1.177 |
Honour | -1.097 |
culosis | -1.009 |
Token | igan |
Token ID | 5516 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
xit | +0.105 |
Uni | +0.103 |
ctors | +0.098 |
Honour | +0.092 |
culosis | +0.084 |
Neg logit contributions | |
ramid | -0.101 |
axter | -0.096 |
itect | -0.096 |
eele | -0.096 |
hare | -0.094 |
Token |
|
Token ID | 198 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
ramid | +2.573 |
itect | +2.470 |
axter | +2.463 |
eele | +2.452 |
hare | +2.405 |
Neg logit contributions | |
xit | -2.591 |
Uni | -2.486 |
ctors | -2.388 |
Honour | -2.203 |
culosis | -2.068 |
Token |
|
Token ID | 198 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
ramid | +1.749 |
itect | +1.684 |
axter | +1.677 |
eele | +1.671 |
hare | +1.643 |
Neg logit contributions | |
xit | -1.677 |
Uni | -1.640 |
ctors | -1.553 |
Honour | -1.445 |
culosis | -1.341 |
Token | 1989 |
Token ID | 25475 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
ramid | +2.090 |
itect | +2.019 |
axter | +2.008 |
eele | +1.991 |
hare | +1.967 |
Neg logit contributions | |
xit | -1.710 |
Uni | -1.677 |
ctors | -1.564 |
Honour | -1.453 |
culosis | -1.333 |
Token | Ted |
Token ID | 11396 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
ramid | +6.145 |
axter | +5.986 |
itect | +5.972 |
eele | +5.947 |
hare | +5.900 |
Neg logit contributions | |
xit | -6.383 |
Uni | -6.022 |
ctors | -5.918 |
Honour | -5.327 |
culosis | -5.189 |
Token | D |
Token ID | 360 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
xit | +1.008 |
Uni | +0.993 |
ctors | +0.938 |
Honour | +0.879 |
culosis | +0.813 |
Neg logit contributions | |
ramid | -0.951 |
itect | -0.913 |
axter | -0.908 |
eele | -0.904 |
hare | -0.887 |
Token | anson |
Token ID | 23103 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ramid | +0.042 |
itect | +0.040 |
eele | +0.040 |
axter | +0.040 |
hare | +0.039 |
Neg logit contributions | |
xit | -0.056 |
Uni | -0.055 |
ctors | -0.053 |
Honour | -0.049 |
culosis | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
ramid | +0.643 |
itect | +0.619 |
axter | +0.617 |
eele | +0.611 |
hare | +0.601 |
Neg logit contributions | |
xit | -0.622 |
Uni | -0.600 |
ctors | -0.572 |
Honour | -0.531 |
culosis | -0.492 |
Token |
|
Token ID | 198 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
ramid | +1.354 |
itect | +1.301 |
axter | +1.300 |
eele | +1.294 |
hare | +1.269 |
Neg logit contributions | |
xit | -1.261 |
Uni | -1.234 |
ctors | -1.167 |
Honour | -1.087 |
culosis | -0.999 |
Token | of |
Token ID | 286 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
ramid | +0.781 |
itect | +0.757 |
axter | +0.750 |
eele | +0.747 |
hare | +0.737 |
Neg logit contributions | |
xit | -0.720 |
Uni | -0.706 |
ctors | -0.665 |
Honour | -0.621 |
culosis | -0.572 |
Token | people |
Token ID | 661 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
ramid | +1.672 |
axter | +1.604 |
itect | +1.603 |
eele | +1.598 |
hare | +1.563 |
Neg logit contributions | |
xit | -1.455 |
Uni | -1.422 |
ctors | -1.346 |
Honour | -1.247 |
culosis | -1.139 |
Token | were |
Token ID | 547 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
ramid | +0.862 |
axter | +0.825 |
itect | +0.823 |
eele | +0.821 |
hare | +0.796 |
Neg logit contributions | |
xit | -0.938 |
Uni | -0.923 |
ctors | -0.878 |
Honour | -0.818 |
culosis | -0.759 |
Token | needed |
Token ID | 2622 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ramid | +1.714 |
itect | +1.648 |
axter | +1.644 |
eele | +1.639 |
hare | +1.599 |
Neg logit contributions | |
xit | -1.710 |
Uni | -1.674 |
ctors | -1.586 |
Honour | -1.479 |
culosis | -1.363 |
Token | to |
Token ID | 284 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
ramid | +0.458 |
axter | +0.440 |
itect | +0.437 |
eele | +0.436 |
hare | +0.422 |
Neg logit contributions | |
xit | -0.465 |
Uni | -0.454 |
ctors | -0.430 |
Honour | -0.401 |
culosis | -0.370 |
Token | respond |
Token ID | 3031 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
ramid | +1.103 |
axter | +1.055 |
itect | +1.055 |
eele | +1.052 |
hare | +1.021 |
Neg logit contributions | |
xit | -1.268 |
Uni | -1.244 |
ctors | -1.186 |
Honour | -1.106 |
culosis | -1.024 |
Token | to |
Token ID | 284 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ramid | +5.423 |
itect | +5.311 |
hare | +5.200 |
axter | +5.181 |
eele | +5.169 |
Neg logit contributions | |
xit | -6.996 |
Uni | -6.798 |
ctors | -6.581 |
Honour | -6.199 |
culosis | -5.862 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ramid | +0.572 |
itect | +0.550 |
axter | +0.550 |
eele | +0.547 |
hare | +0.535 |
Neg logit contributions | |
xit | -0.534 |
Uni | -0.522 |
ctors | -0.493 |
Honour | -0.459 |
culosis | -0.421 |
Token | Deep |
Token ID | 10766 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
xit | +0.218 |
Uni | +0.214 |
ctors | +0.199 |
Honour | +0.186 |
culosis | +0.167 |
Neg logit contributions | |
ramid | -0.267 |
itect | -0.259 |
axter | -0.257 |
eele | -0.257 |
hare | -0.250 |
Token | water |
Token ID | 7050 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
xit | +1.314 |
Uni | +1.226 |
ctors | +1.103 |
Honour | +1.003 |
culosis | +0.821 |
Neg logit contributions | |
ramid | -3.334 |
axter | -3.279 |
itect | -3.258 |
eele | -3.230 |
hare | -3.171 |
Token | Horizon |
Token ID | 22776 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
xit | +1.075 |
Uni | +1.025 |
ctors | +0.930 |
Honour | +0.851 |
culosis | +0.718 |
Neg logit contributions | |
ramid | -2.332 |
axter | -2.265 |
itect | -2.253 |
eele | -2.252 |
hare | -2.214 |
Token | the |
Token ID | 262 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
xit | +0.314 |
Uni | +0.313 |
ctors | +0.290 |
Honour | +0.272 |
culosis | +0.246 |
Neg logit contributions | |
ramid | -0.336 |
axter | -0.320 |
itect | -0.319 |
eele | -0.318 |
hare | -0.309 |
Token | worst |
Token ID | 5290 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
xit | +0.377 |
Uni | +0.376 |
ctors | +0.348 |
Honour | +0.326 |
culosis | +0.295 |
Neg logit contributions | |
ramid | -0.408 |
axter | -0.391 |
eele | -0.390 |
itect | -0.387 |
hare | -0.377 |
Token | ne |
Token ID | 497 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
Uni | +2.317 |
xit | +2.291 |
ctors | +2.133 |
Honour | +1.996 |
culosis | +1.816 |
Neg logit contributions | |
ramid | -2.176 |
axter | -2.046 |
eele | -2.025 |
itect | -2.019 |
hare | -1.974 |
Token | |
Token ID | 3907 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
ramid | +1.715 |
itect | +1.654 |
axter | +1.644 |
eele | +1.637 |
hare | +1.610 |
Neg logit contributions | |
xit | -2.229 |
Uni | -2.191 |
ctors | -2.102 |
Honour | -1.987 |
culosis | -1.862 |
Token | go |
Token ID | 2188 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ramid | +2.615 |
itect | +2.526 |
axter | +2.524 |
eele | +2.521 |
hare | +2.462 |
Neg logit contributions | |
xit | -1.744 |
Uni | -1.679 |
ctors | -1.585 |
Honour | -1.434 |
culosis | -1.298 |
Token | |
Token ID | 3907 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
xit | +3.223 |
Uni | +3.084 |
ctors | +2.952 |
Honour | +2.580 |
culosis | +2.392 |
Neg logit contributions | |
ramid | -3.086 |
axter | -3.058 |
eele | -3.039 |
hare | -2.957 |
itect | -2.922 |
Token | ti |
Token ID | 20259 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
ramid | +5.654 |
itect | +5.362 |
eele | +5.257 |
axter | +5.255 |
hare | +5.242 |
Neg logit contributions | |
Uni | -6.981 |
xit | -6.938 |
ctors | -6.483 |
Honour | -6.276 |
culosis | -5.779 |
Token | |
Token ID | 3907 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
ramid | +1.007 |
axter | +0.961 |
eele | +0.956 |
itect | +0.955 |
hare | +0.937 |
Neg logit contributions | |
xit | -1.188 |
Uni | -1.164 |
ctors | -1.107 |
Honour | -1.034 |
culosis | -0.964 |
Token | at |
Token ID | 265 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
ramid | +5.009 |
itect | +4.812 |
axter | +4.694 |
azo | +4.687 |
hare | +4.659 |
Neg logit contributions | |
Uni | -5.786 |
xit | -5.735 |
ctors | -5.324 |
Honour | -5.166 |
culosis | -4.623 |
Token | |
Token ID | 3907 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ramid | +1.165 |
itect | +1.119 |
axter | +1.116 |
eele | +1.111 |
hare | +1.089 |
Neg logit contributions | |
xit | -1.224 |
Uni | -1.198 |
ctors | -1.138 |
Honour | -1.064 |
culosis | -0.986 |
Token | or |
Token ID | 273 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
ramid | +3.777 |
itect | +3.704 |
axter | +3.606 |
eele | +3.586 |
hare | +3.543 |
Neg logit contributions | |
xit | -4.792 |
Uni | -4.728 |
ctors | -4.507 |
Honour | -4.252 |
culosis | -3.912 |
Token | all |
Token ID | 477 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ramid | +0.805 |
axter | +0.770 |
itect | +0.769 |
eele | +0.765 |
hare | +0.749 |
Neg logit contributions | |
xit | -0.749 |
Uni | -0.738 |
ctors | -0.690 |
Honour | -0.648 |
culosis | -0.593 |
Token | decisions |
Token ID | 5370 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ramid | +2.694 |
itect | +2.597 |
axter | +2.584 |
eele | +2.569 |
hare | +2.528 |
Neg logit contributions | |
xit | -2.535 |
Uni | -2.473 |
ctors | -2.351 |
Honour | -2.178 |
culosis | -2.024 |
Token | would |
Token ID | 561 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
ramid | +2.880 |
itect | +2.773 |
axter | +2.765 |
eele | +2.747 |
hare | +2.709 |
Neg logit contributions | |
xit | -3.013 |
Uni | -2.942 |
ctors | -2.799 |
Honour | -2.610 |
culosis | -2.428 |
Token | need |
Token ID | 761 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
ramid | +0.035 |
eele | +0.033 |
axter | +0.033 |
itect | +0.033 |
olyn | +0.032 |
Neg logit contributions | |
xit | -0.037 |
Uni | -0.036 |
ctors | -0.034 |
Honour | -0.032 |
culosis | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
xit | +0.529 |
Uni | +0.521 |
ctors | +0.492 |
Honour | +0.463 |
culosis | +0.423 |
Neg logit contributions | |
ramid | -0.514 |
axter | -0.492 |
itect | -0.489 |
eele | -0.487 |
hare | -0.478 |
Token | align |
Token ID | 10548 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
ramid | +0.832 |
itect | +0.798 |
axter | +0.797 |
eele | +0.794 |
hare | +0.774 |
Neg logit contributions | |
xit | -0.815 |
Uni | -0.805 |
ctors | -0.763 |
Honour | -0.714 |
culosis | -0.655 |
Token | with |
Token ID | 351 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
ramid | +5.509 |
itect | +5.458 |
axter | +5.350 |
eele | +5.310 |
hare | +5.273 |
Neg logit contributions | |
xit | -6.841 |
Uni | -6.573 |
ctors | -6.438 |
Honour | -5.962 |
culosis | -5.704 |
Token | the |
Token ID | 262 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
Uni | +0.904 |
xit | +0.899 |
ctors | +0.828 |
Honour | +0.787 |
culosis | +0.704 |
Neg logit contributions | |
ramid | -0.982 |
axter | -0.943 |
eele | -0.938 |
itect | -0.933 |
hare | -0.914 |
Token | EPA |
Token ID | 10193 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
ramid | +0.144 |
axter | +0.139 |
itect | +0.138 |
eele | +0.138 |
hare | +0.135 |
Neg logit contributions | |
xit | -0.144 |
Uni | -0.143 |
ctors | -0.133 |
Honour | -0.127 |
culosis | -0.114 |
Token | � |
Token ID | 447 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
xit | +1.542 |
Uni | +1.533 |
ctors | +1.427 |
Honour | +1.364 |
culosis | +1.226 |
Neg logit contributions | |
ramid | -1.477 |
axter | -1.431 |
eele | -1.405 |
itect | -1.398 |
hare | -1.389 |
Token | � |
Token ID | 247 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ramid | +0.778 |
itect | +0.741 |
axter | +0.739 |
eele | +0.737 |
hare | +0.719 |
Neg logit contributions | |
xit | -1.016 |
Uni | -0.993 |
ctors | -0.947 |
Honour | -0.896 |
culosis | -0.830 |
Token | 1989 |
Token ID | 25475 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
ramid | +1.729 |
itect | +1.668 |
axter | +1.658 |
eele | +1.645 |
hare | +1.625 |
Neg logit contributions | |
xit | -1.410 |
Uni | -1.381 |
ctors | -1.290 |
Honour | -1.199 |
culosis | -1.099 |
Token | John |
Token ID | 1757 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
ramid | +5.740 |
axter | +5.573 |
itect | +5.564 |
eele | +5.526 |
hare | +5.496 |
Neg logit contributions | |
xit | -5.931 |
Uni | -5.628 |
ctors | -5.500 |
Honour | -4.992 |
culosis | -4.813 |
Token | Goodman |
Token ID | 33318 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
xit | +0.815 |
Uni | +0.804 |
ctors | +0.756 |
Honour | +0.715 |
culosis | +0.653 |
Neg logit contributions | |
ramid | -0.749 |
itect | -0.717 |
axter | -0.713 |
eele | -0.712 |
hare | -0.696 |
Token |
|
Token ID | 198 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
xit | +1.327 |
Uni | +1.309 |
ctors | +1.224 |
Honour | +1.133 |
culosis | +1.029 |
Neg logit contributions | |
ramid | -1.729 |
itect | -1.668 |
axter | -1.665 |
eele | -1.662 |
hare | -1.635 |
Token |
|
Token ID | 198 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
ramid | +1.414 |
itect | +1.360 |
axter | +1.357 |
eele | +1.351 |
hare | +1.326 |
Neg logit contributions | |
xit | -1.329 |
Uni | -1.300 |
ctors | -1.230 |
Honour | -1.145 |
culosis | -1.056 |
Token | 1989 |
Token ID | 25475 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
ramid | +1.788 |
itect | +1.727 |
axter | +1.715 |
eele | +1.703 |
hare | +1.680 |
Neg logit contributions | |
xit | -1.461 |
Uni | -1.431 |
ctors | -1.338 |
Honour | -1.243 |
culosis | -1.140 |
Token | Fred |
Token ID | 8559 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ramid | +5.992 |
itect | +5.825 |
axter | +5.822 |
eele | +5.788 |
hare | +5.748 |
Neg logit contributions | |
xit | -6.217 |
Uni | -5.875 |
ctors | -5.758 |
Honour | -5.212 |
culosis | -5.051 |
Token | Savage |
Token ID | 22287 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
Uni | +3.177 |
xit | +3.158 |
ctors | +2.951 |
Honour | +2.788 |
culosis | +2.521 |
Neg logit contributions | |
ramid | -3.270 |
itect | -3.146 |
axter | -3.143 |
eele | -3.121 |
hare | -3.041 |
Token | 1990 |
Token ID | 6303 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
xit | +1.179 |
Uni | +1.159 |
ctors | +1.087 |
Honour | +1.006 |
culosis | +0.915 |
Neg logit contributions | |
ramid | -1.511 |
itect | -1.457 |
axter | -1.455 |
eele | -1.450 |
hare | -1.427 |
Token | Ted |
Token ID | 11396 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
ramid | +4.377 |
axter | +4.239 |
itect | +4.235 |
eele | +4.215 |
hare | +4.151 |
Neg logit contributions | |
xit | -4.544 |
Uni | -4.365 |
ctors | -4.210 |
Honour | -3.876 |
culosis | -3.669 |
Token | D |
Token ID | 360 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Uni | +1.298 |
xit | +1.293 |
ctors | +1.203 |
Honour | +1.141 |
culosis | +1.020 |
Neg logit contributions | |
ramid | -1.338 |
axter | -1.278 |
itect | -1.276 |
eele | -1.265 |
hare | -1.232 |
Token | to |
Token ID | 284 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ramid | +1.071 |
itect | +1.025 |
axter | +1.024 |
eele | +1.017 |
hare | +0.997 |
Neg logit contributions | |
xit | -1.207 |
Uni | -1.182 |
ctors | -1.126 |
Honour | -1.055 |
culosis | -0.982 |
Token | buy |
Token ID | 2822 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
xit | +0.411 |
Uni | +0.408 |
ctors | +0.384 |
Honour | +0.358 |
culosis | +0.327 |
Neg logit contributions | |
ramid | -0.401 |
itect | -0.386 |
eele | -0.385 |
axter | -0.383 |
ippi | -0.373 |
Token | an |
Token ID | 281 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
ramid | +1.507 |
itect | +1.448 |
axter | +1.442 |
eele | +1.438 |
hare | +1.409 |
Neg logit contributions | |
xit | -1.478 |
Uni | -1.451 |
ctors | -1.369 |
Honour | -1.277 |
culosis | -1.175 |
Token | entirely |
Token ID | 5000 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ramid | +0.953 |
itect | +0.912 |
eele | +0.909 |
axter | +0.901 |
hare | +0.891 |
Neg logit contributions | |
xit | -0.913 |
Uni | -0.908 |
ctors | -0.840 |
Honour | -0.797 |
culosis | -0.722 |
Token | new |
Token ID | 649 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ramid | +2.545 |
itect | +2.435 |
axter | +2.432 |
eele | +2.416 |
hare | +2.369 |
Neg logit contributions | |
xit | -2.941 |
Uni | -2.881 |
ctors | -2.745 |
Honour | -2.573 |
culosis | -2.400 |
Token | shif |
Token ID | 7143 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
Uni | +0.215 |
xit | +0.214 |
ctors | +0.197 |
Honour | +0.186 |
culosis | +0.167 |
Neg logit contributions | |
ramid | -0.229 |
eele | -0.221 |
itect | -0.219 |
axter | -0.219 |
hare | -0.214 |
Token | ter |
Token ID | 353 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ramid | +3.150 |
itect | +2.904 |
axter | +2.868 |
eele | +2.863 |
hare | +2.772 |
Neg logit contributions | |
xit | -9.241 |
Uni | -8.897 |
ctors | -8.681 |
Honour | -8.283 |
nces | -8.092 |
Token | . |
Token ID | 13 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ramid | +2.195 |
itect | +2.106 |
axter | +2.102 |
eele | +2.092 |
hare | +2.051 |
Neg logit contributions | |
xit | -2.290 |
Uni | -2.244 |
ctors | -2.128 |
Honour | -1.989 |
culosis | -1.842 |
Token | I |
Token ID | 314 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ramid | +0.426 |
axter | +0.407 |
itect | +0.407 |
eele | +0.407 |
hare | +0.397 |
Neg logit contributions | |
xit | -0.400 |
Uni | -0.396 |
ctors | -0.371 |
Honour | -0.348 |
culosis | -0.316 |
Token | am |
Token ID | 716 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
xit | +0.326 |
Uni | +0.322 |
ctors | +0.304 |
Honour | +0.281 |
culosis | +0.258 |
Neg logit contributions | |
ramid | -0.354 |
itect | -0.342 |
eele | -0.342 |
axter | -0.340 |
hare | -0.330 |
Token | going |
Token ID | 1016 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
xit | +0.803 |
Uni | +0.801 |
ctors | +0.751 |
Honour | +0.699 |
culosis | +0.634 |
Neg logit contributions | |
ramid | -0.834 |
eele | -0.796 |
itect | -0.791 |
axter | -0.788 |
olyn | -0.770 |
Token | though |
Token ID | 996 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
Uni | +1.045 |
xit | +1.041 |
ctors | +0.967 |
Honour | +0.902 |
culosis | +0.811 |
Neg logit contributions | |
ramid | -1.242 |
itect | -1.183 |
axter | -1.178 |
eele | -1.175 |
olyn | -1.145 |
Token | , |
Token ID | 11 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
Uni | +0.442 |
xit | +0.442 |
ctors | +0.412 |
Honour | +0.387 |
culosis | +0.349 |
Neg logit contributions | |
ramid | -0.480 |
itect | -0.458 |
axter | -0.453 |
eele | -0.452 |
hare | -0.441 |
Token | as |
Token ID | 355 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
xit | +0.102 |
Uni | +0.102 |
ctors | +0.095 |
Honour | +0.089 |
culosis | +0.080 |
Neg logit contributions | |
ramid | -0.115 |
itect | -0.110 |
eele | -0.109 |
axter | -0.109 |
hare | -0.106 |
Token | cam |
Token ID | 12172 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ramid | +2.547 |
itect | +2.449 |
axter | +2.442 |
eele | +2.431 |
hare | +2.387 |
Neg logit contributions | |
xit | -2.396 |
Uni | -2.347 |
ctors | -2.218 |
Honour | -2.067 |
culosis | -1.903 |
Token | Atkinson |
Token ID | 49042 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
ramid | +0.344 |
axter | +0.326 |
itect | +0.326 |
eele | +0.322 |
hare | +0.317 |
Neg logit contributions | |
xit | -0.388 |
Uni | -0.381 |
ctors | -0.363 |
Honour | -0.339 |
culosis | -0.312 |
Token | responded |
Token ID | 7082 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
ramid | +1.144 |
itect | +1.097 |
axter | +1.095 |
eele | +1.090 |
hare | +1.069 |
Neg logit contributions | |
xit | -1.183 |
Uni | -1.159 |
ctors | -1.099 |
Honour | -1.027 |
culosis | -0.951 |
Token | just |
Token ID | 655 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
ramid | +5.420 |
itect | +5.301 |
eele | +5.281 |
axter | +5.273 |
hare | +5.268 |
Neg logit contributions | |
xit | -6.736 |
Uni | -6.440 |
ctors | -6.311 |
Honour | -5.803 |
culosis | -5.546 |
Token | 96 |
Token ID | 9907 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
ramid | +0.679 |
itect | +0.650 |
axter | +0.648 |
eele | +0.643 |
hare | +0.628 |
Neg logit contributions | |
xit | -0.606 |
Uni | -0.600 |
ctors | -0.558 |
Honour | -0.526 |
culosis | -0.474 |
Token | seconds |
Token ID | 4201 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
xit | +0.834 |
Uni | +0.821 |
ctors | +0.757 |
Honour | +0.677 |
culosis | +0.584 |
Neg logit contributions | |
ramid | -1.531 |
itect | -1.476 |
eele | -1.474 |
axter | -1.472 |
hare | -1.448 |
Token | later |
Token ID | 1568 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
xit | +1.007 |
Uni | +0.983 |
ctors | +0.900 |
Honour | +0.832 |
culosis | +0.704 |
Neg logit contributions | |
ramid | -1.769 |
eele | -1.697 |
itect | -1.694 |
axter | -1.688 |
olyn | -1.654 |
Token | – |
Token ID | 784 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
ramid | +2.141 |
itect | +2.054 |
axter | +2.051 |
eele | +2.041 |
hare | +2.003 |
Neg logit contributions | |
xit | -2.351 |
Uni | -2.300 |
ctors | -2.189 |
Honour | -2.047 |
culosis | -1.904 |
Token | ] |
Token ID | 60 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ramid | +0.160 |
itect | +0.153 |
axter | +0.153 |
eele | +0.152 |
hare | +0.149 |
Neg logit contributions | |
xit | -0.203 |
Uni | -0.199 |
ctors | -0.189 |
Honour | -0.178 |
culosis | -0.166 |
Token |
|
Token ID | 198 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ramid | +0.353 |
axter | +0.341 |
eele | +0.336 |
itect | +0.336 |
hare | +0.329 |
Neg logit contributions | |
xit | -0.307 |
Uni | -0.303 |
ctors | -0.284 |
Honour | -0.267 |
culosis | -0.239 |
Token |
|
Token ID | 198 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
ramid | +0.358 |
axter | +0.346 |
eele | +0.342 |
itect | +0.342 |
hare | +0.334 |
Neg logit contributions | |
xit | -0.313 |
Uni | -0.306 |
ctors | -0.288 |
Honour | -0.269 |
culosis | -0.242 |
Token | In |
Token ID | 818 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
ramid | +0.600 |
axter | +0.575 |
eele | +0.571 |
itect | +0.571 |
hare | +0.554 |
Neg logit contributions | |
xit | -0.689 |
Uni | -0.669 |
ctors | -0.641 |
Honour | -0.602 |
culosis | -0.555 |
Token | April |
Token ID | 3035 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
xit | +0.142 |
Uni | +0.139 |
ctors | +0.130 |
Honour | +0.121 |
culosis | +0.107 |
Neg logit contributions | |
ramid | -0.187 |
axter | -0.181 |
eele | -0.180 |
itect | -0.180 |
hare | -0.176 |
Token | 1990 |
Token ID | 6303 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
ramid | +2.939 |
itect | +2.854 |
axter | +2.832 |
eele | +2.827 |
hare | +2.794 |
Neg logit contributions | |
xit | -1.762 |
Uni | -1.700 |
ctors | -1.594 |
Honour | -1.438 |
culosis | -1.303 |
Token | , |
Token ID | 11 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
ramid | +4.932 |
itect | +4.729 |
eele | +4.720 |
axter | +4.646 |
hare | +4.586 |
Neg logit contributions | |
xit | -7.036 |
Uni | -6.771 |
ctors | -6.595 |
Honour | -6.194 |
culosis | -5.819 |
Token | three |
Token ID | 1115 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ramid | +1.139 |
itect | +1.094 |
axter | +1.093 |
eele | +1.086 |
hare | +1.065 |
Neg logit contributions | |
xit | -1.088 |
Uni | -1.070 |
ctors | -1.008 |
Honour | -0.943 |
culosis | -0.863 |
Token | years |
Token ID | 812 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
xit | +0.416 |
Uni | +0.411 |
ctors | +0.381 |
Honour | +0.354 |
culosis | +0.311 |
Neg logit contributions | |
ramid | -0.569 |
itect | -0.548 |
axter | -0.548 |
eele | -0.547 |
hare | -0.533 |
Token | and |
Token ID | 290 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
xit | +0.129 |
Uni | +0.126 |
ctors | +0.119 |
Honour | +0.111 |
culosis | +0.100 |
Neg logit contributions | |
ramid | -0.152 |
axter | -0.146 |
itect | -0.146 |
eele | -0.146 |
hare | -0.143 |
Token | six |
Token ID | 2237 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ramid | +0.842 |
itect | +0.811 |
axter | +0.810 |
eele | +0.805 |
hare | +0.789 |
Neg logit contributions | |
xit | -0.721 |
Uni | -0.707 |
ctors | -0.663 |
Honour | -0.619 |
culosis | -0.564 |
Token | quarterbacks |
Token ID | 23643 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
ramid | +0.005 |
itect | +0.005 |
axter | +0.005 |
eele | +0.005 |
hare | +0.004 |
Neg logit contributions | |
xit | -0.004 |
Uni | -0.004 |
ctors | -0.003 |
Honour | -0.003 |
culosis | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
ramid | +1.561 |
axter | +1.493 |
itect | +1.487 |
eele | +1.483 |
hare | +1.444 |
Neg logit contributions | |
xit | -1.654 |
Uni | -1.636 |
ctors | -1.544 |
Honour | -1.445 |
culosis | -1.339 |
Token | who |
Token ID | 508 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
xit | +0.134 |
Uni | +0.134 |
ctors | +0.125 |
Honour | +0.116 |
culosis | +0.106 |
Neg logit contributions | |
ramid | -0.138 |
itect | -0.132 |
eele | -0.131 |
axter | -0.131 |
hare | -0.129 |
Token | continued |
Token ID | 3767 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
xit | +1.039 |
Uni | +1.037 |
ctors | +0.982 |
Honour | +0.912 |
culosis | +0.836 |
Neg logit contributions | |
ramid | -1.082 |
itect | -1.031 |
eele | -1.026 |
axter | -1.025 |
hare | -0.992 |
Token | to |
Token ID | 284 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
xit | +0.837 |
Uni | +0.834 |
ctors | +0.775 |
Honour | +0.724 |
culosis | +0.664 |
Neg logit contributions | |
ramid | -0.861 |
axter | -0.825 |
itect | -0.822 |
eele | -0.815 |
hare | -0.800 |
Token | split |
Token ID | 6626 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
ramid | +0.717 |
itect | +0.686 |
axter | +0.685 |
eele | +0.682 |
olyn | +0.664 |
Neg logit contributions | |
xit | -0.712 |
Uni | -0.706 |
ctors | -0.670 |
Honour | -0.626 |
culosis | -0.571 |
Token | first |
Token ID | 717 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ramid | +5.700 |
itect | +5.522 |
axter | +5.467 |
hare | +5.411 |
eele | +5.386 |
Neg logit contributions | |
xit | -6.274 |
Uni | -6.074 |
ctors | -5.886 |
Honour | -5.445 |
culosis | -5.188 |
Token | - |
Token ID | 12 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
ramid | +0.329 |
itect | +0.314 |
axter | +0.314 |
eele | +0.313 |
hare | +0.307 |
Neg logit contributions | |
xit | -0.271 |
Uni | -0.268 |
ctors | -0.251 |
Honour | -0.233 |
culosis | -0.212 |
Token | team |
Token ID | 15097 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
xit | +1.628 |
Uni | +1.603 |
ctors | +1.519 |
Honour | +1.391 |
culosis | +1.256 |
Neg logit contributions | |
ramid | -2.050 |
axter | -1.956 |
eele | -1.953 |
itect | -1.936 |
hare | -1.897 |
Token | repet |
Token ID | 46152 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Uni | +4.163 |
xit | +4.093 |
ctors | +3.918 |
Honour | +3.693 |
nces | +3.332 |
Neg logit contributions | |
ramid | -3.701 |
eele | -3.490 |
axter | -3.472 |
itect | -3.422 |
hare | -3.331 |
Token | itions |
Token ID | 1756 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
xit | +0.536 |
Uni | +0.525 |
ctors | +0.508 |
Honour | +0.470 |
culosis | +0.441 |
Neg logit contributions | |
ramid | -0.414 |
axter | -0.395 |
itect | -0.389 |
eele | -0.389 |
hare | -0.384 |
Token | described |
Token ID | 3417 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
ramid | +1.006 |
itect | +0.968 |
axter | +0.968 |
eele | +0.963 |
hare | +0.939 |
Neg logit contributions | |
xit | -0.839 |
Uni | -0.828 |
ctors | -0.780 |
Honour | -0.726 |
culosis | -0.655 |
Token | it |
Token ID | 340 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
ramid | +1.447 |
itect | +1.387 |
axter | +1.377 |
eele | +1.372 |
hare | +1.346 |
Neg logit contributions | |
xit | -1.450 |
Uni | -1.428 |
ctors | -1.346 |
Honour | -1.261 |
culosis | -1.158 |
Token | as |
Token ID | 355 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
ramid | +0.940 |
itect | +0.899 |
axter | +0.897 |
eele | +0.894 |
hare | +0.874 |
Neg logit contributions | |
xit | -0.877 |
Uni | -0.861 |
ctors | -0.809 |
Honour | -0.759 |
culosis | -0.692 |
Token | a |
Token ID | 257 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
ramid | +1.130 |
itect | +1.082 |
axter | +1.079 |
eele | +1.075 |
hare | +1.049 |
Neg logit contributions | |
xit | -1.071 |
Uni | -1.058 |
ctors | -0.994 |
Honour | -0.932 |
culosis | -0.850 |
Token | carry |
Token ID | 3283 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
ramid | +0.752 |
axter | +0.724 |
itect | +0.720 |
eele | +0.717 |
hare | +0.699 |
Neg logit contributions | |
xit | -0.747 |
Uni | -0.735 |
ctors | -0.698 |
Honour | -0.651 |
culosis | -0.597 |
Token | over |
Token ID | 2502 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
ramid | +1.989 |
axter | +1.915 |
itect | +1.913 |
eele | +1.909 |
hare | +1.870 |
Neg logit contributions | |
xit | -1.564 |
Uni | -1.528 |
ctors | -1.435 |
Honour | -1.326 |
culosis | -1.207 |
Token | from |
Token ID | 422 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
ramid | +5.395 |
itect | +5.294 |
eele | +5.229 |
axter | +5.181 |
hare | +5.151 |
Neg logit contributions | |
xit | -6.460 |
Uni | -6.260 |
ctors | -6.041 |
Honour | -5.590 |
culosis | -5.324 |
Token | the |
Token ID | 262 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ramid | +1.332 |
itect | +1.279 |
axter | +1.273 |
eele | +1.266 |
hare | +1.241 |
Neg logit contributions | |
xit | -1.398 |
Uni | -1.379 |
ctors | -1.300 |
Honour | -1.219 |
culosis | -1.123 |
Token | foundation |
Token ID | 8489 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
ramid | +0.647 |
itect | +0.623 |
axter | +0.620 |
eele | +0.618 |
hare | +0.604 |
Neg logit contributions | |
xit | -0.639 |
Uni | -0.631 |
ctors | -0.592 |
Honour | -0.556 |
culosis | -0.510 |
Token | laid |
Token ID | 8104 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
ramid | +1.670 |
axter | +1.599 |
itect | +1.597 |
eele | +1.590 |
hare | +1.560 |
Neg logit contributions | |
xit | -1.523 |
Uni | -1.503 |
ctors | -1.406 |
Honour | -1.309 |
culosis | -1.198 |
Token | during |
Token ID | 1141 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ramid | +0.151 |
axter | +0.145 |
itect | +0.144 |
eele | +0.144 |
hare | +0.141 |
Neg logit contributions | |
xit | -0.144 |
Uni | -0.143 |
ctors | -0.133 |
Honour | -0.126 |
culosis | -0.115 |
Token | Ted |
Token ID | 11396 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
ramid | +6.145 |
axter | +5.986 |
itect | +5.972 |
eele | +5.947 |
hare | +5.900 |
Neg logit contributions | |
xit | -6.383 |
Uni | -6.022 |
ctors | -5.918 |
Honour | -5.327 |
culosis | -5.189 |
Token | D |
Token ID | 360 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
xit | +1.008 |
Uni | +0.993 |
ctors | +0.938 |
Honour | +0.879 |
culosis | +0.813 |
Neg logit contributions | |
ramid | -0.951 |
itect | -0.913 |
axter | -0.908 |
eele | -0.904 |
hare | -0.887 |
Token | anson |
Token ID | 23103 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ramid | +0.042 |
itect | +0.040 |
eele | +0.040 |
axter | +0.040 |
hare | +0.039 |
Neg logit contributions | |
xit | -0.056 |
Uni | -0.055 |
ctors | -0.053 |
Honour | -0.049 |
culosis | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
ramid | +0.643 |
itect | +0.619 |
axter | +0.617 |
eele | +0.611 |
hare | +0.601 |
Neg logit contributions | |
xit | -0.622 |
Uni | -0.600 |
ctors | -0.572 |
Honour | -0.531 |
culosis | -0.492 |
Token |
|
Token ID | 198 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
ramid | +1.354 |
itect | +1.301 |
axter | +1.300 |
eele | +1.294 |
hare | +1.269 |
Neg logit contributions | |
xit | -1.261 |
Uni | -1.234 |
ctors | -1.167 |
Honour | -1.087 |
culosis | -0.999 |
Token | 1989 |
Token ID | 25475 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ramid | +1.731 |
itect | +1.672 |
axter | +1.661 |
eele | +1.647 |
hare | +1.627 |
Neg logit contributions | |
xit | -1.414 |
Uni | -1.386 |
ctors | -1.294 |
Honour | -1.203 |
culosis | -1.103 |
Token | Michael |
Token ID | 3899 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ramid | +5.833 |
axter | +5.667 |
itect | +5.650 |
eele | +5.623 |
hare | +5.581 |
Neg logit contributions | |
xit | -5.983 |
Uni | -5.668 |
ctors | -5.553 |
Honour | -5.028 |
culosis | -4.848 |
Token | J |
Token ID | 449 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
ramid | +3.416 |
axter | +3.302 |
itect | +3.302 |
eele | +3.286 |
hare | +3.222 |
Neg logit contributions | |
xit | -3.499 |
Uni | -3.381 |
ctors | -3.248 |
Honour | -2.991 |
culosis | -2.820 |
Token | . |
Token ID | 13 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
ramid | +1.529 |
itect | +1.464 |
axter | +1.457 |
eele | +1.444 |
hare | +1.414 |
Neg logit contributions | |
xit | -1.872 |
Uni | -1.839 |
ctors | -1.747 |
Honour | -1.640 |
culosis | -1.522 |
Token | Fox |
Token ID | 5426 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
ramid | +1.266 |
axter | +1.224 |
itect | +1.222 |
eele | +1.216 |
hare | +1.197 |
Neg logit contributions | |
xit | -0.745 |
Uni | -0.731 |
ctors | -0.673 |
Honour | -0.614 |
culosis | -0.541 |
Token |
|
Token ID | 198 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
ramid | +2.068 |
itect | +1.983 |
axter | +1.967 |
eele | +1.951 |
hare | +1.920 |
Neg logit contributions | |
xit | -2.011 |
Uni | -1.931 |
ctors | -1.842 |
Honour | -1.716 |
culosis | -1.593 |
Token | despite |
Token ID | 3805 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
ramid | +0.229 |
itect | +0.220 |
axter | +0.218 |
eele | +0.217 |
hare | +0.213 |
Neg logit contributions | |
xit | -0.210 |
Uni | -0.209 |
ctors | -0.198 |
Honour | -0.185 |
culosis | -0.167 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ramid | +0.093 |
itect | +0.089 |
axter | +0.088 |
eele | +0.088 |
hare | +0.086 |
Neg logit contributions | |
xit | -0.086 |
Uni | -0.086 |
ctors | -0.081 |
Honour | -0.075 |
culosis | -0.068 |
Token | consequences |
Token ID | 6948 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
Uni | +0.207 |
xit | +0.207 |
ctors | +0.193 |
Honour | +0.180 |
culosis | +0.161 |
Neg logit contributions | |
ramid | -0.255 |
itect | -0.246 |
axter | -0.244 |
eele | -0.241 |
hare | -0.238 |
Token | of |
Token ID | 286 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
xit | +0.028 |
Uni | +0.028 |
ctors | +0.026 |
Honour | +0.025 |
culosis | +0.022 |
Neg logit contributions | |
ramid | -0.029 |
itect | -0.028 |
axter | -0.028 |
eele | -0.028 |
hare | -0.027 |
Token | running |
Token ID | 2491 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
ramid | +1.139 |
itect | +1.093 |
axter | +1.084 |
eele | +1.079 |
hare | +1.059 |
Neg logit contributions | |
xit | -1.094 |
Uni | -1.084 |
ctors | -1.020 |
Honour | -0.956 |
culosis | -0.869 |
Token | counter |
Token ID | 3753 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
Uni | +1.525 |
xit | +1.509 |
ctors | +1.412 |
Honour | +1.336 |
nces | +1.186 |
Neg logit contributions | |
ramid | -1.821 |
axter | -1.742 |
itect | -1.732 |
eele | -1.719 |
olyn | -1.672 |
Token | to |
Token ID | 284 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ramid | +5.065 |
itect | +4.815 |
axter | +4.794 |
eele | +4.767 |
hare | +4.617 |
Neg logit contributions | |
xit | -6.823 |
Uni | -6.636 |
ctors | -6.321 |
Honour | -6.032 |
culosis | -5.648 |
Token | what |
Token ID | 644 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
Uni | +0.509 |
xit | +0.502 |
ctors | +0.476 |
Honour | +0.452 |
culosis | +0.403 |
Neg logit contributions | |
ramid | -0.477 |
itect | -0.458 |
axter | -0.455 |
eele | -0.453 |
hare | -0.438 |
Token | is |
Token ID | 318 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Uni | +1.780 |
xit | +1.745 |
ctors | +1.674 |
Honour | +1.593 |
culosis | +1.429 |
Neg logit contributions | |
ramid | -1.427 |
itect | -1.378 |
axter | -1.365 |
eele | -1.356 |
hare | -1.315 |
Token | expected |
Token ID | 2938 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ramid | +0.655 |
axter | +0.633 |
itect | +0.630 |
eele | +0.628 |
olyn | +0.609 |
Neg logit contributions | |
Uni | -0.667 |
xit | -0.666 |
ctors | -0.626 |
Honour | -0.589 |
culosis | -0.530 |
Token | of |
Token ID | 286 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
xit | +0.590 |
Uni | +0.584 |
ctors | +0.550 |
Honour | +0.514 |
culosis | +0.461 |
Neg logit contributions | |
ramid | -0.688 |
axter | -0.660 |
itect | -0.659 |
eele | -0.656 |
hare | -0.638 |
Token | oul |
Token ID | 2852 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ramid | +0.392 |
axter | +0.373 |
itect | +0.373 |
hare | +0.368 |
eele | +0.368 |
Neg logit contributions | |
xit | -0.332 |
Uni | -0.326 |
ctors | -0.308 |
Honour | -0.282 |
nces | -0.254 |
Token | ouse |
Token ID | 1076 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
ramid | +0.594 |
eele | +0.559 |
axter | +0.548 |
itect | +0.546 |
hare | +0.534 |
Neg logit contributions | |
Uni | -0.963 |
xit | -0.962 |
ctors | -0.918 |
Honour | -0.873 |
culosis | -0.825 |
Token | ) |
Token ID | 8 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
ramid | +1.119 |
itect | +1.074 |
axter | +1.070 |
eele | +1.065 |
hare | +1.045 |
Neg logit contributions | |
xit | -1.246 |
Uni | -1.218 |
ctors | -1.160 |
Honour | -1.086 |
culosis | -1.010 |
Token | trained |
Token ID | 8776 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
xit | +0.610 |
Uni | +0.609 |
ctors | +0.570 |
Honour | +0.532 |
culosis | +0.479 |
Neg logit contributions | |
ramid | -0.683 |
axter | -0.653 |
eele | -0.651 |
itect | -0.648 |
hare | -0.637 |
Token | individual |
Token ID | 1981 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
Uni | +0.663 |
xit | +0.660 |
ctors | +0.618 |
Honour | +0.579 |
culosis | +0.515 |
Neg logit contributions | |
ramid | -0.763 |
itect | -0.724 |
axter | -0.721 |
eele | -0.721 |
olyn | -0.703 |
Token | honey |
Token ID | 12498 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
ramid | +1.585 |
itect | +1.514 |
axter | +1.510 |
eele | +1.503 |
hare | +1.470 |
Neg logit contributions | |
xit | -1.716 |
Uni | -1.690 |
ctors | -1.602 |
Honour | -1.503 |
culosis | -1.386 |
Token | bees |
Token ID | 41712 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
ramid | +3.627 |
itect | +3.619 |
axter | +3.595 |
eele | +3.557 |
hare | +3.476 |
Neg logit contributions | |
xit | -8.090 |
Uni | -7.920 |
ctors | -7.458 |
Honour | -7.325 |
culosis | -6.858 |
Token | to |
Token ID | 284 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
ramid | +3.850 |
axter | +3.698 |
itect | +3.695 |
eele | +3.670 |
hare | +3.630 |
Neg logit contributions | |
xit | -4.314 |
Uni | -4.192 |
ctors | -4.009 |
Honour | -3.743 |
culosis | -3.506 |
Token | fly |
Token ID | 6129 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Uni | +0.928 |
xit | +0.923 |
ctors | +0.882 |
Honour | +0.820 |
culosis | +0.742 |
Neg logit contributions | |
ramid | -0.907 |
eele | -0.867 |
itect | -0.865 |
axter | -0.859 |
olyn | -0.846 |
Token | into |
Token ID | 656 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
Uni | +0.597 |
xit | +0.589 |
ctors | +0.550 |
Honour | +0.516 |
culosis | +0.459 |
Neg logit contributions | |
ramid | -0.673 |
eele | -0.646 |
itect | -0.642 |
axter | -0.639 |
olyn | -0.622 |
Token | a |
Token ID | 257 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
ramid | +1.265 |
axter | +1.213 |
eele | +1.207 |
itect | +1.206 |
hare | +1.181 |
Neg logit contributions | |
xit | -1.209 |
Uni | -1.198 |
ctors | -1.125 |
Honour | -1.052 |
culosis | -0.954 |
Token | military |
Token ID | 2422 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
ramid | +0.264 |
itect | +0.254 |
eele | +0.252 |
axter | +0.252 |
hare | +0.246 |
Neg logit contributions | |
xit | -0.242 |
Uni | -0.242 |
ctors | -0.224 |
Honour | -0.212 |
culosis | -0.190 |
Token | and |
Token ID | 290 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
ramid | +0.508 |
itect | +0.488 |
eele | +0.488 |
axter | +0.487 |
hare | +0.479 |
Neg logit contributions | |
Uni | -0.491 |
xit | -0.490 |
ctors | -0.458 |
Honour | -0.429 |
culosis | -0.392 |
Token | the |
Token ID | 262 |
Feature activation | +7.47e-04 |
Pos logit contributions | |
Uni | +0.201 |
xit | +0.200 |
ctors | +0.186 |
Honour | +0.175 |
culosis | +0.158 |
Neg logit contributions | |
ramid | -0.209 |
eele | -0.199 |
itect | -0.199 |
axter | -0.198 |
hare | -0.195 |
Token | Department |
Token ID | 2732 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Uni | +0.002 |
xit | +0.002 |
ctors | +0.002 |
Honour | +0.001 |
culosis | +0.001 |
Neg logit contributions | |
ramid | -0.002 |
itect | -0.002 |
eele | -0.002 |
axter | -0.002 |
hare | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
ramid | +0.247 |
axter | +0.238 |
eele | +0.237 |
itect | +0.237 |
hare | +0.231 |
Neg logit contributions | |
xit | -0.202 |
Uni | -0.199 |
ctors | -0.185 |
Honour | -0.173 |
culosis | -0.156 |
Token | Homeland |
Token ID | 17444 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
ramid | +1.106 |
axter | +1.065 |
itect | +1.058 |
eele | +1.057 |
hare | +1.034 |
Neg logit contributions | |
xit | -0.975 |
Uni | -0.964 |
ctors | -0.897 |
Honour | -0.848 |
culosis | -0.763 |
Token | Security |
Token ID | 4765 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
ramid | +5.130 |
itect | +4.994 |
eele | +4.922 |
axter | +4.815 |
olyn | +4.748 |
Neg logit contributions | |
xit | -6.715 |
Uni | -6.520 |
ctors | -6.276 |
Honour | -5.820 |
culosis | -5.574 |
Token | have |
Token ID | 423 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
ramid | +4.459 |
itect | +4.292 |
axter | +4.273 |
eele | +4.244 |
hare | +4.187 |
Neg logit contributions | |
xit | -5.028 |
Uni | -4.841 |
ctors | -4.659 |
Honour | -4.341 |
culosis | -4.069 |
Token | set |
Token ID | 900 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
ramid | +1.521 |
eele | +1.456 |
axter | +1.453 |
itect | +1.453 |
hare | +1.412 |
Neg logit contributions | |
xit | -1.677 |
Uni | -1.662 |
ctors | -1.572 |
Honour | -1.474 |
culosis | -1.359 |
Token | in |
Token ID | 287 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
Uni | +0.471 |
xit | +0.468 |
ctors | +0.436 |
Honour | +0.411 |
culosis | +0.376 |
Neg logit contributions | |
ramid | -0.503 |
eele | -0.481 |
itect | -0.481 |
axter | -0.481 |
hare | -0.469 |
Token | motion |
Token ID | 6268 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Uni | +0.446 |
xit | +0.437 |
ctors | +0.395 |
Honour | +0.365 |
culosis | +0.313 |
Neg logit contributions | |
ramid | -0.896 |
axter | -0.862 |
itect | -0.859 |
eele | -0.854 |
hare | -0.843 |
Token | the |
Token ID | 262 |
Feature activation | +7.06e-03 |
Pos logit contributions | |
ramid | +0.539 |
itect | +0.517 |
axter | +0.516 |
eele | +0.514 |
hare | +0.504 |
Neg logit contributions | |
xit | -0.534 |
Uni | -0.526 |
ctors | -0.495 |
Honour | -0.462 |
culosis | -0.425 |
Token | upper |
Token ID | 6727 |
Feature activation | -4.62e-03 |
Pos logit contributions | |
xit | +0.015 |
Uni | +0.015 |
ctors | +0.014 |
Honour | +0.013 |
culosis | +0.012 |
Neg logit contributions | |
ramid | -0.016 |
itect | -0.015 |
axter | -0.015 |
eele | -0.015 |
hare | -0.015 |
Token | portion |
Token ID | 6903 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ramid | +0.010 |
itect | +0.010 |
axter | +0.010 |
eele | +0.010 |
hare | +0.009 |
Neg logit contributions | |
xit | -0.010 |
Uni | -0.010 |
ctors | -0.009 |
Honour | -0.009 |
culosis | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
ramid | +0.490 |
itect | +0.471 |
axter | +0.471 |
eele | +0.468 |
hare | +0.459 |
Neg logit contributions | |
xit | -0.436 |
Uni | -0.427 |
ctors | -0.401 |
Honour | -0.372 |
culosis | -0.341 |
Token | the |
Token ID | 262 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
ramid | +0.890 |
itect | +0.856 |
axter | +0.855 |
eele | +0.850 |
hare | +0.834 |
Neg logit contributions | |
xit | -0.879 |
Uni | -0.866 |
ctors | -0.813 |
Honour | -0.762 |
culosis | -0.700 |
Token | shif |
Token ID | 7143 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
ramid | +0.970 |
itect | +0.935 |
axter | +0.931 |
eele | +0.926 |
hare | +0.907 |
Neg logit contributions | |
xit | -0.946 |
Uni | -0.935 |
ctors | -0.874 |
Honour | -0.820 |
culosis | -0.752 |
Token | ter |
Token ID | 353 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
ramid | +3.284 |
itect | +3.028 |
eele | +3.027 |
axter | +2.942 |
hare | +2.924 |
Neg logit contributions | |
xit | -8.594 |
Uni | -8.426 |
ctors | -8.074 |
Honour | -7.782 |
culosis | -7.447 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
ramid | +1.749 |
itect | +1.679 |
axter | +1.676 |
eele | +1.668 |
hare | +1.636 |
Neg logit contributions | |
xit | -1.790 |
Uni | -1.753 |
ctors | -1.662 |
Honour | -1.553 |
culosis | -1.437 |
Token | You |
Token ID | 921 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
ramid | +0.670 |
itect | +0.642 |
axter | +0.641 |
eele | +0.639 |
hare | +0.626 |
Neg logit contributions | |
xit | -0.611 |
Uni | -0.602 |
ctors | -0.564 |
Honour | -0.528 |
culosis | -0.481 |
Token | DO |
Token ID | 8410 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
ramid | +0.809 |
itect | +0.780 |
axter | +0.777 |
eele | +0.774 |
hare | +0.757 |
Neg logit contributions | |
xit | -0.762 |
Uni | -0.750 |
ctors | -0.708 |
Honour | -0.659 |
culosis | -0.604 |
Token | NOT |
Token ID | 5626 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ramid | +1.260 |
itect | +1.199 |
axter | +1.197 |
eele | +1.191 |
hare | +1.161 |
Neg logit contributions | |
xit | -1.502 |
Uni | -1.473 |
ctors | -1.404 |
Honour | -1.310 |
culosis | -1.220 |
Token | com |
Token ID | 785 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
xit | +0.349 |
Uni | +0.342 |
ctors | +0.325 |
Honour | +0.301 |
culosis | +0.273 |
Neg logit contributions | |
ramid | -0.361 |
axter | -0.349 |
eele | -0.345 |
itect | -0.340 |
hare | -0.332 |
Token | / |
Token ID | 14 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
xit | +2.057 |
Uni | +2.017 |
ctors | +1.909 |
Honour | +1.777 |
culosis | +1.633 |
Neg logit contributions | |
ramid | -2.130 |
itect | -2.041 |
axter | -2.034 |
eele | -2.027 |
hare | -1.985 |
Token | om |
Token ID | 296 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
xit | +1.640 |
Uni | +1.583 |
ctors | +1.520 |
Honour | +1.406 |
culosis | +1.316 |
Neg logit contributions | |
ramid | -1.402 |
itect | -1.334 |
eele | -1.325 |
axter | -1.324 |
hare | -1.281 |
Token | g |
Token ID | 70 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
ramid | +0.639 |
itect | +0.613 |
axter | +0.609 |
eele | +0.609 |
hare | +0.592 |
Neg logit contributions | |
xit | -0.730 |
Uni | -0.709 |
ctors | -0.681 |
Honour | -0.635 |
culosis | -0.591 |
Token | its |
Token ID | 896 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ramid | +0.538 |
itect | +0.513 |
axter | +0.513 |
eele | +0.511 |
hare | +0.501 |
Neg logit contributions | |
xit | -0.597 |
Uni | -0.581 |
ctors | -0.556 |
Honour | -0.516 |
culosis | -0.482 |
Token | amb |
Token ID | 4131 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
ramid | +2.175 |
itect | +2.084 |
axter | +2.080 |
eele | +2.070 |
hare | +2.028 |
Neg logit contributions | |
xit | -2.421 |
Uni | -2.372 |
ctors | -2.255 |
Honour | -2.113 |
culosis | -1.963 |
Token | ry |
Token ID | 563 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ramid | +5.661 |
axter | +5.530 |
itect | +5.521 |
eele | +5.474 |
azo | +5.331 |
Neg logit contributions | |
xit | -6.138 |
Uni | -6.105 |
ctors | -5.711 |
Honour | -5.407 |
culosis | -4.983 |
Token | / |
Token ID | 14 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ramid | +3.185 |
itect | +3.047 |
axter | +3.042 |
eele | +3.029 |
hare | +2.971 |
Neg logit contributions | |
xit | -3.264 |
Uni | -3.202 |
ctors | -3.033 |
Honour | -2.852 |
culosis | -2.633 |
Token | status |
Token ID | 13376 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
ramid | +0.573 |
axter | +0.556 |
eele | +0.552 |
itect | +0.550 |
hare | +0.533 |
Neg logit contributions | |
xit | -0.517 |
Uni | -0.507 |
ctors | -0.479 |
Honour | -0.442 |
culosis | -0.409 |
Token | / |
Token ID | 14 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
xit | +0.302 |
Uni | +0.293 |
ctors | +0.279 |
Honour | +0.259 |
culosis | +0.228 |
Neg logit contributions | |
ramid | -0.346 |
axter | -0.332 |
eele | -0.328 |
itect | -0.327 |
olyn | -0.319 |
Token | 9 |
Token ID | 24 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
xit | +2.117 |
Uni | +2.069 |
ctors | +1.980 |
Honour | +1.838 |
culosis | +1.669 |
Neg logit contributions | |
ramid | -1.994 |
axter | -1.879 |
eele | -1.870 |
itect | -1.857 |
olyn | -1.806 |
Token | occupational |
Token ID | 34266 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ramid | +0.321 |
itect | +0.310 |
axter | +0.310 |
eele | +0.308 |
hare | +0.302 |
Neg logit contributions | |
xit | -0.225 |
Uni | -0.220 |
ctors | -0.206 |
Honour | -0.189 |
culosis | -0.170 |
Token | exposure |
Token ID | 7111 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
ramid | +0.627 |
itect | +0.609 |
axter | +0.607 |
eele | +0.605 |
hare | +0.594 |
Neg logit contributions | |
xit | -0.350 |
Uni | -0.341 |
ctors | -0.315 |
Honour | -0.285 |
culosis | -0.253 |
Token | was |
Token ID | 373 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
xit | +1.353 |
Uni | +1.340 |
ctors | +1.261 |
Honour | +1.174 |
culosis | +1.068 |
Neg logit contributions | |
ramid | -1.539 |
itect | -1.482 |
axter | -1.473 |
eele | -1.459 |
hare | -1.421 |
Token | 0 |
Token ID | 657 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
ramid | +0.290 |
itect | +0.280 |
axter | +0.279 |
eele | +0.277 |
hare | +0.271 |
Neg logit contributions | |
xit | -0.238 |
Uni | -0.234 |
ctors | -0.220 |
Honour | -0.204 |
culosis | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
xit | +0.812 |
Uni | +0.802 |
ctors | +0.762 |
Honour | +0.714 |
culosis | +0.669 |
Neg logit contributions | |
ramid | -0.706 |
axter | -0.677 |
itect | -0.676 |
eele | -0.666 |
hare | -0.651 |
Token | 06 |
Token ID | 3312 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
xit | +1.864 |
Uni | +1.823 |
ctors | +1.742 |
Honour | +1.630 |
culosis | +1.464 |
Neg logit contributions | |
ramid | -1.673 |
axter | -1.605 |
eele | -1.576 |
itect | -1.571 |
olyn | -1.537 |
Token | m |
Token ID | 285 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
Uni | +4.589 |
xit | +4.562 |
ctors | +4.327 |
Honour | +3.996 |
culosis | +3.702 |
Neg logit contributions | |
ramid | -4.362 |
axter | -4.128 |
itect | -4.106 |
eele | -4.069 |
hare | -3.930 |
Token | S |
Token ID | 50 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ramid | +0.384 |
itect | +0.366 |
axter | +0.364 |
eele | +0.362 |
hare | +0.349 |
Neg logit contributions | |
xit | -0.508 |
Uni | -0.497 |
ctors | -0.476 |
Honour | -0.447 |
culosis | -0.417 |
Token | v |
Token ID | 85 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
ramid | +0.544 |
itect | +0.518 |
axter | +0.517 |
eele | +0.514 |
hare | +0.502 |
Neg logit contributions | |
xit | -0.741 |
Uni | -0.728 |
ctors | -0.695 |
Honour | -0.655 |
culosis | -0.613 |
Token | per |
Token ID | 583 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
ramid | +1.680 |
itect | +1.611 |
axter | +1.606 |
eele | +1.600 |
hare | +1.569 |
Neg logit contributions | |
xit | -1.813 |
Uni | -1.775 |
ctors | -1.685 |
Honour | -1.578 |
culosis | -1.465 |
Token | person |
Token ID | 1048 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ramid | +1.494 |
axter | +1.433 |
itect | +1.430 |
eele | +1.423 |
hare | +1.385 |
Neg logit contributions | |
xit | -1.522 |
Uni | -1.493 |
ctors | -1.411 |
Honour | -1.319 |
culosis | -1.216 |
Token | bowl |
Token ID | 36859 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
ramid | +1.873 |
axter | +1.798 |
itect | +1.796 |
eele | +1.780 |
hare | +1.744 |
Neg logit contributions | |
xit | -2.114 |
Uni | -2.081 |
ctors | -1.975 |
Honour | -1.854 |
culosis | -1.720 |
Token | - |
Token ID | 12 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
xit | +1.307 |
Uni | +1.296 |
ctors | +1.213 |
Honour | +1.140 |
culosis | +1.035 |
Neg logit contributions | |
ramid | -1.447 |
axter | -1.401 |
itect | -1.390 |
eele | -1.381 |
hare | -1.348 |
Token | Italian |
Token ID | 45696 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
ramid | +0.341 |
itect | +0.327 |
axter | +0.327 |
eele | +0.325 |
hare | +0.315 |
Neg logit contributions | |
xit | -0.403 |
Uni | -0.395 |
ctors | -0.377 |
Honour | -0.353 |
culosis | -0.327 |
Token | St |
Token ID | 520 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
xit | +1.125 |
Uni | +1.117 |
ctors | +1.045 |
Honour | +0.972 |
culosis | +0.877 |
Neg logit contributions | |
ramid | -1.362 |
axter | -1.323 |
eele | -1.305 |
itect | -1.301 |
hare | -1.279 |
Token | ere |
Token ID | 567 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
xit | +1.853 |
Uni | +1.835 |
ctors | +1.736 |
Honour | +1.622 |
culosis | +1.488 |
Neg logit contributions | |
ramid | -1.683 |
axter | -1.598 |
itect | -1.598 |
eele | -1.558 |
hare | -1.545 |
Token | otypes |
Token ID | 13567 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
xit | +3.796 |
Uni | +3.698 |
ctors | +3.589 |
Honour | +3.346 |
culosis | +3.123 |
Neg logit contributions | |
ramid | -2.743 |
eele | -2.590 |
axter | -2.585 |
itect | -2.565 |
hare | -2.519 |
Token | - |
Token ID | 12 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Uni | +4.707 |
xit | +4.657 |
ctors | +4.325 |
Honour | +4.070 |
culosis | +3.701 |
Neg logit contributions | |
ramid | -5.026 |
itect | -4.882 |
axter | -4.871 |
eele | -4.790 |
hare | -4.645 |
Token | Ret |
Token ID | 9781 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ramid | +0.849 |
itect | +0.813 |
axter | +0.812 |
eele | +0.808 |
hare | +0.785 |
Neg logit contributions | |
xit | -1.005 |
Uni | -0.986 |
ctors | -0.938 |
Honour | -0.880 |
culosis | -0.817 |
Token | ards |
Token ID | 1371 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
xit | +3.185 |
Uni | +3.143 |
ctors | +2.973 |
Honour | +2.728 |
culosis | +2.474 |
Neg logit contributions | |
ramid | -3.827 |
axter | -3.745 |
itect | -3.705 |
eele | -3.675 |
hare | -3.644 |
Token | - |
Token ID | 12 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Uni | +3.442 |
xit | +3.430 |
ctors | +3.169 |
Honour | +3.001 |
culosis | +2.712 |
Neg logit contributions | |
ramid | -3.856 |
axter | -3.737 |
eele | -3.719 |
itect | -3.704 |
azo | -3.551 |
Token | RAM |
Token ID | 24115 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ramid | +0.677 |
itect | +0.648 |
axter | +0.647 |
eele | +0.644 |
hare | +0.626 |
Neg logit contributions | |
xit | -0.796 |
Uni | -0.781 |
ctors | -0.743 |
Honour | -0.697 |
culosis | -0.647 |
Token | say |
Token ID | 910 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
xit | +0.229 |
Uni | +0.227 |
ctors | +0.216 |
Honour | +0.202 |
culosis | +0.186 |
Neg logit contributions | |
ramid | -0.209 |
itect | -0.201 |
axter | -0.200 |
eele | -0.199 |
hare | -0.195 |
Token | the |
Token ID | 262 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
xit | +0.042 |
Uni | +0.041 |
ctors | +0.038 |
Honour | +0.036 |
culosis | +0.033 |
Neg logit contributions | |
ramid | -0.044 |
itect | -0.042 |
axter | -0.041 |
eele | -0.041 |
hare | -0.040 |
Token | bill |
Token ID | 2855 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
ramid | +0.080 |
itect | +0.077 |
axter | +0.076 |
eele | +0.076 |
hare | +0.074 |
Neg logit contributions | |
xit | -0.081 |
Uni | -0.081 |
ctors | -0.075 |
Honour | -0.072 |
culosis | -0.065 |
Token | would |
Token ID | 561 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
xit | +1.099 |
Uni | +1.080 |
ctors | +1.010 |
Honour | +0.956 |
culosis | +0.861 |
Neg logit contributions | |
ramid | -1.279 |
axter | -1.229 |
itect | -1.225 |
eele | -1.225 |
hare | -1.188 |
Token | increase |
Token ID | 2620 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
xit | +1.142 |
Uni | +1.114 |
ctors | +1.071 |
Honour | +1.005 |
culosis | +0.912 |
Neg logit contributions | |
ramid | -1.120 |
eele | -1.089 |
itect | -1.087 |
axter | -1.078 |
ippi | -1.046 |
Token | GDP |
Token ID | 12396 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
xit | +0.152 |
Uni | +0.149 |
ctors | +0.140 |
Honour | +0.131 |
culosis | +0.120 |
Neg logit contributions | |
ramid | -0.159 |
itect | -0.153 |
eele | -0.151 |
axter | -0.151 |
hare | -0.148 |
Token | was |
Token ID | 373 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
xit | +4.131 |
Uni | +4.091 |
ctors | +3.754 |
Honour | +3.620 |
nces | +3.192 |
Neg logit contributions | |
ramid | -4.999 |
axter | -4.776 |
itect | -4.744 |
eele | -4.721 |
olyn | -4.558 |
Token | Stanford |
Token ID | 13863 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
xit | +0.380 |
Uni | +0.379 |
ctors | +0.353 |
Honour | +0.332 |
culosis | +0.300 |
Neg logit contributions | |
ramid | -0.414 |
itect | -0.395 |
eele | -0.391 |
axter | -0.391 |
hare | -0.382 |
Token | � |
Token ID | 447 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Uni | +5.540 |
xit | +5.412 |
ctors | +5.132 |
Honour | +4.818 |
culosis | +4.470 |
Neg logit contributions | |
ramid | -4.309 |
axter | -4.038 |
eele | -3.982 |
hare | -3.923 |
itect | -3.878 |
Token | � |
Token ID | 247 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
xit | +0.413 |
Uni | +0.399 |
ctors | +0.372 |
Honour | +0.344 |
culosis | +0.304 |
Neg logit contributions | |
ramid | -0.632 |
axter | -0.609 |
eele | -0.605 |
itect | -0.603 |
hare | -0.597 |
Token | s |
Token ID | 82 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
xit | +0.697 |
Uni | +0.688 |
ctors | +0.653 |
Honour | +0.610 |
culosis | +0.564 |
Neg logit contributions | |
ramid | -0.638 |
axter | -0.601 |
itect | -0.598 |
eele | -0.597 |
hare | -0.587 |
Token | U |
Token ID | 471 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
Uni | +4.107 |
xit | +4.042 |
ctors | +3.826 |
Honour | +3.596 |
culosis | +3.234 |
Neg logit contributions | |
ramid | -4.390 |
axter | -4.281 |
itect | -4.225 |
eele | -4.199 |
olyn | -4.055 |
Token | gly |
Token ID | 10853 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
xit | +1.620 |
Uni | +1.603 |
ctors | +1.511 |
Honour | +1.384 |
culosis | +1.284 |
Neg logit contributions | |
ramid | -1.806 |
axter | -1.763 |
itect | -1.761 |
eele | -1.740 |
hare | -1.714 |
Token | Girl |
Token ID | 7430 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Uni | +2.268 |
xit | +2.239 |
ctors | +2.089 |
Honour | +1.941 |
culosis | +1.736 |
Neg logit contributions | |
ramid | -2.870 |
axter | -2.821 |
eele | -2.759 |
itect | -2.759 |
hare | -2.692 |
Token | - |
Token ID | 12 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
xit | +2.299 |
Uni | +2.292 |
ctors | +2.143 |
Honour | +1.995 |
culosis | +1.825 |
Neg logit contributions | |
ramid | -2.410 |
itect | -2.346 |
axter | -2.338 |
eele | -2.327 |
hare | -2.257 |
Token | False |
Token ID | 25101 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
ramid | +0.440 |
itect | +0.421 |
axter | +0.421 |
eele | +0.419 |
hare | +0.406 |
Neg logit contributions | |
xit | -0.509 |
Uni | -0.500 |
ctors | -0.476 |
Honour | -0.446 |
culosis | -0.413 |
Token | Conv |
Token ID | 34872 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ramid | +1.325 |
itect | +1.279 |
axter | +1.277 |
eele | +1.271 |
hare | +1.250 |
Neg logit contributions | |
xit | -1.029 |
Uni | -1.005 |
ctors | -0.945 |
Honour | -0.872 |
culosis | -0.795 |
Token | ictions |
Token ID | 9278 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
xit | +5.358 |
Uni | +5.306 |
ctors | +5.114 |
Honour | +4.648 |
nces | +4.324 |
Neg logit contributions | |
ramid | -5.076 |
axter | -4.863 |
hare | -4.782 |
eele | -4.775 |
itect | -4.727 |
Token | - |
Token ID | 12 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Uni | +3.188 |
xit | +3.168 |
ctors | +2.938 |
Honour | +2.773 |
culosis | +2.510 |
Neg logit contributions | |
ramid | -3.443 |
itect | -3.341 |
axter | -3.325 |
eele | -3.309 |
hare | -3.187 |
Token | Big |
Token ID | 12804 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
ramid | +0.402 |
itect | +0.385 |
axter | +0.385 |
eele | +0.383 |
hare | +0.371 |
Neg logit contributions | |
xit | -0.466 |
Uni | -0.457 |
ctors | -0.435 |
Honour | -0.408 |
culosis | -0.377 |
Token | gest |
Token ID | 3495 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
xit | +1.104 |
Uni | +1.088 |
ctors | +1.021 |
Honour | +0.931 |
culosis | +0.847 |
Neg logit contributions | |
ramid | -1.524 |
axter | -1.491 |
itect | -1.482 |
eele | -1.465 |
hare | -1.443 |
Token | G |
Token ID | 402 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
Uni | +2.392 |
xit | +2.382 |
ctors | +2.228 |
Honour | +2.079 |
culosis | +1.863 |
Neg logit contributions | |
ramid | -2.892 |
axter | -2.856 |
itect | -2.812 |
eele | -2.768 |
hare | -2.706 |
Token | и |
Token ID | 18849 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
xit | +0.797 |
Uni | +0.777 |
ctors | +0.734 |
Honour | +0.690 |
culosis | +0.637 |
Neg logit contributions | |
ramid | -0.808 |
axter | -0.781 |
eele | -0.774 |
itect | -0.773 |
hare | -0.761 |
Token | я |
Token ID | 40623 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
xit | +2.017 |
Uni | +1.967 |
ctors | +1.839 |
Honour | +1.726 |
culosis | +1.608 |
Neg logit contributions | |
ramid | -1.962 |
axter | -1.914 |
itect | -1.908 |
eele | -1.886 |
hare | -1.843 |
Token | � |
Token ID | 141 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
xit | +2.199 |
Uni | +2.169 |
ctors | +2.021 |
Honour | +1.903 |
culosis | +1.753 |
Neg logit contributions | |
ramid | -2.182 |
axter | -2.114 |
eele | -2.093 |
itect | -2.084 |
hare | -2.025 |
Token | � |
Token ID | 227 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
ramid | +2.419 |
itect | +2.304 |
axter | +2.294 |
eele | +2.275 |
hare | +2.226 |
Neg logit contributions | |
xit | -3.393 |
Uni | -3.331 |
ctors | -3.188 |
Honour | -2.997 |
culosis | -2.819 |
Token | � |
Token ID | 12466 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
ramid | +1.590 |
itect | +1.524 |
axter | +1.521 |
eele | +1.514 |
hare | +1.483 |
Neg logit contributions | |
xit | -1.741 |
Uni | -1.706 |
ctors | -1.621 |
Honour | -1.518 |
culosis | -1.409 |
Token | � |
Token ID | 121 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
xit | +0.993 |
Uni | +0.961 |
ctors | +0.907 |
Honour | +0.834 |
culosis | +0.759 |
Neg logit contributions | |
ramid | -1.357 |
eele | -1.315 |
itect | -1.314 |
axter | -1.314 |
hare | -1.287 |
Token | а |
Token ID | 16142 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
xit | +4.117 |
Uni | +3.938 |
ctors | +3.739 |
Honour | +3.459 |
culosis | +3.115 |
Neg logit contributions | |
ramid | -5.101 |
axter | -4.927 |
eele | -4.870 |
itect | -4.855 |
hare | -4.765 |
Token | � |
Token ID | 12466 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
xit | +3.664 |
Uni | +3.590 |
ctors | +3.395 |
Honour | +3.195 |
culosis | +2.925 |
Neg logit contributions | |
ramid | -3.205 |
axter | -3.079 |
eele | -3.055 |
itect | -3.055 |
hare | -2.947 |
Token | � |
Token ID | 242 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
xit | +1.224 |
Uni | +1.185 |
ctors | +1.122 |
Honour | +1.036 |
culosis | +0.949 |
Neg logit contributions | |
ramid | -1.514 |
eele | -1.470 |
itect | -1.468 |
axter | -1.463 |
hare | -1.430 |
Token | о |
Token ID | 15166 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
xit | +1.447 |
Uni | +1.412 |
ctors | +1.341 |
Honour | +1.263 |
culosis | +1.153 |
Neg logit contributions | |
ramid | -1.318 |
axter | -1.269 |
eele | -1.262 |
itect | -1.261 |
hare | -1.234 |
Token | н |
Token ID | 22177 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
xit | +2.659 |
Uni | +2.610 |
ctors | +2.449 |
Honour | +2.337 |
culosis | +2.092 |
Neg logit contributions | |
ramid | -2.734 |
axter | -2.658 |
eele | -2.631 |
itect | -2.628 |
hare | -2.562 |
Token | concludes |
Token ID | 18978 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
xit | +0.805 |
Uni | +0.787 |
ctors | +0.741 |
Honour | +0.688 |
culosis | +0.619 |
Neg logit contributions | |
ramid | -1.037 |
itect | -0.992 |
axter | -0.988 |
eele | -0.985 |
hare | -0.968 |
Token | . |
Token ID | 13 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
ramid | +0.065 |
itect | +0.062 |
axter | +0.062 |
eele | +0.061 |
hare | +0.060 |
Neg logit contributions | |
xit | -0.082 |
Uni | -0.081 |
ctors | -0.077 |
Honour | -0.072 |
culosis | -0.068 |
Token | Which |
Token ID | 9022 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ramid | +0.096 |
itect | +0.092 |
axter | +0.092 |
eele | +0.092 |
hare | +0.090 |
Neg logit contributions | |
xit | -0.098 |
Uni | -0.096 |
ctors | -0.091 |
Honour | -0.085 |
culosis | -0.079 |
Token | means |
Token ID | 1724 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ramid | +0.425 |
itect | +0.408 |
axter | +0.403 |
eele | +0.400 |
hare | +0.395 |
Neg logit contributions | |
xit | -0.404 |
Uni | -0.400 |
ctors | -0.375 |
Honour | -0.354 |
culosis | -0.322 |
Token | the |
Token ID | 262 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
xit | +0.319 |
Uni | +0.316 |
ctors | +0.297 |
Honour | +0.281 |
culosis | +0.254 |
Neg logit contributions | |
ramid | -0.345 |
itect | -0.329 |
axter | -0.327 |
eele | -0.322 |
hare | -0.316 |
Token | rest |
Token ID | 1334 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
ramid | +0.775 |
itect | +0.746 |
axter | +0.744 |
eele | +0.741 |
hare | +0.728 |
Neg logit contributions | |
xit | -0.680 |
Uni | -0.665 |
ctors | -0.628 |
Honour | -0.583 |
culosis | -0.535 |
Token | of |
Token ID | 286 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
xit | +1.224 |
Uni | +1.197 |
ctors | +1.131 |
Honour | +1.049 |
culosis | +0.962 |
Neg logit contributions | |
ramid | -1.402 |
itect | -1.346 |
axter | -1.344 |
eele | -1.338 |
hare | -1.313 |
Token | us |
Token ID | 514 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
ramid | +0.367 |
itect | +0.353 |
axter | +0.352 |
eele | +0.350 |
hare | +0.343 |
Neg logit contributions | |
xit | -0.321 |
Uni | -0.315 |
ctors | -0.297 |
Honour | -0.277 |
culosis | -0.252 |
Token | can |
Token ID | 460 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
ramid | +0.077 |
itect | +0.074 |
axter | +0.073 |
eele | +0.073 |
hare | +0.071 |
Neg logit contributions | |
xit | -0.080 |
Uni | -0.079 |
ctors | -0.075 |
Honour | -0.070 |
culosis | -0.065 |
Token | listen |
Token ID | 6004 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ramid | +0.604 |
itect | +0.581 |
axter | +0.580 |
eele | +0.578 |
hare | +0.566 |
Neg logit contributions | |
xit | -0.561 |
Uni | -0.550 |
ctors | -0.523 |
Honour | -0.486 |
culosis | -0.446 |
Token | to |
Token ID | 284 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
xit | +0.389 |
Uni | +0.382 |
ctors | +0.362 |
Honour | +0.340 |
culosis | +0.312 |
Neg logit contributions | |
ramid | -0.374 |
itect | -0.358 |
axter | -0.357 |
eele | -0.356 |
hare | -0.347 |
Token | explains |
Token ID | 6688 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
ramid | +0.746 |
itect | +0.718 |
axter | +0.714 |
eele | +0.713 |
hare | +0.699 |
Neg logit contributions | |
xit | -0.580 |
Uni | -0.567 |
ctors | -0.535 |
Honour | -0.494 |
culosis | -0.448 |
Token | that |
Token ID | 326 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
ramid | +1.860 |
axter | +1.787 |
itect | +1.784 |
eele | +1.778 |
hare | +1.744 |
Neg logit contributions | |
xit | -2.001 |
Uni | -1.957 |
ctors | -1.861 |
Honour | -1.737 |
culosis | -1.617 |
Token | Wagner |
Token ID | 26451 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ramid | +0.471 |
itect | +0.452 |
axter | +0.448 |
eele | +0.446 |
hare | +0.437 |
Neg logit contributions | |
xit | -0.407 |
Uni | -0.401 |
ctors | -0.378 |
Honour | -0.353 |
culosis | -0.319 |
Token | never |
Token ID | 1239 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
xit | +2.171 |
Uni | +2.153 |
ctors | +2.067 |
Honour | +1.927 |
culosis | +1.761 |
Neg logit contributions | |
ramid | -2.332 |
axter | -2.205 |
itect | -2.191 |
eele | -2.182 |
hare | -2.125 |
Token | visited |
Token ID | 8672 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
ramid | +1.981 |
itect | +1.901 |
axter | +1.897 |
eele | +1.889 |
hare | +1.851 |
Neg logit contributions | |
xit | -1.978 |
Uni | -1.938 |
ctors | -1.838 |
Honour | -1.715 |
culosis | -1.584 |
Token | Brah |
Token ID | 36415 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
ramid | +0.184 |
itect | +0.177 |
axter | +0.176 |
eele | +0.176 |
hare | +0.172 |
Neg logit contributions | |
xit | -0.155 |
Uni | -0.152 |
ctors | -0.143 |
Honour | -0.133 |
culosis | -0.121 |
Token | ms |
Token ID | 907 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
xit | +1.169 |
Uni | +1.114 |
ctors | +1.092 |
Honour | +0.979 |
nces | +0.905 |
Neg logit contributions | |
ramid | -1.549 |
eele | -1.515 |
itect | -1.508 |
axter | -1.491 |
hare | -1.472 |
Token | 's |
Token ID | 338 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
ramid | +0.258 |
eele | +0.247 |
axter | +0.247 |
itect | +0.246 |
hare | +0.239 |
Neg logit contributions | |
xit | -0.275 |
Uni | -0.272 |
ctors | -0.258 |
Honour | -0.243 |
culosis | -0.224 |
Token | flat |
Token ID | 6228 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
ramid | +1.887 |
itect | +1.812 |
axter | +1.811 |
eele | +1.798 |
hare | +1.769 |
Neg logit contributions | |
xit | -1.946 |
Uni | -1.892 |
ctors | -1.800 |
Honour | -1.677 |
culosis | -1.562 |
Token | , |
Token ID | 11 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
xit | +1.888 |
Uni | +1.885 |
ctors | +1.785 |
Honour | +1.645 |
culosis | +1.513 |
Neg logit contributions | |
ramid | -2.055 |
axter | -1.962 |
eele | -1.960 |
itect | -1.957 |
hare | -1.888 |
Token | so |
Token ID | 523 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
xit | +0.804 |
Uni | +0.799 |
ctors | +0.747 |
Honour | +0.701 |
culosis | +0.630 |
Neg logit contributions | |
ramid | -0.949 |
itect | -0.906 |
eele | -0.902 |
axter | -0.899 |
hare | -0.880 |
Token | his |
Token ID | 465 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
ramid | +0.136 |
itect | +0.130 |
eele | +0.130 |
axter | +0.128 |
hare | +0.125 |
Neg logit contributions | |
xit | -0.121 |
Uni | -0.120 |
ctors | -0.112 |
Honour | -0.104 |
culosis | -0.094 |
Token | arm |
Token ID | 3211 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
ramid | +0.487 |
itect | +0.468 |
axter | +0.466 |
eele | +0.464 |
hare | +0.454 |
Neg logit contributions | |
xit | -0.485 |
Uni | -0.477 |
ctors | -0.450 |
Honour | -0.421 |
culosis | -0.388 |
Token | around |
Token ID | 1088 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
xit | +0.483 |
Uni | +0.482 |
ctors | +0.438 |
Honour | +0.396 |
culosis | +0.342 |
Neg logit contributions | |
ramid | -0.916 |
eele | -0.882 |
axter | -0.877 |
itect | -0.874 |
olyn | -0.853 |
Token | Robinson |
Token ID | 12652 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
ramid | +0.442 |
itect | +0.423 |
eele | +0.422 |
axter | +0.420 |
hare | +0.409 |
Neg logit contributions | |
xit | -0.449 |
Uni | -0.447 |
ctors | -0.419 |
Honour | -0.391 |
culosis | -0.358 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ramid | +1.098 |
itect | +1.048 |
axter | +1.047 |
eele | +1.044 |
hare | +1.020 |
Neg logit contributions | |
xit | -1.236 |
Uni | -1.218 |
ctors | -1.153 |
Honour | -1.082 |
culosis | -1.004 |
Token | Some |
Token ID | 2773 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
ramid | +0.366 |
axter | +0.350 |
itect | +0.347 |
eele | +0.347 |
hare | +0.340 |
Neg logit contributions | |
xit | -0.333 |
Uni | -0.331 |
ctors | -0.311 |
Honour | -0.290 |
culosis | -0.261 |
Token | other |
Token ID | 584 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
Uni | +1.604 |
xit | +1.596 |
ctors | +1.492 |
Honour | +1.403 |
culosis | +1.258 |
Neg logit contributions | |
ramid | -1.668 |
itect | -1.587 |
eele | -1.576 |
axter | -1.574 |
olyn | -1.540 |
Token | defenders |
Token ID | 16355 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
ramid | +1.338 |
itect | +1.276 |
axter | +1.270 |
eele | +1.265 |
hare | +1.237 |
Neg logit contributions | |
xit | -1.572 |
Uni | -1.556 |
ctors | -1.473 |
Honour | -1.388 |
culosis | -1.280 |
Token | join |
Token ID | 4654 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ramid | +1.635 |
itect | +1.568 |
axter | +1.563 |
eele | +1.557 |
hare | +1.520 |
Neg logit contributions | |
xit | -1.667 |
Uni | -1.640 |
ctors | -1.552 |
Honour | -1.451 |
culosis | -1.340 |
Token | in |
Token ID | 287 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
ramid | +2.701 |
axter | +2.601 |
itect | +2.595 |
eele | +2.583 |
hare | +2.547 |
Neg logit contributions | |
xit | -2.762 |
Uni | -2.688 |
ctors | -2.562 |
Honour | -2.389 |
culosis | -2.226 |
Token | , |
Token ID | 11 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
ramid | +0.503 |
itect | +0.480 |
eele | +0.477 |
axter | +0.477 |
hare | +0.463 |
Neg logit contributions | |
xit | -0.469 |
Uni | -0.467 |
ctors | -0.434 |
Honour | -0.406 |
culosis | -0.369 |
Token | - |
Token ID | 12 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
xit | +2.395 |
Uni | +2.382 |
ctors | +2.227 |
Honour | +2.091 |
culosis | +1.884 |
Neg logit contributions | |
ramid | -2.468 |
axter | -2.418 |
eele | -2.355 |
itect | -2.345 |
olyn | -2.303 |
Token | top |
Token ID | 4852 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
xit | +0.485 |
Uni | +0.474 |
ctors | +0.449 |
Honour | +0.418 |
culosis | +0.387 |
Neg logit contributions | |
ramid | -0.477 |
axter | -0.458 |
itect | -0.456 |
eele | -0.453 |
olyn | -0.441 |
Token | actor |
Token ID | 8674 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Uni | +1.150 |
xit | +1.147 |
ctors | +1.075 |
Honour | +1.004 |
culosis | +0.908 |
Neg logit contributions | |
ramid | -1.246 |
itect | -1.190 |
axter | -1.184 |
eele | -1.180 |
hare | -1.140 |
Token | part |
Token ID | 636 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
ramid | +0.237 |
axter | +0.225 |
itect | +0.225 |
eele | +0.224 |
hare | +0.218 |
Neg logit contributions | |
xit | -0.247 |
Uni | -0.245 |
ctors | -0.232 |
Honour | -0.216 |
culosis | -0.200 |
Token | of |
Token ID | 286 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
ramid | +1.929 |
itect | +1.849 |
axter | +1.845 |
eele | +1.836 |
hare | +1.799 |
Neg logit contributions | |
xit | -2.064 |
Uni | -2.023 |
ctors | -1.921 |
Honour | -1.797 |
culosis | -1.666 |
Token | him |
Token ID | 683 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
ramid | +0.936 |
itect | +0.897 |
axter | +0.892 |
eele | +0.885 |
hare | +0.867 |
Neg logit contributions | |
xit | -0.887 |
Uni | -0.882 |
ctors | -0.829 |
Honour | -0.774 |
culosis | -0.711 |
Token | as |
Token ID | 355 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
xit | +1.991 |
Uni | +1.966 |
ctors | +1.855 |
Honour | +1.723 |
culosis | +1.580 |
Neg logit contributions | |
ramid | -1.994 |
axter | -1.895 |
eele | -1.886 |
itect | -1.882 |
olyn | -1.822 |
Token | well |
Token ID | 880 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
ramid | +1.602 |
itect | +1.530 |
axter | +1.519 |
eele | +1.506 |
hare | +1.477 |
Neg logit contributions | |
xit | -1.579 |
Uni | -1.569 |
ctors | -1.473 |
Honour | -1.378 |
culosis | -1.265 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
xit | +1.607 |
Uni | +1.596 |
ctors | +1.517 |
Honour | +1.411 |
culosis | +1.295 |
Neg logit contributions | |
ramid | -1.525 |
axter | -1.440 |
itect | -1.430 |
eele | -1.426 |
hare | -1.392 |
Token | yes |
Token ID | 3763 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
Uni | +0.233 |
xit | +0.232 |
ctors | +0.218 |
Honour | +0.204 |
culosis | +0.185 |
Neg logit contributions | |
ramid | -0.253 |
itect | -0.242 |
eele | -0.241 |
axter | -0.240 |
hare | -0.234 |
Token | ? |
Token ID | 30 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
xit | +0.163 |
Uni | +0.160 |
ctors | +0.151 |
Honour | +0.141 |
culosis | +0.130 |
Neg logit contributions | |
ramid | -0.168 |
itect | -0.161 |
axter | -0.161 |
eele | -0.161 |
hare | -0.157 |
Token | election |
Token ID | 3071 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
ramid | +2.585 |
itect | +2.479 |
axter | +2.474 |
eele | +2.462 |
hare | +2.413 |
Neg logit contributions | |
xit | -2.801 |
Uni | -2.744 |
ctors | -2.607 |
Honour | -2.440 |
culosis | -2.266 |
Token | run |
Token ID | 1057 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ramid | +1.433 |
itect | +1.383 |
axter | +1.367 |
eele | +1.361 |
hare | +1.333 |
Neg logit contributions | |
xit | -1.525 |
Uni | -1.505 |
ctors | -1.412 |
Honour | -1.334 |
culosis | -1.208 |
Token | - |
Token ID | 12 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
xit | +2.579 |
Uni | +2.499 |
ctors | +2.355 |
Honour | +2.198 |
culosis | +2.018 |
Neg logit contributions | |
ramid | -2.731 |
itect | -2.630 |
axter | -2.625 |
eele | -2.599 |
hare | -2.537 |
Token | off |
Token ID | 2364 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
ramid | +1.097 |
itect | +1.058 |
axter | +1.056 |
eele | +1.052 |
hare | +1.033 |
Neg logit contributions | |
xit | -0.902 |
Uni | -0.880 |
ctors | -0.829 |
Honour | -0.768 |
culosis | -0.703 |
Token | between |
Token ID | 1022 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
ramid | +0.569 |
itect | +0.544 |
axter | +0.544 |
eele | +0.542 |
hare | +0.527 |
Neg logit contributions | |
xit | -0.608 |
Uni | -0.600 |
ctors | -0.561 |
Honour | -0.532 |
culosis | -0.482 |
Token | Gu |
Token ID | 1962 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
ramid | +0.045 |
itect | +0.043 |
axter | +0.043 |
eele | +0.043 |
hare | +0.042 |
Neg logit contributions | |
xit | -0.041 |
Uni | -0.041 |
ctors | -0.038 |
Honour | -0.036 |
culosis | -0.032 |
Token | iller |
Token ID | 4665 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
xit | +1.372 |
Uni | +1.324 |
ctors | +1.265 |
Honour | +1.171 |
culosis | +1.081 |
Neg logit contributions | |
ramid | -1.288 |
itect | -1.242 |
axter | -1.241 |
eele | -1.240 |
hare | -1.205 |
Token | mo |
Token ID | 5908 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
xit | +1.921 |
Uni | +1.879 |
ctors | +1.799 |
Honour | +1.690 |
culosis | +1.556 |
Neg logit contributions | |
ramid | -1.735 |
axter | -1.658 |
eele | -1.656 |
itect | -1.636 |
olyn | -1.596 |
Token | L |
Token ID | 406 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
ramid | +1.156 |
axter | +1.093 |
itect | +1.090 |
eele | +1.087 |
hare | +1.073 |
Neg logit contributions | |
xit | -1.182 |
Uni | -1.166 |
ctors | -1.089 |
Honour | -1.027 |
culosis | -0.923 |
Token | asso |
Token ID | 28372 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
ramid | +1.642 |
itect | +1.577 |
eele | +1.573 |
axter | +1.565 |
hare | +1.534 |
Neg logit contributions | |
xit | -1.917 |
Uni | -1.883 |
ctors | -1.773 |
Honour | -1.667 |
culosis | -1.514 |
Token | and |
Token ID | 290 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
xit | +0.089 |
Uni | +0.087 |
ctors | +0.081 |
Honour | +0.075 |
culosis | +0.068 |
Neg logit contributions | |
ramid | -0.107 |
axter | -0.102 |
itect | -0.102 |
eele | -0.102 |
hare | -0.100 |
Token | says |
Token ID | 1139 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ramid | +0.138 |
itect | +0.133 |
axter | +0.132 |
eele | +0.132 |
hare | +0.129 |
Neg logit contributions | |
xit | -0.107 |
Uni | -0.106 |
ctors | -0.098 |
Honour | -0.092 |
culosis | -0.083 |
Token | the |
Token ID | 262 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
xit | +0.236 |
Uni | +0.235 |
ctors | +0.218 |
Honour | +0.208 |
culosis | +0.188 |
Neg logit contributions | |
ramid | -0.247 |
itect | -0.234 |
axter | -0.234 |
eele | -0.233 |
hare | -0.229 |
Token | authority |
Token ID | 4934 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
ramid | +0.048 |
axter | +0.046 |
itect | +0.046 |
eele | +0.046 |
hare | +0.045 |
Neg logit contributions | |
xit | -0.049 |
Uni | -0.048 |
ctors | -0.045 |
Honour | -0.043 |
culosis | -0.039 |
Token | in |
Token ID | 287 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
xit | +0.051 |
Uni | +0.050 |
ctors | +0.047 |
Honour | +0.045 |
culosis | +0.041 |
Neg logit contributions | |
ramid | -0.043 |
axter | -0.041 |
itect | -0.041 |
eele | -0.041 |
hare | -0.040 |
Token | its |
Token ID | 663 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
xit | +0.645 |
Uni | +0.643 |
ctors | +0.592 |
Honour | +0.568 |
culosis | +0.499 |
Neg logit contributions | |
ramid | -0.765 |
itect | -0.729 |
axter | -0.727 |
eele | -0.721 |
hare | -0.709 |
Token | legal |
Token ID | 2742 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
ramid | +0.893 |
itect | +0.853 |
axter | +0.849 |
eele | +0.846 |
hare | +0.826 |
Neg logit contributions | |
xit | -1.062 |
Uni | -1.047 |
ctors | -0.989 |
Honour | -0.940 |
culosis | -0.864 |
Token | documents |
Token ID | 4963 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ramid | +1.436 |
itect | +1.370 |
axter | +1.367 |
eele | +1.360 |
hare | +1.328 |
Neg logit contributions | |
xit | -1.827 |
Uni | -1.794 |
ctors | -1.707 |
Honour | -1.612 |
culosis | -1.499 |
Token | . |
Token ID | 13 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
ramid | +0.540 |
itect | +0.515 |
axter | +0.514 |
eele | +0.511 |
hare | +0.498 |
Neg logit contributions | |
xit | -0.647 |
Uni | -0.636 |
ctors | -0.604 |
Honour | -0.569 |
culosis | -0.528 |
Token | But |
Token ID | 887 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
xit | +0.458 |
Uni | +0.455 |
ctors | +0.423 |
Honour | +0.401 |
culosis | +0.356 |
Neg logit contributions | |
ramid | -0.529 |
axter | -0.510 |
eele | -0.500 |
itect | -0.498 |
hare | -0.490 |
Token | all |
Token ID | 477 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
ramid | +2.116 |
itect | +2.030 |
axter | +2.027 |
eele | +2.017 |
hare | +1.978 |
Neg logit contributions | |
xit | -2.078 |
Uni | -2.037 |
ctors | -1.926 |
Honour | -1.800 |
culosis | -1.658 |
Token | walked |
Token ID | 6807 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
ramid | +2.116 |
itect | +2.031 |
axter | +2.028 |
eele | +2.021 |
hare | +1.980 |
Neg logit contributions | |
xit | -2.127 |
Uni | -2.085 |
ctors | -1.974 |
Honour | -1.846 |
culosis | -1.704 |
Token | � |
Token ID | 447 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
ramid | +0.104 |
itect | +0.099 |
axter | +0.099 |
eele | +0.099 |
hare | +0.096 |
Neg logit contributions | |
xit | -0.108 |
Uni | -0.106 |
ctors | -0.100 |
Honour | -0.093 |
culosis | -0.086 |
Token | � |
Token ID | 247 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
xit | +1.720 |
Uni | +1.687 |
ctors | +1.597 |
Honour | +1.511 |
nces | +1.385 |
Neg logit contributions | |
ramid | -1.573 |
eele | -1.486 |
axter | -1.485 |
itect | -1.482 |
olyn | -1.446 |
Token | s |
Token ID | 82 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
xit | +0.994 |
Uni | +0.976 |
ctors | +0.931 |
Honour | +0.874 |
culosis | +0.815 |
Neg logit contributions | |
ramid | -0.814 |
itect | -0.766 |
axter | -0.764 |
eele | -0.763 |
hare | -0.741 |
Token | a |
Token ID | 257 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
xit | +1.293 |
Uni | +1.274 |
ctors | +1.193 |
Honour | +1.112 |
nces | +1.002 |
Neg logit contributions | |
ramid | -1.504 |
axter | -1.438 |
itect | -1.437 |
eele | -1.427 |
olyn | -1.392 |
Token | lot |
Token ID | 1256 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
xit | +1.325 |
Uni | +1.319 |
ctors | +1.254 |
Honour | +1.167 |
culosis | +1.063 |
Neg logit contributions | |
ramid | -1.244 |
axter | -1.198 |
itect | -1.186 |
eele | -1.185 |
hare | -1.143 |
Token | of |
Token ID | 286 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
xit | +0.866 |
Uni | +0.851 |
ctors | +0.797 |
Honour | +0.739 |
culosis | +0.671 |
Neg logit contributions | |
ramid | -1.017 |
axter | -0.974 |
itect | -0.972 |
eele | -0.971 |
hare | -0.949 |
Token | anger |
Token ID | 8993 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
Uni | +0.271 |
xit | +0.270 |
ctors | +0.250 |
Honour | +0.239 |
culosis | +0.211 |
Neg logit contributions | |
ramid | -0.300 |
itect | -0.288 |
axter | -0.286 |
eele | -0.283 |
olyn | -0.277 |
Token | , |
Token ID | 11 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ramid | +0.807 |
eele | +0.773 |
axter | +0.771 |
itect | +0.771 |
hare | +0.751 |
Neg logit contributions | |
xit | -0.722 |
Uni | -0.711 |
ctors | -0.667 |
Honour | -0.619 |
culosis | -0.569 |
Token | there |
Token ID | 612 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
xit | +0.694 |
Uni | +0.692 |
ctors | +0.642 |
Honour | +0.608 |
culosis | +0.542 |
Neg logit contributions | |
ramid | -0.794 |
itect | -0.759 |
eele | -0.757 |
axter | -0.755 |
hare | -0.735 |
Token | � |
Token ID | 447 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
xit | +0.762 |
Uni | +0.749 |
ctors | +0.718 |
Honour | +0.672 |
culosis | +0.630 |
Neg logit contributions | |
ramid | -0.564 |
itect | -0.534 |
axter | -0.534 |
eele | -0.533 |
hare | -0.519 |
Token | � |
Token ID | 247 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
xit | +1.782 |
Uni | +1.743 |
ctors | +1.660 |
Honour | +1.553 |
nces | +1.446 |
Neg logit contributions | |
ramid | -1.600 |
eele | -1.534 |
itect | -1.526 |
axter | -1.522 |
hare | -1.484 |
Token | sort |
Token ID | 3297 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ramid | +0.437 |
itect | +0.416 |
axter | +0.412 |
eele | +0.410 |
hare | +0.399 |
Neg logit contributions | |
xit | -0.434 |
Uni | -0.430 |
ctors | -0.403 |
Honour | -0.378 |
culosis | -0.345 |
Token | of |
Token ID | 286 |
Feature activation | +4.21e-03 |
Pos logit contributions | |
xit | +1.994 |
Uni | +1.924 |
ctors | +1.821 |
Honour | +1.677 |
culosis | +1.485 |
Neg logit contributions | |
ramid | -2.661 |
axter | -2.583 |
eele | -2.549 |
itect | -2.517 |
olyn | -2.472 |
Token | outside |
Token ID | 2354 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
xit | +0.009 |
Uni | +0.009 |
ctors | +0.009 |
Honour | +0.008 |
culosis | +0.007 |
Neg logit contributions | |
ramid | -0.009 |
itect | -0.009 |
axter | -0.009 |
eele | -0.009 |
hare | -0.009 |
Token | spending |
Token ID | 4581 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
xit | +0.079 |
Uni | +0.079 |
ctors | +0.073 |
Honour | +0.069 |
culosis | +0.063 |
Neg logit contributions | |
ramid | -0.077 |
axter | -0.074 |
eele | -0.073 |
itect | -0.073 |
hare | -0.071 |
Token | can |
Token ID | 460 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
ramid | +0.225 |
axter | +0.217 |
eele | +0.215 |
itect | +0.215 |
hare | +0.209 |
Neg logit contributions | |
xit | -0.204 |
Uni | -0.201 |
ctors | -0.189 |
Honour | -0.175 |
culosis | -0.161 |
Token | convince |
Token ID | 11508 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
ramid | +0.887 |
axter | +0.853 |
itect | +0.847 |
eele | +0.846 |
hare | +0.822 |
Neg logit contributions | |
xit | -0.919 |
Uni | -0.899 |
ctors | -0.860 |
Honour | -0.796 |
culosis | -0.739 |
Token | New |
Token ID | 968 |
Feature activation | -8.45e-03 |
Pos logit contributions | |
ramid | +0.442 |
itect | +0.422 |
axter | +0.420 |
eele | +0.418 |
hare | +0.408 |
Neg logit contributions | |
xit | -0.437 |
Uni | -0.431 |
ctors | -0.405 |
Honour | -0.378 |
culosis | -0.347 |
Token | Jersey |
Token ID | 8221 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ramid | +0.016 |
axter | +0.016 |
itect | +0.016 |
eele | +0.016 |
hare | +0.015 |
Neg logit contributions | |
xit | -0.021 |
Uni | -0.021 |
ctors | -0.020 |
Honour | -0.018 |
culosis | -0.017 |
Token | voters |
Token ID | 4446 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
ramid | +2.899 |
itect | +2.777 |
axter | +2.758 |
eele | +2.745 |
hare | +2.684 |
Neg logit contributions | |
xit | -3.988 |
Uni | -3.906 |
ctors | -3.734 |
Honour | -3.522 |
culosis | -3.302 |
Token | that |
Token ID | 326 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
ramid | +0.896 |
axter | +0.855 |
itect | +0.853 |
eele | +0.848 |
hare | +0.820 |
Neg logit contributions | |
xit | -0.883 |
Uni | -0.868 |
ctors | -0.816 |
Honour | -0.762 |
culosis | -0.702 |
Token | Booker |
Token ID | 31004 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
xit | +1.111 |
Uni | +1.104 |
ctors | +1.021 |
Honour | +0.955 |
culosis | +0.873 |
Neg logit contributions | |
ramid | -1.195 |
itect | -1.125 |
axter | -1.122 |
eele | -1.108 |
hare | -1.084 |
Token | fire |
Token ID | 2046 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
Uni | +0.861 |
xit | +0.859 |
ctors | +0.795 |
Honour | +0.756 |
culosis | +0.689 |
Neg logit contributions | |
ramid | -0.852 |
axter | -0.827 |
eele | -0.809 |
itect | -0.790 |
hare | -0.783 |
Token | for |
Token ID | 329 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
ramid | +1.435 |
axter | +1.382 |
eele | +1.376 |
itect | +1.370 |
hare | +1.338 |
Neg logit contributions | |
xit | -1.560 |
Uni | -1.535 |
ctors | -1.451 |
Honour | -1.357 |
culosis | -1.263 |
Token | Fox |
Token ID | 5426 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
Uni | +1.162 |
xit | +1.154 |
ctors | +1.077 |
Honour | +1.015 |
culosis | +0.917 |
Neg logit contributions | |
ramid | -1.274 |
axter | -1.226 |
itect | -1.214 |
eele | -1.205 |
hare | -1.189 |
Token | News |
Token ID | 3000 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
xit | +0.847 |
Uni | +0.835 |
ctors | +0.769 |
Honour | +0.696 |
culosis | +0.623 |
Neg logit contributions | |
ramid | -1.371 |
axter | -1.342 |
itect | -1.321 |
eele | -1.320 |
hare | -1.292 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Uni | +1.795 |
xit | +1.791 |
ctors | +1.670 |
Honour | +1.568 |
culosis | +1.436 |
Neg logit contributions | |
ramid | -1.785 |
axter | -1.738 |
eele | -1.685 |
itect | -1.684 |
azo | -1.653 |
Token | The |
Token ID | 383 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
xit | +0.225 |
Uni | +0.224 |
ctors | +0.209 |
Honour | +0.198 |
culosis | +0.176 |
Neg logit contributions | |
ramid | -0.259 |
axter | -0.250 |
eele | -0.247 |
itect | -0.246 |
hare | -0.241 |
Token | First |
Token ID | 3274 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
xit | +0.279 |
Uni | +0.277 |
ctors | +0.260 |
Honour | +0.244 |
culosis | +0.222 |
Neg logit contributions | |
ramid | -0.286 |
axter | -0.275 |
eele | -0.273 |
itect | -0.273 |
hare | -0.267 |
Token | Family |
Token ID | 7884 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
xit | +0.812 |
Uni | +0.796 |
ctors | +0.748 |
Honour | +0.696 |
culosis | +0.620 |
Neg logit contributions | |
ramid | -1.038 |
axter | -1.000 |
itect | -0.997 |
eele | -0.995 |
hare | -0.978 |
Token | would |
Token ID | 561 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
xit | +2.542 |
Uni | +2.516 |
ctors | +2.356 |
Honour | +2.207 |
culosis | +1.970 |
Neg logit contributions | |
ramid | -2.965 |
axter | -2.859 |
eele | -2.813 |
itect | -2.794 |
ippi | -2.734 |
Token | have |
Token ID | 423 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
xit | +1.053 |
Uni | +1.029 |
ctors | +0.990 |
Honour | +0.922 |
culosis | +0.842 |
Neg logit contributions | |
ramid | -1.018 |
axter | -0.982 |
eele | -0.982 |
itect | -0.970 |
hare | -0.945 |
Token | been |
Token ID | 587 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
ramid | +1.329 |
itect | +1.273 |
axter | +1.273 |
eele | +1.269 |
hare | +1.237 |
Neg logit contributions | |
xit | -1.441 |
Uni | -1.414 |
ctors | -1.342 |
Honour | -1.258 |
culosis | -1.162 |
Token | other |
Token ID | 584 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
xit | +0.125 |
Uni | +0.125 |
ctors | +0.116 |
Honour | +0.109 |
culosis | +0.098 |
Neg logit contributions | |
ramid | -0.135 |
itect | -0.130 |
axter | -0.130 |
eele | -0.130 |
hare | -0.126 |
Token | , |
Token ID | 11 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
ramid | +1.001 |
itect | +0.963 |
axter | +0.959 |
eele | +0.956 |
hare | +0.934 |
Neg logit contributions | |
xit | -0.957 |
Uni | -0.946 |
ctors | -0.888 |
Honour | -0.831 |
culosis | -0.760 |
Token | the |
Token ID | 262 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
ramid | +1.471 |
itect | +1.415 |
axter | +1.412 |
eele | +1.404 |
hare | +1.382 |
Neg logit contributions | |
xit | -1.352 |
Uni | -1.318 |
ctors | -1.251 |
Honour | -1.161 |
culosis | -1.073 |
Token | Christian |
Token ID | 4302 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
ramid | +1.138 |
itect | +1.096 |
axter | +1.094 |
eele | +1.092 |
hare | +1.069 |
Neg logit contributions | |
xit | -0.984 |
Uni | -0.967 |
ctors | -0.907 |
Honour | -0.844 |
culosis | -0.769 |
Token | Cong |
Token ID | 2908 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ramid | +1.526 |
itect | +1.470 |
axter | +1.468 |
eele | +1.463 |
hare | +1.435 |
Neg logit contributions | |
xit | -1.288 |
Uni | -1.261 |
ctors | -1.186 |
Honour | -1.100 |
culosis | -1.006 |
Token | regation |
Token ID | 43068 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
xit | +1.577 |
Uni | +1.526 |
ctors | +1.390 |
Honour | +1.196 |
culosis | +1.051 |
Neg logit contributions | |
ramid | -3.183 |
itect | -3.113 |
eele | -3.108 |
axter | -3.093 |
hare | -3.051 |
Token | of |
Token ID | 286 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
ramid | +0.665 |
axter | +0.638 |
itect | +0.637 |
eele | +0.636 |
hare | +0.622 |
Neg logit contributions | |
xit | -0.623 |
Uni | -0.612 |
ctors | -0.577 |
Honour | -0.538 |
culosis | -0.494 |
Token | Brazil |
Token ID | 7595 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
ramid | +1.492 |
itect | +1.434 |
axter | +1.431 |
eele | +1.425 |
hare | +1.398 |
Neg logit contributions | |
xit | -1.441 |
Uni | -1.411 |
ctors | -1.335 |
Honour | -1.245 |
culosis | -1.148 |
Token | , |
Token ID | 11 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
ramid | +0.971 |
axter | +0.929 |
itect | +0.928 |
eele | +0.925 |
hare | +0.905 |
Neg logit contributions | |
xit | -1.057 |
Uni | -1.041 |
ctors | -0.986 |
Honour | -0.924 |
culosis | -0.854 |
Token | was |
Token ID | 373 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
ramid | +0.618 |
itect | +0.593 |
axter | +0.593 |
eele | +0.591 |
hare | +0.578 |
Neg logit contributions | |
xit | -0.585 |
Uni | -0.576 |
ctors | -0.544 |
Honour | -0.507 |
culosis | -0.466 |
Token | founded |
Token ID | 9393 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
ramid | +1.853 |
itect | +1.790 |
axter | +1.788 |
eele | +1.781 |
hare | +1.752 |
Neg logit contributions | |
xit | -1.283 |
Uni | -1.251 |
ctors | -1.171 |
Honour | -1.074 |
culosis | -0.971 |
Token | E |
Token ID | 412 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ramid | +2.402 |
itect | +2.313 |
axter | +2.302 |
eele | +2.297 |
hare | +2.257 |
Neg logit contributions | |
xit | -2.516 |
Uni | -2.451 |
ctors | -2.336 |
Honour | -2.172 |
culosis | -2.032 |
Token | . |
Token ID | 13 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
ramid | +2.105 |
eele | +1.987 |
itect | +1.982 |
axter | +1.980 |
hare | +1.936 |
Neg logit contributions | |
xit | -2.905 |
Uni | -2.856 |
ctors | -2.703 |
Honour | -2.567 |
culosis | -2.422 |
Token | V |
Token ID | 569 |
Feature activation | -7.48e-02 |
Pos logit contributions | |
ramid | +1.801 |
axter | +1.725 |
itect | +1.725 |
eele | +1.713 |
hare | +1.677 |
Neg logit contributions | |
xit | -1.817 |
Uni | -1.785 |
ctors | -1.689 |
Honour | -1.582 |
culosis | -1.454 |
Token | ., |
Token ID | 1539 |
Feature activation | -6.15e-03 |
Pos logit contributions | |
ramid | +0.145 |
itect | +0.139 |
axter | +0.138 |
eele | +0.138 |
hare | +0.135 |
Neg logit contributions | |
xit | -0.186 |
Uni | -0.182 |
ctors | -0.173 |
Honour | -0.163 |
culosis | -0.153 |
Token | Harris |
Token ID | 10026 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
ramid | +0.014 |
axter | +0.014 |
itect | +0.014 |
eele | +0.014 |
hare | +0.013 |
Neg logit contributions | |
xit | -0.013 |
Uni | -0.013 |
ctors | -0.012 |
Honour | -0.011 |
culosis | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ramid | +1.653 |
itect | +1.597 |
eele | +1.587 |
axter | +1.582 |
hare | +1.548 |
Neg logit contributions | |
xit | -2.075 |
Uni | -2.021 |
ctors | -1.936 |
Honour | -1.826 |
culosis | -1.702 |
Token | D |
Token ID | 360 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
ramid | +2.897 |
itect | +2.802 |
eele | +2.780 |
axter | +2.779 |
hare | +2.741 |
Neg logit contributions | |
xit | -3.137 |
Uni | -3.039 |
ctors | -2.916 |
Honour | -2.697 |
culosis | -2.555 |
Token | . |
Token ID | 13 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
ramid | +1.549 |
axter | +1.478 |
itect | +1.475 |
eele | +1.473 |
hare | +1.432 |
Neg logit contributions | |
xit | -2.160 |
Uni | -2.112 |
ctors | -2.014 |
Honour | -1.905 |
culosis | -1.797 |
Token | B |
Token ID | 347 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
ramid | +2.040 |
itect | +1.956 |
axter | +1.954 |
eele | +1.944 |
hare | +1.905 |
Neg logit contributions | |
xit | -2.042 |
Uni | -2.003 |
ctors | -1.896 |
Honour | -1.773 |
culosis | -1.634 |
Token | ., |
Token ID | 1539 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
ramid | +0.448 |
itect | +0.426 |
axter | +0.426 |
eele | +0.424 |
hare | +0.414 |
Neg logit contributions | |
xit | -0.581 |
Uni | -0.570 |
ctors | -0.543 |
Honour | -0.512 |
culosis | -0.479 |
Token | Herz |
Token ID | 34321 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
ramid | +0.836 |
itect | +0.802 |
axter | +0.801 |
eele | +0.796 |
hare | +0.782 |
Neg logit contributions | |
xit | -0.755 |
Uni | -0.743 |
ctors | -0.698 |
Honour | -0.652 |
culosis | -0.595 |
Token | they |
Token ID | 484 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
xit | +0.227 |
Uni | +0.223 |
ctors | +0.211 |
Honour | +0.198 |
culosis | +0.179 |
Neg logit contributions | |
ramid | -0.244 |
itect | -0.234 |
axter | -0.233 |
eele | -0.232 |
hare | -0.226 |
Token | may |
Token ID | 743 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ramid | +1.001 |
itect | +0.961 |
axter | +0.961 |
eele | +0.959 |
hare | +0.927 |
Neg logit contributions | |
xit | -1.107 |
Uni | -1.087 |
ctors | -1.038 |
Honour | -0.976 |
culosis | -0.900 |
Token | have |
Token ID | 423 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
xit | +0.893 |
Uni | +0.875 |
ctors | +0.846 |
Honour | +0.795 |
culosis | +0.726 |
Neg logit contributions | |
ramid | -0.851 |
eele | -0.818 |
axter | -0.817 |
itect | -0.817 |
olyn | -0.790 |
Token | been |
Token ID | 587 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
ramid | +1.191 |
itect | +1.139 |
axter | +1.134 |
eele | +1.131 |
hare | +1.096 |
Neg logit contributions | |
xit | -1.592 |
Uni | -1.568 |
ctors | -1.496 |
Honour | -1.416 |
culosis | -1.316 |
Token | carried |
Token ID | 5281 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ramid | +0.546 |
itect | +0.525 |
axter | +0.522 |
eele | +0.522 |
hare | +0.508 |
Neg logit contributions | |
xit | -0.551 |
Uni | -0.542 |
ctors | -0.512 |
Honour | -0.480 |
culosis | -0.440 |
Token | out |
Token ID | 503 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ramid | +0.455 |
itect | +0.438 |
axter | +0.437 |
eele | +0.435 |
hare | +0.427 |
Neg logit contributions | |
xit | -0.375 |
Uni | -0.366 |
ctors | -0.344 |
Honour | -0.320 |
culosis | -0.292 |
Token | to |
Token ID | 284 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
ramid | +3.791 |
axter | +3.645 |
itect | +3.643 |
hare | +3.610 |
eele | +3.608 |
Neg logit contributions | |
xit | -4.266 |
Uni | -4.142 |
ctors | -3.965 |
Honour | -3.667 |
culosis | -3.465 |
Token | qu |
Token ID | 627 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
ramid | +0.929 |
axter | +0.894 |
itect | +0.892 |
eele | +0.886 |
hare | +0.864 |
Neg logit contributions | |
xit | -0.953 |
Uni | -0.940 |
ctors | -0.895 |
Honour | -0.842 |
culosis | -0.770 |
Token | ell |
Token ID | 695 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ramid | +0.526 |
itect | +0.497 |
axter | +0.497 |
eele | +0.492 |
hare | +0.480 |
Neg logit contributions | |
xit | -0.816 |
Uni | -0.803 |
ctors | -0.767 |
Honour | -0.727 |
culosis | -0.682 |
Token | unrest |
Token ID | 17093 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
xit | +2.482 |
Uni | +2.463 |
ctors | +2.272 |
Honour | +2.146 |
culosis | +1.933 |
Neg logit contributions | |
ramid | -2.677 |
itect | -2.541 |
axter | -2.541 |
eele | -2.533 |
hare | -2.436 |
Token | and |
Token ID | 290 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
ramid | +0.811 |
axter | +0.779 |
itect | +0.776 |
eele | +0.775 |
hare | +0.754 |
Neg logit contributions | |
xit | -0.797 |
Uni | -0.782 |
ctors | -0.739 |
Honour | -0.689 |
culosis | -0.636 |
Token | Will |
Token ID | 2561 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Uni | +0.633 |
xit | +0.632 |
ctors | +0.588 |
Honour | +0.558 |
culosis | +0.494 |
Neg logit contributions | |
ramid | -0.728 |
axter | -0.700 |
itect | -0.689 |
eele | -0.688 |
hare | -0.676 |
Token | Black |
Token ID | 2619 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
xit | +0.920 |
Uni | +0.908 |
ctors | +0.850 |
Honour | +0.805 |
culosis | +0.727 |
Neg logit contributions | |
ramid | -0.931 |
axter | -0.882 |
eele | -0.879 |
itect | -0.878 |
hare | -0.860 |
Token | mon |
Token ID | 2144 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ramid | +1.816 |
axter | +1.733 |
eele | +1.728 |
itect | +1.728 |
hare | +1.680 |
Neg logit contributions | |
xit | -2.451 |
Uni | -2.412 |
ctors | -2.299 |
Honour | -2.170 |
culosis | -2.015 |
Token | is |
Token ID | 318 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ramid | +2.440 |
itect | +2.340 |
axter | +2.337 |
eele | +2.325 |
hare | +2.280 |
Neg logit contributions | |
xit | -2.523 |
Uni | -2.472 |
ctors | -2.345 |
Honour | -2.191 |
culosis | -2.029 |
Token | learning |
Token ID | 4673 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
ramid | +0.467 |
itect | +0.445 |
eele | +0.444 |
axter | +0.443 |
hare | +0.430 |
Neg logit contributions | |
xit | -0.425 |
Uni | -0.420 |
ctors | -0.393 |
Honour | -0.368 |
culosis | -0.334 |
Token | safety |
Token ID | 3747 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
ramid | +0.181 |
itect | +0.172 |
axter | +0.171 |
eele | +0.171 |
hare | +0.167 |
Neg logit contributions | |
xit | -0.173 |
Uni | -0.172 |
ctors | -0.161 |
Honour | -0.152 |
culosis | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
ramid | +4.346 |
itect | +4.216 |
axter | +4.215 |
eele | +4.165 |
hare | +4.111 |
Neg logit contributions | |
xit | -4.651 |
Uni | -4.490 |
ctors | -4.299 |
Honour | -4.015 |
culosis | -3.741 |
Token | and |
Token ID | 290 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
Uni | +1.249 |
xit | +1.238 |
ctors | +1.151 |
Honour | +1.069 |
culosis | +0.950 |
Neg logit contributions | |
ramid | -1.671 |
itect | -1.598 |
eele | -1.592 |
axter | -1.581 |
hare | -1.560 |
Token | is |
Token ID | 318 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Uni | +0.843 |
xit | +0.834 |
ctors | +0.775 |
Honour | +0.733 |
culosis | +0.651 |
Neg logit contributions | |
ramid | -0.917 |
itect | -0.870 |
axter | -0.859 |
eele | -0.857 |
hare | -0.843 |
Token | noticeably |
Token ID | 33752 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
ramid | +0.662 |
itect | +0.630 |
eele | +0.628 |
axter | +0.627 |
hare | +0.609 |
Neg logit contributions | |
xit | -0.612 |
Uni | -0.608 |
ctors | -0.568 |
Honour | -0.531 |
culosis | -0.482 |
Token | bigger |
Token ID | 5749 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
xit | +0.911 |
Uni | +0.911 |
ctors | +0.843 |
Honour | +0.798 |
culosis | +0.715 |
Neg logit contributions | |
ramid | -1.100 |
itect | -1.045 |
axter | -1.037 |
eele | -1.032 |
olyn | -1.011 |
Token | what |
Token ID | 644 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
ramid | +0.029 |
axter | +0.028 |
itect | +0.028 |
eele | +0.028 |
olyn | +0.027 |
Neg logit contributions | |
xit | -0.029 |
Uni | -0.029 |
ctors | -0.027 |
Honour | -0.025 |
culosis | -0.023 |
Token | investors |
Token ID | 7713 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
xit | +1.782 |
Uni | +1.777 |
ctors | +1.659 |
Honour | +1.531 |
culosis | +1.391 |
Neg logit contributions | |
ramid | -1.847 |
eele | -1.759 |
itect | -1.750 |
axter | -1.743 |
hare | -1.717 |
Token | will |
Token ID | 481 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
ramid | +1.954 |
itect | +1.870 |
axter | +1.864 |
eele | +1.853 |
hare | +1.817 |
Neg logit contributions | |
xit | -2.407 |
Uni | -2.359 |
ctors | -2.248 |
Honour | -2.112 |
culosis | -1.972 |
Token | continue |
Token ID | 2555 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
xit | +0.773 |
Uni | +0.762 |
ctors | +0.732 |
Honour | +0.675 |
culosis | +0.616 |
Neg logit contributions | |
ramid | -0.788 |
eele | -0.756 |
axter | -0.753 |
itect | -0.748 |
olyn | -0.735 |
Token | to |
Token ID | 284 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
xit | +0.881 |
Uni | +0.866 |
ctors | +0.819 |
Honour | +0.766 |
culosis | +0.709 |
Neg logit contributions | |
ramid | -0.828 |
itect | -0.794 |
axter | -0.793 |
eele | -0.789 |
hare | -0.773 |
Token | watch |
Token ID | 2342 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ramid | +0.123 |
eele | +0.118 |
axter | +0.118 |
itect | +0.118 |
olyn | +0.115 |
Neg logit contributions | |
xit | -0.117 |
Uni | -0.116 |
ctors | -0.110 |
Honour | -0.102 |
culosis | -0.093 |
Token | , |
Token ID | 11 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
ramid | +3.000 |
itect | +2.886 |
axter | +2.875 |
eele | +2.852 |
hare | +2.811 |
Neg logit contributions | |
xit | -3.535 |
Uni | -3.461 |
ctors | -3.301 |
Honour | -3.094 |
culosis | -2.896 |
Token | primarily |
Token ID | 7525 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
ramid | +0.194 |
itect | +0.186 |
eele | +0.184 |
axter | +0.184 |
hare | +0.180 |
Neg logit contributions | |
xit | -0.215 |
Uni | -0.213 |
ctors | -0.200 |
Honour | -0.188 |
culosis | -0.173 |
Token | due |
Token ID | 2233 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
xit | +1.013 |
Uni | +1.003 |
ctors | +0.933 |
Honour | +0.874 |
culosis | +0.794 |
Neg logit contributions | |
ramid | -1.030 |
itect | -0.985 |
eele | -0.978 |
axter | -0.977 |
olyn | -0.951 |
Token | to |
Token ID | 284 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
ramid | +1.721 |
itect | +1.654 |
eele | +1.650 |
axter | +1.649 |
hare | +1.609 |
Neg logit contributions | |
xit | -2.066 |
Uni | -2.018 |
ctors | -1.931 |
Honour | -1.810 |
culosis | -1.691 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e-03 |
Pos logit contributions | |
ramid | +0.602 |
itect | +0.577 |
axter | +0.575 |
eele | +0.573 |
hare | +0.560 |
Neg logit contributions | |
xit | -0.556 |
Uni | -0.548 |
ctors | -0.512 |
Honour | -0.479 |
culosis | -0.437 |
Token | t |
Token ID | 83 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
xit | +1.534 |
Uni | +1.526 |
ctors | +1.417 |
Honour | +1.334 |
nces | +1.209 |
Neg logit contributions | |
ramid | -1.600 |
axter | -1.526 |
itect | -1.508 |
eele | -1.495 |
ippi | -1.472 |
Token | as |
Token ID | 292 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
ramid | +1.711 |
axter | +1.638 |
itect | +1.628 |
eele | +1.627 |
hare | +1.611 |
Neg logit contributions | |
xit | -1.284 |
Uni | -1.270 |
ctors | -1.187 |
Honour | -1.087 |
culosis | -0.987 |
Token | or |
Token ID | 393 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
ramid | +1.613 |
axter | +1.538 |
itect | +1.537 |
eele | +1.527 |
hare | +1.495 |
Neg logit contributions | |
xit | -1.868 |
Uni | -1.835 |
ctors | -1.744 |
Honour | -1.638 |
culosis | -1.519 |
Token | even |
Token ID | 772 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
ramid | +1.532 |
itect | +1.469 |
axter | +1.469 |
eele | +1.461 |
hare | +1.433 |
Neg logit contributions | |
xit | -1.337 |
Uni | -1.319 |
ctors | -1.236 |
Honour | -1.152 |
culosis | -1.047 |
Token | the |
Token ID | 262 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
ramid | +0.849 |
axter | +0.811 |
itect | +0.811 |
eele | +0.806 |
hare | +0.789 |
Neg logit contributions | |
xit | -0.745 |
Uni | -0.742 |
ctors | -0.690 |
Honour | -0.647 |
culosis | -0.583 |
Token | middle |
Token ID | 3504 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ramid | +0.145 |
itect | +0.140 |
axter | +0.139 |
eele | +0.139 |
hare | +0.136 |
Neg logit contributions | |
xit | -0.127 |
Uni | -0.126 |
ctors | -0.117 |
Honour | -0.110 |
culosis | -0.099 |
Token | of |
Token ID | 286 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
ramid | +4.379 |
itect | +4.224 |
eele | +4.217 |
axter | +4.202 |
hare | +4.142 |
Neg logit contributions | |
xit | -4.320 |
Uni | -4.179 |
ctors | -3.982 |
Honour | -3.681 |
culosis | -3.479 |
Token | the |
Token ID | 262 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Uni | +1.088 |
xit | +1.086 |
ctors | +1.005 |
Honour | +0.947 |
CV | +0.832 |
Neg logit contributions | |
ramid | -1.245 |
axter | -1.198 |
itect | -1.186 |
eele | -1.178 |
hare | -1.149 |
Token | road |
Token ID | 2975 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Uni | +0.689 |
xit | +0.689 |
ctors | +0.641 |
Honour | +0.603 |
culosis | +0.541 |
Neg logit contributions | |
ramid | -0.725 |
itect | -0.702 |
axter | -0.700 |
eele | -0.693 |
hare | -0.674 |
Token | clubs |
Token ID | 9784 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Uni | +0.987 |
xit | +0.981 |
ctors | +0.917 |
Honour | +0.870 |
culosis | +0.775 |
Neg logit contributions | |
ramid | -1.010 |
axter | -0.964 |
itect | -0.958 |
eele | -0.954 |
hare | -0.927 |
Token | like |
Token ID | 588 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ramid | +0.363 |
axter | +0.348 |
eele | +0.345 |
itect | +0.345 |
olyn | +0.334 |
Neg logit contributions | |
xit | -0.364 |
Uni | -0.362 |
ctors | -0.339 |
Honour | -0.318 |
culosis | -0.289 |