Token | - |
Token ID | 12 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
� | +0.704 |
Rudolph | +0.699 |
steen | +0.673 |
之 | +0.672 |
ahime | +0.651 |
Neg logit contributions | |
xual | -0.566 |
honour | -0.565 |
rogens | -0.519 |
icle | -0.519 |
stealth | -0.492 |
Token | known |
Token ID | 4002 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
� | +0.216 |
Rudolph | +0.215 |
steen | +0.208 |
之 | +0.208 |
ahime | +0.202 |
Neg logit contributions | |
xual | -0.127 |
honour | -0.127 |
rogens | -0.115 |
icle | -0.115 |
stealth | -0.107 |
Token | type |
Token ID | 2099 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
honour | +0.710 |
xual | +0.703 |
icle | +0.657 |
rogens | +0.654 |
stealth | +0.626 |
Neg logit contributions | |
� | -0.759 |
Rudolph | -0.749 |
steen | -0.724 |
之 | -0.723 |
ahime | -0.701 |
Token | of |
Token ID | 286 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
honour | +0.917 |
xual | +0.911 |
icle | +0.859 |
rogens | +0.840 |
stealth | +0.808 |
Neg logit contributions | |
� | -0.950 |
Rudolph | -0.940 |
之 | -0.907 |
steen | -0.905 |
ahime | -0.878 |
Token | ign |
Token ID | 3627 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
honour | +0.107 |
xual | +0.107 |
icle | +0.099 |
rogens | +0.099 |
stealth | +0.095 |
Neg logit contributions | |
� | -0.108 |
Rudolph | -0.107 |
之 | -0.103 |
steen | -0.103 |
ahime | -0.100 |
Token | eous |
Token ID | 15303 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
honour | +0.655 |
xual | +0.650 |
icle | +0.581 |
rogens | +0.566 |
stealth | +0.500 |
Neg logit contributions | |
� | -1.979 |
Rudolph | -1.967 |
之 | -1.911 |
steen | -1.906 |
ahime | -1.863 |
Token | rock |
Token ID | 3881 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
honour | +4.123 |
xual | +3.916 |
icle | +3.882 |
rogens | +3.734 |
stealth | +3.609 |
Neg logit contributions | |
� | -4.483 |
Rudolph | -4.381 |
之 | -4.301 |
steen | -4.231 |
ahime | -4.220 |
Token | found |
Token ID | 1043 |
Feature activation | +6.38e-03 |
Pos logit contributions | |
honour | +0.841 |
xual | +0.832 |
icle | +0.779 |
rogens | +0.773 |
stealth | +0.741 |
Neg logit contributions | |
� | -0.881 |
Rudolph | -0.863 |
steen | -0.834 |
之 | -0.834 |
ahime | -0.809 |
Token | in |
Token ID | 287 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
honour | +0.004 |
xual | +0.004 |
rogens | +0.004 |
icle | +0.004 |
stealth | +0.004 |
Neg logit contributions | |
� | -0.005 |
Rudolph | -0.005 |
steen | -0.005 |
之 | -0.005 |
ahime | -0.005 |
Token | many |
Token ID | 867 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
honour | +0.103 |
xual | +0.103 |
rogens | +0.096 |
icle | +0.095 |
stealth | +0.091 |
Neg logit contributions | |
� | -0.103 |
Rudolph | -0.102 |
steen | -0.099 |
之 | -0.098 |
ahime | -0.095 |
Token | volcanic |
Token ID | 31513 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
honour | +0.624 |
xual | +0.614 |
rogens | +0.575 |
icle | +0.574 |
stealth | +0.548 |
Neg logit contributions | |
� | -0.699 |
Rudolph | -0.690 |
steen | -0.671 |
之 | -0.667 |
ahime | -0.650 |
Token | heads |
Token ID | 6665 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
� | +0.019 |
Rudolph | +0.019 |
steen | +0.018 |
之 | +0.018 |
ahime | +0.017 |
Neg logit contributions | |
honour | -0.016 |
xual | -0.016 |
rogens | -0.015 |
icle | -0.015 |
stealth | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
honour | +1.601 |
xual | +1.584 |
icle | +1.493 |
rogens | +1.478 |
stealth | +1.403 |
Neg logit contributions | |
� | -1.697 |
Rudolph | -1.678 |
之 | -1.617 |
steen | -1.608 |
ahime | -1.569 |
Token | the |
Token ID | 262 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
honour | +0.011 |
xual | +0.011 |
rogens | +0.010 |
icle | +0.010 |
stealth | +0.009 |
Neg logit contributions | |
� | -0.012 |
Rudolph | -0.012 |
steen | -0.011 |
之 | -0.011 |
ahime | -0.011 |
Token | two |
Token ID | 734 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
honour | +0.274 |
xual | +0.271 |
rogens | +0.250 |
icle | +0.250 |
stealth | +0.239 |
Neg logit contributions | |
� | -0.329 |
Rudolph | -0.325 |
steen | -0.315 |
之 | -0.313 |
ahime | -0.303 |
Token | popular |
Token ID | 2968 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
honour | +0.167 |
xual | +0.167 |
rogens | +0.153 |
icle | +0.153 |
stealth | +0.145 |
Neg logit contributions | |
� | -0.212 |
Rudolph | -0.210 |
steen | -0.203 |
之 | -0.203 |
ahime | -0.196 |
Token | Luck |
Token ID | 14546 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
� | +0.431 |
Rudolph | +0.430 |
之 | +0.414 |
steen | +0.413 |
ahime | +0.400 |
Neg logit contributions | |
xual | -0.329 |
honour | -0.324 |
rogens | -0.299 |
icle | -0.298 |
stealth | -0.280 |
Token | now |
Token ID | 2197 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
honour | +3.606 |
xual | +3.557 |
icle | +3.388 |
rogens | +3.325 |
stealth | +3.174 |
Neg logit contributions | |
� | -4.806 |
Rudolph | -4.655 |
steen | -4.522 |
之 | -4.500 |
ahime | -4.417 |
Token | - |
Token ID | 12 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
honour | +0.121 |
xual | +0.121 |
rogens | +0.111 |
icle | +0.111 |
stealth | +0.105 |
Neg logit contributions | |
� | -0.169 |
Rudolph | -0.168 |
steen | -0.162 |
之 | -0.162 |
ahime | -0.157 |
Token | based |
Token ID | 3106 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
� | +0.091 |
Rudolph | +0.091 |
之 | +0.088 |
steen | +0.088 |
ahime | +0.086 |
Neg logit contributions | |
honour | -0.043 |
xual | -0.043 |
icle | -0.039 |
rogens | -0.038 |
stealth | -0.036 |
Token | hel |
Token ID | 932 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
honour | +0.641 |
xual | +0.630 |
rogens | +0.580 |
icle | +0.579 |
stealth | +0.552 |
Neg logit contributions | |
� | -0.915 |
Rudolph | -0.903 |
steen | -0.878 |
之 | -0.874 |
ahime | -0.848 |
Token | pl |
Token ID | 489 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
xual | +0.341 |
honour | +0.340 |
icle | +0.317 |
rogens | +0.317 |
stealth | +0.302 |
Neg logit contributions | |
� | -0.317 |
Rudolph | -0.315 |
之 | -0.301 |
steen | -0.301 |
ahime | -0.289 |
Token | and |
Token ID | 290 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
honour | +0.528 |
xual | +0.526 |
rogens | +0.487 |
icle | +0.486 |
stealth | +0.465 |
Neg logit contributions | |
� | -0.552 |
Rudolph | -0.545 |
steen | -0.525 |
之 | -0.524 |
ahime | -0.507 |
Token | knew |
Token ID | 2993 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
xual | +0.027 |
honour | +0.027 |
rogens | +0.025 |
icle | +0.025 |
stealth | +0.024 |
Neg logit contributions | |
� | -0.024 |
Rudolph | -0.024 |
steen | -0.023 |
之 | -0.023 |
ahime | -0.022 |
Token | T |
Token ID | 309 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
honour | +1.383 |
xual | +1.368 |
rogens | +1.266 |
icle | +1.260 |
stealth | +1.217 |
Neg logit contributions | |
� | -1.598 |
Rudolph | -1.560 |
steen | -1.529 |
之 | -1.519 |
ahime | -1.479 |
Token | amer |
Token ID | 2382 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
xual | +1.083 |
honour | +1.082 |
icle | +1.028 |
rogens | +1.023 |
stealth | +0.982 |
Neg logit contributions | |
� | -0.625 |
Rudolph | -0.612 |
之 | -0.583 |
steen | -0.576 |
ahime | -0.546 |
Token | lan |
Token ID | 9620 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
honour | +1.024 |
xual | +1.007 |
icle | +0.964 |
rogens | +0.936 |
stealth | +0.911 |
Neg logit contributions | |
� | -0.961 |
Rudolph | -0.937 |
steen | -0.903 |
之 | -0.901 |
ahime | -0.863 |
Token | Tsarnaev |
Token ID | 43760 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
honour | +0.645 |
xual | +0.638 |
icle | +0.588 |
rogens | +0.586 |
stealth | +0.559 |
Neg logit contributions | |
� | -0.893 |
Rudolph | -0.880 |
之 | -0.854 |
steen | -0.854 |
ahime | -0.831 |
Token | . |
Token ID | 13 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
honour | +3.744 |
xual | +3.636 |
icle | +3.382 |
rogens | +3.347 |
stealth | +3.297 |
Neg logit contributions | |
� | -4.461 |
Rudolph | -4.312 |
steen | -4.190 |
之 | -4.175 |
ahime | -4.116 |
Token | Kh |
Token ID | 5311 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
honour | +0.020 |
xual | +0.020 |
rogens | +0.019 |
icle | +0.019 |
stealth | +0.018 |
Neg logit contributions | |
� | -0.024 |
Rudolph | -0.023 |
steen | -0.023 |
之 | -0.023 |
ahime | -0.022 |
Token | us |
Token ID | 385 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
honour | +0.155 |
xual | +0.154 |
icle | +0.145 |
rogens | +0.145 |
stealth | +0.138 |
Neg logit contributions | |
� | -0.137 |
Rudolph | -0.136 |
之 | -0.130 |
steen | -0.130 |
ahime | -0.124 |
Token | en |
Token ID | 268 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
� | +0.048 |
Rudolph | +0.048 |
之 | +0.046 |
steen | +0.045 |
ahime | +0.043 |
Neg logit contributions | |
honour | -0.060 |
xual | -0.060 |
icle | -0.056 |
rogens | -0.056 |
stealth | -0.053 |
Token | Tar |
Token ID | 14110 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
xual | +0.296 |
honour | +0.296 |
icle | +0.277 |
rogens | +0.275 |
stealth | +0.264 |
Neg logit contributions | |
� | -0.264 |
Rudolph | -0.261 |
之 | -0.252 |
steen | -0.249 |
ahime | -0.242 |
Token | was |
Token ID | 373 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
honour | +1.477 |
xual | +1.461 |
rogens | +1.365 |
icle | +1.355 |
stealth | +1.303 |
Neg logit contributions | |
� | -1.605 |
Rudolph | -1.587 |
steen | -1.523 |
之 | -1.522 |
ahime | -1.488 |
Token | informed |
Token ID | 7981 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
xual | +0.131 |
honour | +0.129 |
icle | +0.120 |
rogens | +0.119 |
stealth | +0.112 |
Neg logit contributions | |
� | -0.163 |
Rudolph | -0.162 |
steen | -0.156 |
之 | -0.156 |
ahime | -0.150 |
Token | of |
Token ID | 286 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
� | +0.231 |
Rudolph | +0.229 |
steen | +0.220 |
之 | +0.219 |
ahime | +0.212 |
Neg logit contributions | |
honour | -0.241 |
xual | -0.241 |
rogens | -0.224 |
icle | -0.224 |
stealth | -0.214 |
Token | a |
Token ID | 257 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
� | +0.260 |
Rudolph | +0.258 |
steen | +0.248 |
之 | +0.248 |
ahime | +0.239 |
Neg logit contributions | |
xual | -0.230 |
honour | -0.229 |
rogens | -0.211 |
icle | -0.211 |
stealth | -0.200 |
Token | potential |
Token ID | 2785 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
� | +0.144 |
Rudolph | +0.143 |
之 | +0.137 |
steen | +0.137 |
ahime | +0.132 |
Neg logit contributions | |
xual | -0.129 |
honour | -0.128 |
rogens | -0.119 |
icle | -0.118 |
stealth | -0.112 |
Token | doping |
Token ID | 42631 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
� | +0.728 |
Rudolph | +0.725 |
之 | +0.697 |
steen | +0.695 |
ahime | +0.675 |
Neg logit contributions | |
xual | -0.481 |
honour | -0.467 |
rogens | -0.431 |
icle | -0.427 |
stealth | -0.398 |
Token | violation |
Token ID | 8747 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
honour | +3.242 |
xual | +3.086 |
icle | +2.880 |
rogens | +2.849 |
stealth | +2.749 |
Neg logit contributions | |
� | -4.808 |
Rudolph | -4.776 |
steen | -4.651 |
之 | -4.634 |
ahime | -4.497 |
Token | stemming |
Token ID | 34807 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
honour | +0.282 |
xual | +0.281 |
icle | +0.260 |
rogens | +0.260 |
stealth | +0.248 |
Neg logit contributions | |
� | -0.292 |
Rudolph | -0.289 |
steen | -0.278 |
之 | -0.278 |
ahime | -0.268 |
Token | from |
Token ID | 422 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
Rudolph | +0.630 |
� | +0.620 |
steen | +0.598 |
之 | +0.596 |
Myr | +0.582 |
Neg logit contributions | |
xual | -0.515 |
honour | -0.493 |
icle | -0.461 |
rogens | -0.459 |
gallery | -0.434 |
Token | an |
Token ID | 281 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
� | +0.047 |
Rudolph | +0.047 |
steen | +0.045 |
之 | +0.045 |
ahime | +0.043 |
Neg logit contributions | |
xual | -0.041 |
honour | -0.040 |
rogens | -0.037 |
icle | -0.037 |
stealth | -0.035 |
Token | out |
Token ID | 503 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
� | +0.347 |
Rudolph | +0.345 |
之 | +0.330 |
steen | +0.330 |
ahime | +0.319 |
Neg logit contributions | |
xual | -0.325 |
honour | -0.322 |
rogens | -0.299 |
icle | -0.299 |
stealth | -0.284 |
Token | Minister |
Token ID | 4139 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
� | +0.747 |
Rudolph | +0.742 |
steen | +0.715 |
之 | +0.714 |
ahime | +0.690 |
Neg logit contributions | |
xual | -0.633 |
honour | -0.632 |
rogens | -0.583 |
icle | -0.582 |
stealth | -0.552 |
Token | P |
Token ID | 350 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
honour | +0.196 |
xual | +0.195 |
icle | +0.180 |
rogens | +0.179 |
stealth | +0.171 |
Neg logit contributions | |
� | -0.219 |
Rudolph | -0.215 |
之 | -0.208 |
steen | -0.208 |
ahime | -0.202 |
Token | iy |
Token ID | 7745 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
honour | +0.368 |
xual | +0.364 |
icle | +0.343 |
rogens | +0.343 |
stealth | +0.325 |
Neg logit contributions | |
� | -0.318 |
Rudolph | -0.310 |
之 | -0.303 |
steen | -0.298 |
ahime | -0.287 |
Token | ush |
Token ID | 1530 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
� | +0.200 |
Rudolph | +0.199 |
之 | +0.193 |
steen | +0.192 |
ahime | +0.185 |
Neg logit contributions | |
honour | -0.127 |
xual | -0.124 |
icle | -0.115 |
rogens | -0.114 |
stealth | -0.106 |
Token | G |
Token ID | 402 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
honour | +0.316 |
xual | +0.307 |
rogens | +0.286 |
icle | +0.284 |
stealth | +0.276 |
Neg logit contributions | |
� | -0.364 |
Rudolph | -0.356 |
steen | -0.348 |
之 | -0.347 |
ahime | -0.334 |
Token | oyal |
Token ID | 4815 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
� | +0.052 |
Rudolph | +0.051 |
之 | +0.050 |
steen | +0.050 |
ahime | +0.049 |
Neg logit contributions | |
honour | -0.021 |
xual | -0.020 |
icle | -0.018 |
rogens | -0.018 |
stealth | -0.016 |
Token | later |
Token ID | 1568 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
honour | +3.802 |
xual | +3.618 |
icle | +3.414 |
rogens | +3.364 |
stealth | +3.296 |
Neg logit contributions | |
� | -4.016 |
Rudolph | -3.947 |
steen | -3.819 |
之 | -3.808 |
ahime | -3.759 |
Token | joined |
Token ID | 5399 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
honour | +0.437 |
xual | +0.433 |
icle | +0.402 |
rogens | +0.401 |
stealth | +0.386 |
Neg logit contributions | |
� | -0.432 |
Rudolph | -0.427 |
steen | -0.410 |
之 | -0.410 |
ahime | -0.397 |
Token | in |
Token ID | 287 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
� | +0.547 |
Rudolph | +0.545 |
steen | +0.522 |
之 | +0.522 |
ahime | +0.502 |
Neg logit contributions | |
xual | -0.509 |
honour | -0.506 |
rogens | -0.470 |
icle | -0.469 |
stealth | -0.445 |
Token | . |
Token ID | 13 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
� | +0.220 |
Rudolph | +0.218 |
steen | +0.210 |
之 | +0.210 |
ahime | +0.203 |
Neg logit contributions | |
honour | -0.205 |
xual | -0.203 |
rogens | -0.188 |
icle | -0.187 |
stealth | -0.179 |
Token |
|
Token ID | 198 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
� | +0.231 |
Rudolph | +0.229 |
steen | +0.221 |
之 | +0.220 |
ahime | +0.214 |
Neg logit contributions | |
honour | -0.205 |
xual | -0.204 |
icle | -0.189 |
rogens | -0.188 |
stealth | -0.179 |
Token | receiving |
Token ID | 6464 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
honour | +0.353 |
xual | +0.351 |
icle | +0.325 |
rogens | +0.323 |
stealth | +0.311 |
Neg logit contributions | |
� | -0.380 |
Rudolph | -0.376 |
steen | -0.363 |
之 | -0.363 |
ahime | -0.352 |
Token | the |
Token ID | 262 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
� | +0.162 |
Rudolph | +0.160 |
steen | +0.155 |
之 | +0.154 |
ahime | +0.149 |
Neg logit contributions | |
honour | -0.137 |
xual | -0.136 |
rogens | -0.126 |
icle | -0.126 |
stealth | -0.119 |
Token | welcome |
Token ID | 7062 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
honour | +0.106 |
xual | +0.105 |
icle | +0.097 |
rogens | +0.097 |
stealth | +0.093 |
Neg logit contributions | |
� | -0.119 |
Rudolph | -0.118 |
steen | -0.114 |
之 | -0.114 |
ahime | -0.110 |
Token | endorsement |
Token ID | 17819 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
honour | +0.693 |
xual | +0.679 |
icle | +0.635 |
rogens | +0.625 |
stealth | +0.604 |
Neg logit contributions | |
� | -0.761 |
Rudolph | -0.743 |
之 | -0.719 |
steen | -0.717 |
ahime | -0.703 |
Token | of |
Token ID | 286 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
� | +1.665 |
Rudolph | +1.658 |
steen | +1.589 |
之 | +1.588 |
ahime | +1.529 |
Neg logit contributions | |
xual | -1.595 |
honour | -1.587 |
rogens | -1.475 |
icle | -1.470 |
stealth | -1.400 |
Token | UFC |
Token ID | 11448 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
� | +0.278 |
Rudolph | +0.274 |
steen | +0.264 |
之 | +0.264 |
ahime | +0.255 |
Neg logit contributions | |
honour | -0.273 |
xual | -0.270 |
icle | -0.251 |
rogens | -0.251 |
stealth | -0.240 |
Token | W |
Token ID | 54 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
honour | +3.475 |
xual | +3.344 |
icle | +3.115 |
rogens | +3.065 |
stealth | +3.031 |
Neg logit contributions | |
� | -4.363 |
Rudolph | -4.207 |
steen | -4.139 |
之 | -4.061 |
ahime | -4.054 |
Token | local |
Token ID | 1957 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
� | +0.332 |
Rudolph | +0.331 |
之 | +0.318 |
steen | +0.318 |
ahime | +0.305 |
Neg logit contributions | |
xual | -0.313 |
honour | -0.312 |
rogens | -0.290 |
icle | -0.289 |
stealth | -0.274 |
Token | 555 |
Token ID | 44717 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
honour | +1.185 |
xual | +1.166 |
icle | +1.084 |
rogens | +1.077 |
stealth | +1.036 |
Neg logit contributions | |
� | -1.447 |
Rudolph | -1.422 |
steen | -1.382 |
之 | -1.368 |
ahime | -1.338 |
Token | was |
Token ID | 373 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
honour | +1.139 |
xual | +1.127 |
icle | +1.041 |
rogens | +1.039 |
stealth | +0.996 |
Neg logit contributions | |
� | -1.236 |
Rudolph | -1.224 |
steen | -1.178 |
之 | -1.171 |
ahime | -1.151 |
Token | being |
Token ID | 852 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
honour | +0.134 |
xual | +0.133 |
rogens | +0.124 |
icle | +0.124 |
stealth | +0.118 |
Neg logit contributions | |
� | -0.144 |
Rudolph | -0.141 |
steen | -0.136 |
之 | -0.136 |
ahime | -0.132 |
Token | Western |
Token ID | 4885 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
honour | +0.014 |
xual | +0.014 |
rogens | +0.013 |
icle | +0.013 |
stealth | +0.013 |
Neg logit contributions | |
� | -0.015 |
Rudolph | -0.015 |
steen | -0.014 |
之 | -0.014 |
ahime | -0.014 |
Token | tourists |
Token ID | 15930 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
� | +0.980 |
Rudolph | +0.971 |
steen | +0.928 |
之 | +0.927 |
ahime | +0.892 |
Neg logit contributions | |
honour | -1.150 |
xual | -1.149 |
rogens | -1.070 |
icle | -1.069 |
stealth | -1.026 |
Token | are |
Token ID | 389 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
� | +0.150 |
Rudolph | +0.149 |
steen | +0.143 |
之 | +0.143 |
ahime | +0.138 |
Neg logit contributions | |
xual | -0.135 |
honour | -0.134 |
rogens | -0.124 |
icle | -0.124 |
stealth | -0.118 |
Token | not |
Token ID | 407 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
� | +0.251 |
Rudolph | +0.248 |
steen | +0.239 |
之 | +0.239 |
ahime | +0.231 |
Neg logit contributions | |
honour | -0.224 |
xual | -0.223 |
rogens | -0.206 |
icle | -0.205 |
stealth | -0.196 |
Token | arrested |
Token ID | 5169 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
� | +0.167 |
Rudolph | +0.165 |
之 | +0.159 |
steen | +0.159 |
ahime | +0.154 |
Neg logit contributions | |
honour | -0.149 |
xual | -0.148 |
rogens | -0.137 |
icle | -0.137 |
stealth | -0.131 |
Token | randomly |
Token ID | 15456 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
honour | +0.317 |
xual | +0.313 |
icle | +0.290 |
rogens | +0.289 |
stealth | +0.277 |
Neg logit contributions | |
� | -0.378 |
Rudolph | -0.371 |
之 | -0.359 |
steen | -0.359 |
ahime | -0.352 |
Token | in |
Token ID | 287 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
honour | +3.415 |
xual | +3.282 |
icle | +3.064 |
stealth | +2.982 |
rogens | +2.978 |
Neg logit contributions | |
� | -4.422 |
Rudolph | -4.211 |
ahime | -4.166 |
之 | -4.127 |
steen | -4.107 |
Token | North |
Token ID | 2258 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
honour | +0.208 |
xual | +0.207 |
rogens | +0.192 |
icle | +0.192 |
stealth | +0.185 |
Neg logit contributions | |
� | -0.194 |
Rudolph | -0.192 |
steen | -0.185 |
之 | -0.184 |
ahime | -0.178 |
Token | Korea |
Token ID | 4969 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
� | +0.140 |
Rudolph | +0.138 |
steen | +0.132 |
之 | +0.132 |
ahime | +0.126 |
Neg logit contributions | |
honour | -0.184 |
xual | -0.184 |
rogens | -0.172 |
icle | -0.172 |
stealth | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
� | +0.727 |
Rudolph | +0.724 |
steen | +0.696 |
之 | +0.695 |
ahime | +0.669 |
Neg logit contributions | |
xual | -0.684 |
honour | -0.681 |
rogens | -0.633 |
icle | -0.630 |
stealth | -0.599 |
Token | If |
Token ID | 1002 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
honour | +0.090 |
xual | +0.089 |
icle | +0.082 |
rogens | +0.082 |
stealth | +0.078 |
Neg logit contributions | |
� | -0.115 |
Rudolph | -0.113 |
steen | -0.110 |
之 | -0.110 |
ahime | -0.107 |
Token | � |
Token ID | 247 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
� | +0.057 |
Rudolph | +0.056 |
steen | +0.053 |
之 | +0.053 |
ahime | +0.051 |
Neg logit contributions | |
xual | -0.089 |
honour | -0.089 |
icle | -0.084 |
rogens | -0.084 |
stealth | -0.081 |
Token | ve |
Token ID | 303 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
� | +0.008 |
Rudolph | +0.008 |
之 | +0.007 |
steen | +0.007 |
ahime | +0.007 |
Neg logit contributions | |
xual | -0.008 |
honour | -0.008 |
icle | -0.007 |
rogens | -0.007 |
stealth | -0.007 |
Token | gotten |
Token ID | 7891 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
� | +0.038 |
Rudolph | +0.038 |
之 | +0.036 |
steen | +0.036 |
ahime | +0.035 |
Neg logit contributions | |
honour | -0.037 |
xual | -0.037 |
rogens | -0.035 |
icle | -0.034 |
stealth | -0.033 |
Token | really |
Token ID | 1107 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
� | +0.903 |
Rudolph | +0.897 |
steen | +0.863 |
之 | +0.862 |
ahime | +0.833 |
Neg logit contributions | |
xual | -0.797 |
honour | -0.797 |
rogens | -0.735 |
icle | -0.734 |
stealth | -0.698 |
Token | into |
Token ID | 656 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
� | +0.476 |
Rudolph | +0.471 |
之 | +0.455 |
steen | +0.455 |
ahime | +0.441 |
Neg logit contributions | |
honour | -0.390 |
xual | -0.389 |
rogens | -0.358 |
icle | -0.358 |
stealth | -0.341 |
Token | homebrew |
Token ID | 45729 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
honour | +1.000 |
xual | +0.984 |
icle | +0.909 |
rogens | +0.895 |
stealth | +0.883 |
Neg logit contributions | |
� | -1.132 |
Rudolph | -1.096 |
之 | -1.081 |
steen | -1.076 |
ahime | -1.048 |
Token | ing |
Token ID | 278 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
honour | +3.529 |
xual | +3.525 |
icle | +3.317 |
rogens | +3.259 |
stealth | +3.189 |
Neg logit contributions | |
� | -4.044 |
Rudolph | -3.974 |
之 | -3.900 |
steen | -3.897 |
ahime | -3.766 |
Token | lately |
Token ID | 16537 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
honour | +0.529 |
xual | +0.527 |
rogens | +0.490 |
icle | +0.490 |
stealth | +0.468 |
Neg logit contributions | |
� | -0.573 |
Rudolph | -0.566 |
steen | -0.548 |
之 | -0.548 |
ahime | -0.529 |
Token | ? |
Token ID | 30 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
� | +0.499 |
Rudolph | +0.493 |
之 | +0.476 |
steen | +0.474 |
ahime | +0.460 |
Neg logit contributions | |
honour | -0.471 |
xual | -0.469 |
icle | -0.438 |
rogens | -0.436 |
stealth | -0.416 |
Token | Well |
Token ID | 3894 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
honour | +0.552 |
xual | +0.544 |
icle | +0.509 |
rogens | +0.501 |
stealth | +0.481 |
Neg logit contributions | |
� | -0.628 |
Rudolph | -0.619 |
之 | -0.604 |
steen | -0.600 |
ahime | -0.588 |
Token | , |
Token ID | 11 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
� | +0.356 |
Rudolph | +0.352 |
之 | +0.341 |
steen | +0.340 |
ahime | +0.330 |
Neg logit contributions | |
honour | -0.316 |
xual | -0.315 |
icle | -0.292 |
rogens | -0.291 |
stealth | -0.278 |
Token | successful |
Token ID | 4388 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
� | +0.206 |
Rudolph | +0.204 |
steen | +0.197 |
之 | +0.197 |
ahime | +0.191 |
Neg logit contributions | |
honour | -0.174 |
xual | -0.173 |
rogens | -0.159 |
icle | -0.159 |
stealth | -0.152 |
Token | infiltration |
Token ID | 45106 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
� | +1.441 |
Rudolph | +1.435 |
之 | +1.379 |
steen | +1.379 |
ahime | +1.333 |
Neg logit contributions | |
xual | -1.110 |
honour | -1.100 |
rogens | -1.013 |
icle | -1.010 |
stealth | -0.951 |
Token | of |
Token ID | 286 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
� | +1.649 |
Rudolph | +1.634 |
steen | +1.574 |
之 | +1.571 |
ahime | +1.516 |
Neg logit contributions | |
honour | -1.614 |
xual | -1.613 |
rogens | -1.494 |
icle | -1.493 |
stealth | -1.428 |
Token | about |
Token ID | 546 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
� | +0.317 |
Rudolph | +0.314 |
steen | +0.303 |
之 | +0.303 |
ahime | +0.293 |
Neg logit contributions | |
honour | -0.252 |
xual | -0.252 |
rogens | -0.232 |
icle | -0.231 |
stealth | -0.220 |
Token | 60 |
Token ID | 3126 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
� | +0.609 |
Rudolph | +0.609 |
之 | +0.582 |
steen | +0.582 |
ahime | +0.561 |
Neg logit contributions | |
xual | -0.540 |
honour | -0.535 |
rogens | -0.496 |
icle | -0.495 |
stealth | -0.467 |
Token | PKK |
Token ID | 35176 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
� | +0.337 |
Rudolph | +0.335 |
steen | +0.323 |
之 | +0.323 |
ahime | +0.312 |
Neg logit contributions | |
xual | -0.246 |
honour | -0.246 |
rogens | -0.225 |
icle | -0.224 |
stealth | -0.212 |
Token | gu |
Token ID | 915 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
honour | +3.270 |
xual | +3.070 |
rogens | +2.914 |
icle | +2.879 |
stealth | +2.862 |
Neg logit contributions | |
� | -4.378 |
Rudolph | -4.257 |
steen | -4.196 |
之 | -4.120 |
ahime | -4.095 |
Token | err |
Token ID | 8056 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
honour | +1.536 |
xual | +1.522 |
rogens | +1.446 |
icle | +1.442 |
stealth | +1.352 |
Neg logit contributions | |
� | -1.444 |
Rudolph | -1.409 |
steen | -1.358 |
之 | -1.355 |
ahime | -1.296 |
Token | illas |
Token ID | 25314 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
� | +0.157 |
Rudolph | +0.152 |
之 | +0.148 |
steen | +0.147 |
ahime | +0.142 |
Neg logit contributions | |
honour | -0.176 |
xual | -0.175 |
rogens | -0.166 |
icle | -0.166 |
stealth | -0.157 |
Token | into |
Token ID | 656 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
honour | +0.454 |
xual | +0.446 |
icle | +0.411 |
rogens | +0.410 |
stealth | +0.395 |
Neg logit contributions | |
� | -0.628 |
Rudolph | -0.611 |
steen | -0.594 |
之 | -0.593 |
ahime | -0.579 |
Token | Turkey |
Token ID | 7137 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
honour | +0.658 |
xual | +0.652 |
icle | +0.591 |
rogens | +0.589 |
stealth | +0.559 |
Neg logit contributions | |
� | -1.059 |
Rudolph | -1.046 |
steen | -1.019 |
之 | -1.015 |
ahime | -0.987 |
Token | - |
Token ID | 12 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
xual | +0.004 |
honour | +0.004 |
rogens | +0.004 |
icle | +0.004 |
stealth | +0.003 |
Neg logit contributions | |
� | -0.005 |
Rudolph | -0.005 |
steen | -0.005 |
之 | -0.005 |
ahime | -0.004 |
Token | w |
Token ID | 86 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
xual | +0.126 |
honour | +0.126 |
rogens | +0.116 |
icle | +0.116 |
stealth | +0.110 |
Neg logit contributions | |
� | -0.154 |
Rudolph | -0.153 |
steen | -0.148 |
之 | -0.147 |
ahime | -0.143 |
Token | earing |
Token ID | 6648 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
� | +0.226 |
Rudolph | +0.226 |
steen | +0.216 |
之 | +0.216 |
ahime | +0.209 |
Neg logit contributions | |
xual | -0.218 |
honour | -0.217 |
rogens | -0.202 |
icle | -0.201 |
stealth | -0.192 |
Token | of |
Token ID | 286 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
honour | +0.305 |
xual | +0.303 |
icle | +0.281 |
rogens | +0.281 |
stealth | +0.269 |
Neg logit contributions | |
� | -0.319 |
Rudolph | -0.314 |
steen | -0.305 |
之 | -0.303 |
ahime | -0.293 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
� | +0.141 |
Rudolph | +0.139 |
steen | +0.135 |
之 | +0.134 |
ahime | +0.130 |
Neg logit contributions | |
honour | -0.111 |
xual | -0.110 |
rogens | -0.101 |
icle | -0.101 |
stealth | -0.096 |
Token | hijab |
Token ID | 48492 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
honour | +0.081 |
xual | +0.080 |
icle | +0.073 |
rogens | +0.072 |
stealth | +0.068 |
Neg logit contributions | |
� | -0.131 |
Rudolph | -0.129 |
steen | -0.126 |
之 | -0.125 |
ahime | -0.122 |
Token | or |
Token ID | 393 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
honour | +3.355 |
xual | +3.280 |
icle | +3.034 |
rogens | +2.966 |
stealth | +2.894 |
Neg logit contributions | |
� | -4.253 |
Rudolph | -4.098 |
steen | -4.002 |
之 | -3.927 |
ahime | -3.854 |
Token | veil |
Token ID | 30615 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
� | +0.027 |
Rudolph | +0.027 |
steen | +0.026 |
之 | +0.026 |
ahime | +0.025 |
Neg logit contributions | |
honour | -0.022 |
xual | -0.022 |
icle | -0.020 |
rogens | -0.020 |
stealth | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
honour | +1.481 |
xual | +1.463 |
icle | +1.354 |
rogens | +1.334 |
stealth | +1.290 |
Neg logit contributions | |
� | -1.737 |
Rudolph | -1.692 |
steen | -1.643 |
之 | -1.626 |
ahime | -1.589 |
Token | � |
Token ID | 447 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
� | +0.113 |
Rudolph | +0.111 |
steen | +0.108 |
之 | +0.107 |
ahime | +0.104 |
Neg logit contributions | |
honour | -0.099 |
xual | -0.098 |
icle | -0.090 |
rogens | -0.090 |
stealth | -0.086 |
Token | � |
Token ID | 251 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
honour | +0.134 |
xual | +0.133 |
rogens | +0.124 |
icle | +0.123 |
stealth | +0.118 |
Neg logit contributions | |
� | -0.131 |
Rudolph | -0.130 |
steen | -0.125 |
之 | -0.125 |
ahime | -0.120 |
Token | outright |
Token ID | 15828 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
� | +0.533 |
Rudolph | +0.527 |
steen | +0.509 |
之 | +0.507 |
ahime | +0.488 |
Neg logit contributions | |
honour | -0.537 |
xual | -0.520 |
rogens | -0.489 |
icle | -0.488 |
stealth | -0.469 |
Token | ban |
Token ID | 3958 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
honour | +0.283 |
xual | +0.279 |
rogens | +0.259 |
icle | +0.259 |
stealth | +0.249 |
Neg logit contributions | |
� | -0.284 |
Rudolph | -0.281 |
steen | -0.270 |
之 | -0.270 |
ahime | -0.261 |
Token | on |
Token ID | 319 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
honour | +0.287 |
xual | +0.286 |
icle | +0.266 |
rogens | +0.264 |
stealth | +0.253 |
Neg logit contributions | |
� | -0.296 |
Rudolph | -0.292 |
之 | -0.280 |
steen | -0.278 |
ahime | -0.271 |
Token | wearing |
Token ID | 5762 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
� | +0.524 |
Rudolph | +0.522 |
steen | +0.502 |
之 | +0.501 |
ahime | +0.484 |
Neg logit contributions | |
xual | -0.427 |
honour | -0.425 |
rogens | -0.392 |
icle | -0.392 |
stealth | -0.370 |
Token | the |
Token ID | 262 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
honour | +0.028 |
xual | +0.028 |
rogens | +0.026 |
icle | +0.026 |
stealth | +0.025 |
Neg logit contributions | |
� | -0.033 |
Rudolph | -0.033 |
steen | -0.032 |
之 | -0.032 |
ahime | -0.031 |
Token | hijab |
Token ID | 48492 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
honour | +0.049 |
xual | +0.049 |
rogens | +0.045 |
icle | +0.045 |
stealth | +0.042 |
Neg logit contributions | |
� | -0.070 |
Rudolph | -0.069 |
steen | -0.067 |
之 | -0.067 |
ahime | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
honour | +3.349 |
xual | +3.249 |
icle | +3.010 |
rogens | +2.954 |
stealth | +2.911 |
Neg logit contributions | |
� | -4.264 |
Rudolph | -4.096 |
steen | -3.998 |
之 | -3.985 |
ahime | -3.886 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
� | +0.134 |
Rudolph | +0.133 |
steen | +0.129 |
之 | +0.128 |
ahime | +0.125 |
Neg logit contributions | |
honour | -0.115 |
xual | -0.114 |
icle | -0.105 |
rogens | -0.105 |
stealth | -0.100 |
Token |
|
Token ID | 198 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
� | +0.085 |
Rudolph | +0.085 |
steen | +0.082 |
之 | +0.081 |
Myr | +0.078 |
Neg logit contributions | |
xual | -0.083 |
honour | -0.082 |
rogens | -0.077 |
icle | -0.076 |
stealth | -0.072 |
Token | Sad |
Token ID | 26699 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
honour | +0.030 |
xual | +0.029 |
icle | +0.028 |
rogens | +0.028 |
stealth | +0.026 |
Neg logit contributions | |
� | -0.031 |
Rudolph | -0.031 |
steen | -0.029 |
之 | -0.029 |
ahime | -0.028 |
Token | ain |
Token ID | 391 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
honour | +0.403 |
xual | +0.402 |
rogens | +0.370 |
icle | +0.370 |
stealth | +0.349 |
Neg logit contributions | |
� | -0.510 |
Rudolph | -0.505 |
之 | -0.487 |
steen | -0.486 |
ahime | -0.471 |
Token | re |
Token ID | 260 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
� | +0.743 |
Rudolph | +0.738 |
之 | +0.710 |
steen | +0.709 |
ahime | +0.686 |
Neg logit contributions | |
xual | -0.631 |
honour | -0.630 |
rogens | -0.581 |
icle | -0.580 |
stealth | -0.550 |
Token | . |
Token ID | 13 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
xual | +0.855 |
honour | +0.850 |
icle | +0.792 |
rogens | +0.787 |
stealth | +0.750 |
Neg logit contributions | |
� | -0.881 |
Rudolph | -0.878 |
之 | -0.838 |
steen | -0.835 |
ahime | -0.810 |
Token | kov |
Token ID | 21862 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
� | +0.457 |
Rudolph | +0.455 |
之 | +0.440 |
steen | +0.439 |
ahime | +0.427 |
Neg logit contributions | |
xual | -0.281 |
honour | -0.280 |
icle | -0.254 |
rogens | -0.254 |
stealth | -0.237 |
Token | id |
Token ID | 312 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
honour | +1.218 |
xual | +1.217 |
icle | +1.154 |
rogens | +1.140 |
stealth | +1.073 |
Neg logit contributions | |
� | -1.189 |
Rudolph | -1.183 |
之 | -1.129 |
steen | -1.114 |
ahime | -1.080 |
Token | g |
Token ID | 70 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
� | +1.052 |
Rudolph | +1.046 |
之 | +1.000 |
steen | +0.997 |
ahime | +0.961 |
Neg logit contributions | |
honour | -1.088 |
xual | -1.087 |
icle | -1.014 |
rogens | -1.011 |
stealth | -0.961 |
Token | oyal |
Token ID | 4815 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
� | +0.335 |
Rudolph | +0.333 |
之 | +0.318 |
steen | +0.317 |
ahime | +0.307 |
Neg logit contributions | |
honour | -0.337 |
xual | -0.337 |
icle | -0.314 |
rogens | -0.313 |
stealth | -0.298 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
xual | +3.529 |
honour | +3.496 |
icle | +3.289 |
rogens | +3.194 |
gallery | +3.096 |
Neg logit contributions | |
Rudolph | -3.921 |
� | -3.898 |
之 | -3.693 |
steen | -3.616 |
ahime | -3.576 |
Token | net |
Token ID | 3262 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
xual | +0.062 |
honour | +0.062 |
icle | +0.056 |
rogens | +0.056 |
stealth | +0.052 |
Neg logit contributions | |
� | -0.111 |
Rudolph | -0.111 |
之 | -0.107 |
steen | -0.107 |
ahime | -0.104 |
Token | ) |
Token ID | 8 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
� | +0.329 |
Rudolph | +0.327 |
steen | +0.314 |
之 | +0.314 |
ahime | +0.304 |
Neg logit contributions | |
xual | -0.296 |
honour | -0.296 |
rogens | -0.274 |
icle | -0.273 |
stealth | -0.260 |
Token | or |
Token ID | 393 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
honour | +0.708 |
xual | +0.708 |
icle | +0.654 |
rogens | +0.652 |
stealth | +0.623 |
Neg logit contributions | |
� | -0.810 |
Rudolph | -0.799 |
之 | -0.771 |
steen | -0.770 |
ahime | -0.742 |
Token | Stan |
Token ID | 7299 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
� | +0.131 |
Rudolph | +0.130 |
steen | +0.125 |
之 | +0.125 |
ahime | +0.121 |
Neg logit contributions | |
honour | -0.120 |
xual | -0.120 |
icle | -0.111 |
rogens | -0.110 |
stealth | -0.105 |
Token | against |
Token ID | 1028 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
honour | +1.157 |
xual | +1.141 |
icle | +1.061 |
rogens | +1.057 |
stealth | +1.016 |
Neg logit contributions | |
� | -1.134 |
Rudolph | -1.120 |
steen | -1.078 |
之 | -1.074 |
ahime | -1.054 |
Token | Mark |
Token ID | 2940 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
Rudolph | +0.027 |
� | +0.027 |
steen | +0.026 |
之 | +0.026 |
ahime | +0.025 |
Neg logit contributions | |
xual | -0.029 |
honour | -0.028 |
rogens | -0.027 |
icle | -0.026 |
stealth | -0.025 |
Token | Hunt |
Token ID | 12937 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
xual | +0.451 |
honour | +0.451 |
icle | +0.420 |
rogens | +0.419 |
stealth | +0.401 |
Neg logit contributions | |
� | -0.411 |
Rudolph | -0.406 |
steen | -0.390 |
之 | -0.390 |
ahime | -0.375 |
Token | back |
Token ID | 736 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
� | +0.848 |
Rudolph | +0.841 |
steen | +0.808 |
之 | +0.808 |
ahime | +0.782 |
Neg logit contributions | |
xual | -0.760 |
honour | -0.760 |
rogens | -0.702 |
icle | -0.701 |
stealth | -0.666 |
Token | at |
Token ID | 379 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
honour | +0.638 |
xual | +0.638 |
rogens | +0.586 |
icle | +0.585 |
stealth | +0.556 |
Neg logit contributions | |
� | -0.796 |
Rudolph | -0.790 |
之 | -0.761 |
steen | -0.760 |
ahime | -0.740 |
Token | UFC |
Token ID | 11448 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
� | +0.278 |
Rudolph | +0.276 |
steen | +0.267 |
之 | +0.267 |
ahime | +0.261 |
Neg logit contributions | |
honour | -0.154 |
xual | -0.154 |
rogens | -0.138 |
icle | -0.138 |
stealth | -0.129 |
Token | 200 |
Token ID | 939 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
honour | +3.080 |
xual | +2.936 |
icle | +2.755 |
rogens | +2.673 |
stealth | +2.622 |
Neg logit contributions | |
� | -4.345 |
Rudolph | -4.181 |
steen | -4.127 |
ahime | -4.099 |
之 | -4.034 |
Token | . |
Token ID | 13 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
� | +0.942 |
Rudolph | +0.935 |
steen | +0.898 |
之 | +0.898 |
ahime | +0.866 |
Neg logit contributions | |
xual | -0.886 |
honour | -0.884 |
rogens | -0.819 |
icle | -0.817 |
stealth | -0.778 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
honour | +0.037 |
xual | +0.037 |
icle | +0.034 |
rogens | +0.034 |
stealth | +0.032 |
Neg logit contributions | |
� | -0.043 |
Rudolph | -0.042 |
steen | -0.041 |
之 | -0.041 |
ahime | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Rudolph | +0.870 |
� | +0.865 |
之 | +0.836 |
steen | +0.834 |
Myr | +0.802 |
Neg logit contributions | |
xual | -0.954 |
honour | -0.902 |
rogens | -0.865 |
icle | -0.844 |
stealth | -0.809 |
Token | US |
Token ID | 2937 |
Feature activation | -9.72e-02 |
Pos logit contributions | |
� | +0.803 |
Rudolph | +0.798 |
steen | +0.763 |
之 | +0.762 |
ahime | +0.736 |
Neg logit contributions | |
honour | -0.886 |
xual | -0.885 |
rogens | -0.825 |
icle | -0.825 |
stealth | -0.788 |
Token | January |
Token ID | 3269 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
Rudolph | +0.079 |
� | +0.078 |
steen | +0.075 |
之 | +0.075 |
Myr | +0.072 |
Neg logit contributions | |
xual | -0.072 |
honour | -0.070 |
rogens | -0.066 |
icle | -0.066 |
stealth | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
honour | +0.590 |
xual | +0.585 |
icle | +0.543 |
rogens | +0.540 |
stealth | +0.519 |
Neg logit contributions | |
� | -0.623 |
Rudolph | -0.615 |
之 | -0.592 |
steen | -0.589 |
ahime | -0.574 |
Token |
|
Token ID | 198 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
xual | +0.081 |
honour | +0.081 |
rogens | +0.075 |
icle | +0.074 |
stealth | +0.071 |
Neg logit contributions | |
� | -0.092 |
Rudolph | -0.091 |
steen | -0.088 |
之 | -0.087 |
ahime | -0.084 |
Token |
|
Token ID | 198 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
Rudolph | +0.487 |
� | +0.486 |
steen | +0.470 |
之 | +0.467 |
Myr | +0.448 |
Neg logit contributions | |
xual | -0.501 |
honour | -0.484 |
rogens | -0.457 |
icle | -0.450 |
stealth | -0.431 |
Token | Par |
Token ID | 10044 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
� | +0.448 |
Rudolph | +0.445 |
steen | +0.427 |
之 | +0.427 |
ahime | +0.412 |
Neg logit contributions | |
xual | -0.436 |
honour | -0.436 |
rogens | -0.404 |
icle | -0.404 |
stealth | -0.385 |
Token | liament |
Token ID | 5130 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
� | +0.268 |
Rudolph | +0.264 |
之 | +0.256 |
steen | +0.255 |
ahime | +0.248 |
Neg logit contributions | |
honour | -0.179 |
xual | -0.178 |
icle | -0.165 |
rogens | -0.164 |
stealth | -0.154 |
Token | Hill |
Token ID | 3327 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
honour | +3.409 |
xual | +3.249 |
icle | +3.096 |
rogens | +3.063 |
stealth | +2.956 |
Neg logit contributions | |
� | -3.926 |
Rudolph | -3.896 |
之 | -3.743 |
steen | -3.736 |
ahime | -3.721 |
Token | on |
Token ID | 319 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
� | +0.544 |
Rudolph | +0.540 |
steen | +0.518 |
之 | +0.518 |
ahime | +0.498 |
Neg logit contributions | |
xual | -0.544 |
honour | -0.543 |
rogens | -0.504 |
icle | -0.503 |
stealth | -0.480 |
Token | Wed |
Token ID | 3300 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
� | +0.553 |
Rudolph | +0.551 |
steen | +0.528 |
之 | +0.528 |
ahime | +0.510 |
Neg logit contributions | |
xual | -0.448 |
honour | -0.442 |
rogens | -0.409 |
icle | -0.407 |
stealth | -0.385 |
Token | nes |
Token ID | 2516 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
Rudolph | +1.654 |
� | +1.653 |
steen | +1.580 |
之 | +1.568 |
ahime | +1.508 |
Neg logit contributions | |
xual | -2.036 |
honour | -2.023 |
rogens | -1.901 |
icle | -1.887 |
stealth | -1.805 |
Token | days |
Token ID | 12545 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
� | +0.430 |
Rudolph | +0.426 |
之 | +0.408 |
steen | +0.408 |
ahime | +0.394 |
Neg logit contributions | |
xual | -0.441 |
honour | -0.441 |
rogens | -0.409 |
icle | -0.409 |
stealth | -0.390 |
Token | , |
Token ID | 11 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
� | +0.341 |
Rudolph | +0.337 |
steen | +0.325 |
之 | +0.325 |
ahime | +0.315 |
Neg logit contributions | |
honour | -0.299 |
xual | -0.297 |
icle | -0.276 |
rogens | -0.276 |
stealth | -0.263 |
Token | the |
Token ID | 262 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
honour | +0.043 |
xual | +0.043 |
rogens | +0.040 |
icle | +0.040 |
stealth | +0.038 |
Neg logit contributions | |
� | -0.043 |
Rudolph | -0.043 |
steen | -0.041 |
之 | -0.041 |
ahime | -0.040 |
Token | levels |
Token ID | 2974 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
� | +0.207 |
Rudolph | +0.206 |
steen | +0.199 |
之 | +0.198 |
ahime | +0.192 |
Neg logit contributions | |
honour | -0.173 |
xual | -0.173 |
rogens | -0.159 |
icle | -0.159 |
stealth | -0.152 |
Token | of |
Token ID | 286 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
� | +0.050 |
Rudolph | +0.050 |
steen | +0.048 |
之 | +0.048 |
ahime | +0.046 |
Neg logit contributions | |
honour | -0.049 |
xual | -0.049 |
rogens | -0.045 |
icle | -0.045 |
stealth | -0.043 |
Token | radioactive |
Token ID | 25521 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
� | +0.083 |
Rudolph | +0.082 |
steen | +0.079 |
之 | +0.079 |
ahime | +0.077 |
Neg logit contributions | |
honour | -0.073 |
xual | -0.073 |
rogens | -0.067 |
icle | -0.067 |
stealth | -0.064 |
Token | iodine |
Token ID | 50047 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
honour | +2.505 |
xual | +2.389 |
icle | +2.283 |
rogens | +2.279 |
stealth | +2.223 |
Neg logit contributions | |
� | -3.085 |
Rudolph | -3.063 |
之 | -2.969 |
steen | -2.960 |
ahime | -2.883 |
Token | will |
Token ID | 481 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
honour | +3.176 |
xual | +3.043 |
icle | +2.957 |
rogens | +2.942 |
stealth | +2.798 |
Neg logit contributions | |
� | -4.076 |
Rudolph | -4.035 |
steen | -3.929 |
之 | -3.900 |
ahime | -3.760 |
Token | only |
Token ID | 691 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
honour | +0.279 |
xual | +0.277 |
rogens | +0.256 |
icle | +0.256 |
stealth | +0.245 |
Neg logit contributions | |
� | -0.319 |
Rudolph | -0.316 |
steen | -0.305 |
之 | -0.304 |
ahime | -0.295 |
Token | be |
Token ID | 307 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
� | +1.610 |
Rudolph | +1.599 |
之 | +1.537 |
steen | +1.536 |
ahime | +1.480 |
Neg logit contributions | |
xual | -1.368 |
honour | -1.349 |
rogens | -1.252 |
icle | -1.251 |
stealth | -1.176 |
Token | about |
Token ID | 546 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
� | +0.211 |
Rudolph | +0.210 |
steen | +0.202 |
之 | +0.202 |
ahime | +0.196 |
Neg logit contributions | |
xual | -0.161 |
honour | -0.161 |
rogens | -0.147 |
icle | -0.147 |
stealth | -0.139 |
Token | two |
Token ID | 734 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
� | +0.249 |
Rudolph | +0.247 |
steen | +0.238 |
之 | +0.238 |
ahime | +0.229 |
Neg logit contributions | |
xual | -0.222 |
honour | -0.222 |
rogens | -0.205 |
icle | -0.205 |
stealth | -0.194 |
Token | , |
Token ID | 11 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
� | +0.032 |
Rudolph | +0.031 |
steen | +0.030 |
之 | +0.030 |
ahime | +0.029 |
Neg logit contributions | |
honour | -0.027 |
xual | -0.027 |
rogens | -0.025 |
icle | -0.025 |
stealth | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
� | +0.072 |
Rudolph | +0.071 |
steen | +0.068 |
之 | +0.068 |
ahime | +0.066 |
Neg logit contributions | |
honour | -0.062 |
xual | -0.062 |
rogens | -0.057 |
icle | -0.057 |
stealth | -0.055 |
Token | crisis |
Token ID | 4902 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
� | +0.352 |
Rudolph | +0.350 |
steen | +0.337 |
之 | +0.337 |
ahime | +0.326 |
Neg logit contributions | |
honour | -0.297 |
xual | -0.296 |
rogens | -0.273 |
icle | -0.272 |
stealth | -0.259 |
Token | at |
Token ID | 379 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
� | +0.230 |
Rudolph | +0.228 |
steen | +0.218 |
之 | +0.218 |
ahime | +0.210 |
Neg logit contributions | |
xual | -0.246 |
honour | -0.246 |
rogens | -0.229 |
icle | -0.228 |
stealth | -0.218 |
Token | the |
Token ID | 262 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
� | +0.689 |
Rudolph | +0.684 |
steen | +0.660 |
之 | +0.659 |
ahime | +0.639 |
Neg logit contributions | |
honour | -0.528 |
xual | -0.527 |
rogens | -0.484 |
icle | -0.483 |
stealth | -0.457 |
Token | Fukushima |
Token ID | 34170 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
� | +0.218 |
Rudolph | +0.217 |
steen | +0.209 |
之 | +0.209 |
ahime | +0.203 |
Neg logit contributions | |
xual | -0.161 |
honour | -0.160 |
rogens | -0.147 |
icle | -0.146 |
stealth | -0.138 |
Token | plant |
Token ID | 4618 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
honour | +2.880 |
xual | +2.742 |
icle | +2.591 |
rogens | +2.561 |
stealth | +2.465 |
Neg logit contributions | |
� | -4.438 |
Rudolph | -4.342 |
steen | -4.276 |
之 | -4.210 |
ahime | -4.105 |
Token | has |
Token ID | 468 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
honour | +1.454 |
xual | +1.445 |
rogens | +1.348 |
icle | +1.346 |
stealth | +1.293 |
Neg logit contributions | |
� | -1.421 |
Rudolph | -1.405 |
steen | -1.353 |
之 | -1.347 |
ahime | -1.305 |
Token | worsened |
Token ID | 44838 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
xual | +0.090 |
honour | +0.090 |
rogens | +0.083 |
icle | +0.083 |
stealth | +0.079 |
Neg logit contributions | |
� | -0.099 |
Rudolph | -0.098 |
steen | -0.094 |
之 | -0.094 |
ahime | -0.091 |
Token | since |
Token ID | 1201 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
� | +0.465 |
Rudolph | +0.462 |
steen | +0.445 |
之 | +0.444 |
ahime | +0.430 |
Neg logit contributions | |
xual | -0.398 |
honour | -0.397 |
rogens | -0.366 |
icle | -0.365 |
stealth | -0.347 |
Token | Friday |
Token ID | 3217 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
honour | +0.673 |
xual | +0.665 |
rogens | +0.620 |
icle | +0.615 |
stealth | +0.591 |
Neg logit contributions | |
� | -0.775 |
Rudolph | -0.764 |
steen | -0.742 |
之 | -0.739 |
ahime | -0.717 |
Token | ? |
Token ID | 30 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
� | +0.499 |
Rudolph | +0.493 |
之 | +0.476 |
steen | +0.474 |
ahime | +0.460 |
Neg logit contributions | |
honour | -0.471 |
xual | -0.469 |
icle | -0.438 |
rogens | -0.436 |
stealth | -0.416 |
Token | Well |
Token ID | 3894 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
honour | +0.552 |
xual | +0.544 |
icle | +0.509 |
rogens | +0.501 |
stealth | +0.481 |
Neg logit contributions | |
� | -0.628 |
Rudolph | -0.619 |
之 | -0.604 |
steen | -0.600 |
ahime | -0.588 |
Token | , |
Token ID | 11 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
� | +0.356 |
Rudolph | +0.352 |
之 | +0.341 |
steen | +0.340 |
ahime | +0.330 |
Neg logit contributions | |
honour | -0.316 |
xual | -0.315 |
icle | -0.292 |
rogens | -0.291 |
stealth | -0.278 |
Token | fuck |
Token ID | 5089 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
honour | +0.105 |
xual | +0.104 |
icle | +0.096 |
rogens | +0.096 |
stealth | +0.092 |
Neg logit contributions | |
� | -0.113 |
Rudolph | -0.112 |
之 | -0.108 |
steen | -0.108 |
ahime | -0.105 |
Token | your |
Token ID | 534 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
� | +0.571 |
Rudolph | +0.566 |
之 | +0.545 |
steen | +0.543 |
ahime | +0.526 |
Neg logit contributions | |
honour | -0.528 |
xual | -0.526 |
icle | -0.487 |
rogens | -0.486 |
stealth | -0.464 |
Token | homebrew |
Token ID | 45729 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
� | +0.285 |
Rudolph | +0.283 |
steen | +0.273 |
之 | +0.272 |
ahime | +0.264 |
Neg logit contributions | |
honour | -0.247 |
xual | -0.246 |
icle | -0.227 |
rogens | -0.227 |
stealth | -0.216 |
Token | ing |
Token ID | 278 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
honour | +3.362 |
xual | +3.301 |
icle | +3.128 |
rogens | +3.075 |
stealth | +2.978 |
Neg logit contributions | |
� | -3.808 |
Rudolph | -3.798 |
steen | -3.710 |
之 | -3.682 |
ahime | -3.560 |
Token | . |
Token ID | 13 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
honour | +0.571 |
xual | +0.563 |
rogens | +0.524 |
icle | +0.524 |
stealth | +0.502 |
Neg logit contributions | |
� | -0.618 |
Rudolph | -0.614 |
steen | -0.596 |
之 | -0.592 |
ahime | -0.575 |
Token | Give |
Token ID | 13786 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
honour | +0.281 |
xual | +0.280 |
icle | +0.259 |
rogens | +0.257 |
stealth | +0.245 |
Neg logit contributions | |
� | -0.328 |
Rudolph | -0.324 |
之 | -0.315 |
steen | -0.313 |
ahime | -0.306 |
Token | me |
Token ID | 502 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
honour | +0.692 |
xual | +0.687 |
icle | +0.634 |
rogens | +0.631 |
stealth | +0.605 |
Neg logit contributions | |
� | -0.765 |
Rudolph | -0.756 |
之 | -0.733 |
steen | -0.730 |
ahime | -0.709 |
Token | Kam |
Token ID | 12670 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
� | +0.351 |
Rudolph | +0.348 |
之 | +0.336 |
steen | +0.335 |
ahime | +0.325 |
Neg logit contributions | |
honour | -0.291 |
xual | -0.289 |
rogens | -0.267 |
icle | -0.266 |
stealth | -0.254 |
Token | fuel |
Token ID | 25802 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
� | +0.208 |
Rudolph | +0.206 |
之 | +0.199 |
steen | +0.199 |
ahime | +0.193 |
Neg logit contributions | |
xual | -0.169 |
honour | -0.168 |
rogens | -0.154 |
icle | -0.153 |
stealth | -0.145 |
Token | ed |
Token ID | 276 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
honour | +0.551 |
xual | +0.547 |
icle | +0.514 |
rogens | +0.508 |
stealth | +0.491 |
Neg logit contributions | |
� | -0.563 |
Rudolph | -0.554 |
steen | -0.535 |
之 | -0.533 |
ahime | -0.514 |
Token | nuclear |
Token ID | 4523 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
honour | +0.465 |
xual | +0.460 |
icle | +0.431 |
rogens | +0.430 |
stealth | +0.415 |
Neg logit contributions | |
� | -0.459 |
Rudolph | -0.452 |
steen | -0.437 |
之 | -0.435 |
ahime | -0.419 |
Token | reactor |
Token ID | 21905 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
honour | +0.705 |
xual | +0.702 |
icle | +0.653 |
rogens | +0.652 |
stealth | +0.624 |
Neg logit contributions | |
� | -0.713 |
Rudolph | -0.707 |
steen | -0.680 |
之 | -0.678 |
ahime | -0.654 |
Token | at |
Token ID | 379 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
honour | +1.594 |
xual | +1.565 |
icle | +1.462 |
rogens | +1.460 |
stealth | +1.407 |
Neg logit contributions | |
� | -1.839 |
Rudolph | -1.811 |
steen | -1.760 |
之 | -1.747 |
ahime | -1.689 |
Token | Fukushima |
Token ID | 34170 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
� | +0.266 |
Rudolph | +0.264 |
steen | +0.254 |
之 | +0.254 |
ahime | +0.245 |
Neg logit contributions | |
xual | -0.240 |
honour | -0.239 |
rogens | -0.221 |
icle | -0.221 |
stealth | -0.210 |
Token | — |
Token ID | 851 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
honour | +3.324 |
xual | +3.199 |
icle | +3.000 |
rogens | +2.973 |
stealth | +2.872 |
Neg logit contributions | |
� | -3.972 |
Rudolph | -3.875 |
steen | -3.801 |
之 | -3.745 |
ahime | -3.632 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
� | +1.158 |
Rudolph | +1.149 |
steen | +1.106 |
之 | +1.104 |
ahime | +1.066 |
Neg logit contributions | |
honour | -1.034 |
xual | -1.033 |
rogens | -0.954 |
icle | -0.953 |
stealth | -0.908 |
Token | only |
Token ID | 691 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
� | +0.121 |
Rudolph | +0.120 |
steen | +0.116 |
之 | +0.116 |
ahime | +0.112 |
Neg logit contributions | |
xual | -0.090 |
honour | -0.089 |
rogens | -0.082 |
icle | -0.082 |
stealth | -0.077 |
Token | one |
Token ID | 530 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
� | +1.658 |
Rudolph | +1.654 |
之 | +1.587 |
steen | +1.583 |
ahime | +1.530 |
Neg logit contributions | |
xual | -1.459 |
honour | -1.436 |
rogens | -1.335 |
icle | -1.327 |
stealth | -1.249 |
Token | of |
Token ID | 286 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
� | +0.377 |
Rudolph | +0.373 |
steen | +0.360 |
之 | +0.359 |
ahime | +0.348 |
Neg logit contributions | |
honour | -0.348 |
xual | -0.344 |
rogens | -0.320 |
icle | -0.319 |
stealth | -0.306 |
Token | � |
Token ID | 250 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
� | +0.450 |
Rudolph | +0.447 |
steen | +0.429 |
之 | +0.428 |
ahime | +0.413 |
Neg logit contributions | |
honour | -0.466 |
xual | -0.466 |
rogens | -0.433 |
icle | -0.432 |
stealth | -0.412 |
Token | The |
Token ID | 464 |
Feature activation | -5.70e-03 |
Pos logit contributions | |
honour | +0.010 |
xual | +0.010 |
icle | +0.010 |
rogens | +0.010 |
stealth | +0.009 |
Neg logit contributions | |
� | -0.010 |
Rudolph | -0.010 |
steen | -0.009 |
之 | -0.009 |
ahime | -0.009 |
Token | place |
Token ID | 1295 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
� | +0.004 |
Rudolph | +0.004 |
steen | +0.004 |
之 | +0.004 |
ahime | +0.004 |
Neg logit contributions | |
honour | -0.004 |
xual | -0.004 |
rogens | -0.004 |
icle | -0.004 |
stealth | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
honour | +1.674 |
xual | +1.651 |
icle | +1.529 |
rogens | +1.522 |
stealth | +1.447 |
Neg logit contributions | |
� | -1.778 |
Rudolph | -1.751 |
steen | -1.699 |
之 | -1.678 |
ahime | -1.663 |
Token | their |
Token ID | 511 |
Feature activation | -9.93e-02 |
Pos logit contributions | |
� | +0.104 |
Rudolph | +0.104 |
steen | +0.100 |
之 | +0.100 |
ahime | +0.096 |
Neg logit contributions | |
xual | -0.092 |
honour | -0.092 |
rogens | -0.085 |
icle | -0.085 |
stealth | -0.081 |
Token | virginity |
Token ID | 48533 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
� | +0.081 |
Rudolph | +0.081 |
steen | +0.078 |
之 | +0.078 |
ahime | +0.075 |
Neg logit contributions | |
xual | -0.068 |
honour | -0.068 |
rogens | -0.062 |
icle | -0.062 |
stealth | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
honour | +3.691 |
xual | +3.546 |
rogens | +3.320 |
icle | +3.300 |
stealth | +3.194 |
Neg logit contributions | |
� | -3.613 |
Rudolph | -3.469 |
steen | -3.382 |
ahime | -3.318 |
之 | -3.295 |
Token | � |
Token ID | 447 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
honour | +0.105 |
xual | +0.104 |
rogens | +0.096 |
icle | +0.096 |
stealth | +0.092 |
Neg logit contributions | |
� | -0.114 |
Rudolph | -0.112 |
steen | -0.108 |
之 | -0.108 |
ahime | -0.105 |
Token | � |
Token ID | 251 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
� | +0.163 |
Rudolph | +0.162 |
steen | +0.156 |
之 | +0.155 |
ahime | +0.151 |
Neg logit contributions | |
honour | -0.148 |
xual | -0.147 |
rogens | -0.136 |
icle | -0.135 |
stealth | -0.129 |
Token | i |
Token ID | 1312 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
� | +0.244 |
Rudolph | +0.241 |
steen | +0.233 |
之 | +0.231 |
ahime | +0.224 |
Neg logit contributions | |
honour | -0.242 |
xual | -0.240 |
rogens | -0.222 |
icle | -0.222 |
stealth | -0.213 |
Token | . |
Token ID | 13 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
� | +0.005 |
Rudolph | +0.005 |
steen | +0.005 |
之 | +0.005 |
ahime | +0.004 |
Neg logit contributions | |
xual | -0.005 |
honour | -0.005 |
rogens | -0.004 |
icle | -0.004 |
stealth | -0.004 |
Token | guy |
Token ID | 22932 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
xual | +0.372 |
honour | +0.371 |
rogens | +0.345 |
icle | +0.345 |
stealth | +0.329 |
Neg logit contributions | |
� | -0.358 |
Rudolph | -0.355 |
steen | -0.341 |
之 | -0.340 |
ahime | -0.328 |
Token | , |
Token ID | 11 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
xual | +0.094 |
honour | +0.094 |
rogens | +0.086 |
icle | +0.086 |
stealth | +0.081 |
Neg logit contributions | |
� | -0.132 |
Rudolph | -0.131 |
steen | -0.126 |
之 | -0.126 |
ahime | -0.122 |
Token | unconditional |
Token ID | 42423 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
honour | +0.162 |
xual | +0.162 |
rogens | +0.150 |
icle | +0.149 |
stealth | +0.142 |
Neg logit contributions | |
� | -0.183 |
Rudolph | -0.182 |
steen | -0.175 |
之 | -0.175 |
ahime | -0.169 |
Token | - |
Token ID | 12 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
� | +1.189 |
Rudolph | +1.188 |
之 | +1.144 |
steen | +1.143 |
ahime | +1.095 |
Neg logit contributions | |
xual | -1.053 |
honour | -1.023 |
icle | -0.962 |
rogens | -0.962 |
stealth | -0.901 |
Token | l |
Token ID | 75 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
honour | +0.347 |
xual | +0.346 |
rogens | +0.319 |
icle | +0.318 |
stealth | +0.301 |
Neg logit contributions | |
� | -0.427 |
Rudolph | -0.424 |
steen | -0.408 |
之 | -0.408 |
ahime | -0.395 |
Token | oyal |
Token ID | 4815 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
� | +1.159 |
Rudolph | +1.151 |
steen | +1.118 |
之 | +1.115 |
ahime | +1.083 |
Neg logit contributions | |
xual | -0.669 |
honour | -0.663 |
rogens | -0.597 |
icle | -0.596 |
stealth | -0.561 |
Token | ty |
Token ID | 774 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
honour | +3.205 |
xual | +3.048 |
icle | +2.869 |
rogens | +2.807 |
stealth | +2.744 |
Neg logit contributions | |
� | -4.070 |
Rudolph | -3.993 |
steen | -3.841 |
之 | -3.819 |
ahime | -3.731 |
Token | - |
Token ID | 12 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
honour | +0.218 |
xual | +0.217 |
rogens | +0.199 |
icle | +0.199 |
stealth | +0.189 |
Neg logit contributions | |
� | -0.277 |
Rudolph | -0.275 |
steen | -0.265 |
之 | -0.265 |
ahime | -0.256 |
Token | vers |
Token ID | 690 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
honour | +0.526 |
xual | +0.522 |
icle | +0.483 |
rogens | +0.483 |
stealth | +0.458 |
Neg logit contributions | |
� | -0.598 |
Rudolph | -0.594 |
之 | -0.568 |
steen | -0.566 |
ahime | -0.549 |
Token | us |
Token ID | 385 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
� | +0.366 |
Rudolph | +0.364 |
steen | +0.348 |
之 | +0.348 |
ahime | +0.335 |
Neg logit contributions | |
xual | -0.387 |
honour | -0.386 |
icle | -0.359 |
rogens | -0.359 |
stealth | -0.343 |
Token | - |
Token ID | 12 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
� | +0.113 |
Rudolph | +0.112 |
steen | +0.108 |
之 | +0.108 |
ahime | +0.104 |
Neg logit contributions | |
xual | -0.094 |
honour | -0.094 |
rogens | -0.087 |
icle | -0.087 |
stealth | -0.082 |
Token | of |
Token ID | 286 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
honour | +0.409 |
xual | +0.406 |
icle | +0.378 |
rogens | +0.376 |
stealth | +0.360 |
Neg logit contributions | |
� | -0.410 |
Rudolph | -0.406 |
steen | -0.392 |
之 | -0.390 |
ahime | -0.378 |
Token | life |
Token ID | 1204 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
� | +0.097 |
Rudolph | +0.096 |
steen | +0.092 |
之 | +0.092 |
ahime | +0.088 |
Neg logit contributions | |
honour | -0.102 |
xual | -0.102 |
rogens | -0.095 |
icle | -0.095 |
stealth | -0.091 |
Token | – |
Token ID | 784 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
� | +0.197 |
Rudolph | +0.195 |
steen | +0.188 |
之 | +0.187 |
ahime | +0.181 |
Neg logit contributions | |
honour | -0.188 |
xual | -0.186 |
rogens | -0.173 |
icle | -0.173 |
stealth | -0.165 |
Token | beyond |
Token ID | 3675 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
� | +1.182 |
Rudolph | +1.173 |
steen | +1.128 |
之 | +1.127 |
ahime | +1.089 |
Neg logit contributions | |
xual | -1.069 |
honour | -1.069 |
rogens | -0.987 |
icle | -0.985 |
stealth | -0.938 |
Token | the |
Token ID | 262 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
� | +0.253 |
Rudolph | +0.249 |
之 | +0.241 |
steen | +0.241 |
ahime | +0.233 |
Neg logit contributions | |
honour | -0.229 |
xual | -0.227 |
rogens | -0.210 |
icle | -0.210 |
stealth | -0.201 |
Token | plat |
Token ID | 40315 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
� | +0.029 |
Rudolph | +0.028 |
之 | +0.028 |
steen | +0.027 |
ahime | +0.027 |
Neg logit contributions | |
honour | -0.025 |
xual | -0.025 |
icle | -0.023 |
rogens | -0.023 |
stealth | -0.022 |
Token | itudes |
Token ID | 10455 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
Rudolph | +3.640 |
� | +3.569 |
之 | +3.411 |
steen | +3.406 |
ahime | +3.262 |
Neg logit contributions | |
xual | -4.328 |
honour | -4.255 |
rogens | -4.078 |
icle | -3.949 |
stealth | -3.849 |
Token | ? |
Token ID | 30 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
� | +0.271 |
Rudolph | +0.266 |
steen | +0.257 |
之 | +0.257 |
ahime | +0.250 |
Neg logit contributions | |
honour | -0.252 |
xual | -0.250 |
icle | -0.232 |
rogens | -0.231 |
stealth | -0.221 |
Token | I |
Token ID | 314 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
honour | +0.475 |
xual | +0.468 |
icle | +0.432 |
rogens | +0.430 |
stealth | +0.411 |
Neg logit contributions | |
� | -0.558 |
Rudolph | -0.548 |
steen | -0.531 |
之 | -0.531 |
ahime | -0.521 |
Token | am |
Token ID | 716 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
� | +0.266 |
Rudolph | +0.265 |
steen | +0.254 |
之 | +0.254 |
ahime | +0.243 |
Neg logit contributions | |
xual | -0.264 |
honour | -0.260 |
rogens | -0.244 |
icle | -0.243 |
stealth | -0.230 |
Token | certain |
Token ID | 1728 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
honour | +0.579 |
xual | +0.561 |
icle | +0.522 |
rogens | +0.522 |
stealth | +0.504 |
Neg logit contributions | |
� | -0.640 |
Rudolph | -0.628 |
steen | -0.610 |
之 | -0.608 |
ahime | -0.595 |
Token | 11 |
Token ID | 1157 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
honour | +0.112 |
xual | +0.111 |
icle | +0.104 |
rogens | +0.103 |
stealth | +0.098 |
Neg logit contributions | |
� | -0.131 |
Rudolph | -0.130 |
steen | -0.126 |
之 | -0.125 |
ahime | -0.122 |
Token | ) |
Token ID | 8 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
xual | +0.173 |
honour | +0.170 |
rogens | +0.160 |
icle | +0.157 |
stealth | +0.151 |
Neg logit contributions | |
� | -0.182 |
Rudolph | -0.182 |
之 | -0.175 |
steen | -0.175 |
Myr | -0.166 |
Token | When |
Token ID | 1649 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
honour | +0.680 |
xual | +0.670 |
icle | +0.616 |
rogens | +0.613 |
stealth | +0.583 |
Neg logit contributions | |
� | -0.885 |
Rudolph | -0.868 |
steen | -0.847 |
之 | -0.844 |
ahime | -0.826 |
Token | Dancing |
Token ID | 31799 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
honour | +1.314 |
xual | +1.293 |
icle | +1.197 |
rogens | +1.194 |
stealth | +1.149 |
Neg logit contributions | |
� | -1.424 |
Rudolph | -1.384 |
steen | -1.345 |
之 | -1.341 |
ahime | -1.306 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
� | +0.128 |
Rudolph | +0.127 |
steen | +0.123 |
之 | +0.122 |
ahime | +0.118 |
Neg logit contributions | |
honour | -0.116 |
xual | -0.116 |
rogens | -0.107 |
icle | -0.107 |
stealth | -0.101 |
Token | Walt |
Token ID | 18935 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
� | +0.011 |
Rudolph | +0.011 |
steen | +0.011 |
之 | +0.011 |
ahime | +0.011 |
Neg logit contributions | |
honour | -0.010 |
xual | -0.010 |
rogens | -0.009 |
icle | -0.009 |
stealth | -0.009 |
Token | z |
Token ID | 89 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Rudolph | +2.972 |
� | +2.861 |
steen | +2.761 |
之 | +2.728 |
rh | +2.555 |
Neg logit contributions | |
xual | -4.967 |
honour | -4.939 |
rogens | -4.690 |
icle | -4.632 |
stealth | -4.480 |
Token | , |
Token ID | 11 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
� | +1.566 |
Rudolph | +1.557 |
steen | +1.495 |
之 | +1.492 |
ahime | +1.438 |
Neg logit contributions | |
xual | -1.498 |
honour | -1.495 |
rogens | -1.385 |
icle | -1.382 |
stealth | -1.317 |
Token | Mind |
Token ID | 10175 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
� | +0.276 |
Rudolph | +0.273 |
steen | +0.263 |
之 | +0.263 |
ahime | +0.255 |
Neg logit contributions | |
honour | -0.234 |
xual | -0.233 |
rogens | -0.215 |
icle | -0.214 |
stealth | -0.204 |
Token | Your |
Token ID | 3406 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
� | +0.548 |
Rudolph | +0.542 |
之 | +0.523 |
steen | +0.522 |
ahime | +0.505 |
Neg logit contributions | |
honour | -0.463 |
xual | -0.462 |
rogens | -0.425 |
icle | -0.425 |
stealth | -0.404 |
Token | Hands |
Token ID | 22237 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
� | +0.252 |
Rudolph | +0.248 |
steen | +0.239 |
之 | +0.238 |
ahime | +0.231 |
Neg logit contributions | |
honour | -0.246 |
xual | -0.244 |
icle | -0.226 |
rogens | -0.226 |
stealth | -0.216 |
Token | to |
Token ID | 284 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
honour | +0.676 |
xual | +0.665 |
icle | +0.613 |
rogens | +0.611 |
stealth | +0.587 |
Neg logit contributions | |
� | -0.809 |
Rudolph | -0.799 |
之 | -0.768 |
steen | -0.768 |
ahime | -0.761 |
Token | this |
Token ID | 428 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
honour | +0.187 |
xual | +0.185 |
icle | +0.171 |
rogens | +0.170 |
stealth | +0.164 |
Neg logit contributions | |
� | -0.205 |
Rudolph | -0.201 |
之 | -0.194 |
steen | -0.194 |
ahime | -0.190 |
Token | woman |
Token ID | 2415 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
� | +0.432 |
Rudolph | +0.427 |
steen | +0.412 |
之 | +0.411 |
ahime | +0.399 |
Neg logit contributions | |
honour | -0.393 |
xual | -0.391 |
icle | -0.361 |
rogens | -0.361 |
stealth | -0.345 |
Token | with |
Token ID | 351 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
honour | +0.416 |
xual | +0.411 |
icle | +0.382 |
rogens | +0.381 |
stealth | +0.367 |
Neg logit contributions | |
� | -0.405 |
Rudolph | -0.395 |
steen | -0.381 |
之 | -0.377 |
ahime | -0.375 |
Token | sentimental |
Token ID | 46908 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
honour | +0.159 |
xual | +0.157 |
icle | +0.145 |
rogens | +0.144 |
stealth | +0.138 |
Neg logit contributions | |
� | -0.184 |
Rudolph | -0.181 |
steen | -0.175 |
之 | -0.174 |
ahime | -0.170 |
Token | plat |
Token ID | 40315 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
� | +0.455 |
Rudolph | +0.449 |
steen | +0.433 |
之 | +0.431 |
ahime | +0.418 |
Neg logit contributions | |
honour | -0.425 |
xual | -0.424 |
rogens | -0.392 |
icle | -0.392 |
stealth | -0.374 |
Token | itudes |
Token ID | 10455 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
Rudolph | +3.308 |
� | +3.236 |
steen | +3.126 |
之 | +3.104 |
ahime | +2.990 |
Neg logit contributions | |
xual | -3.938 |
honour | -3.922 |
rogens | -3.712 |
icle | -3.665 |
stealth | -3.576 |
Token | , |
Token ID | 11 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
� | +0.305 |
Rudolph | +0.302 |
steen | +0.291 |
之 | +0.290 |
ahime | +0.282 |
Neg logit contributions | |
honour | -0.264 |
xual | -0.264 |
icle | -0.243 |
rogens | -0.242 |
stealth | -0.231 |
Token | Lac |
Token ID | 23115 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
� | +0.162 |
Rudolph | +0.159 |
steen | +0.153 |
之 | +0.153 |
ahime | +0.149 |
Neg logit contributions | |
honour | -0.150 |
xual | -0.149 |
rogens | -0.138 |
icle | -0.137 |
stealth | -0.131 |
Token | an |
Token ID | 272 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
Rudolph | +1.443 |
steen | +1.429 |
� | +1.425 |
之 | +1.380 |
ahime | +1.341 |
Neg logit contributions | |
xual | -1.286 |
honour | -1.256 |
rogens | -1.157 |
icle | -1.134 |
stealth | -1.107 |
Token | � |
Token ID | 447 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
� | +0.035 |
Rudolph | +0.034 |
steen | +0.033 |
之 | +0.033 |
ahime | +0.032 |
Neg logit contributions | |
honour | -0.036 |
xual | -0.036 |
rogens | -0.033 |
icle | -0.033 |
stealth | -0.032 |
Token | simply |
Token ID | 2391 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
� | +0.272 |
Rudolph | +0.269 |
之 | +0.260 |
steen | +0.259 |
ahime | +0.252 |
Neg logit contributions | |
honour | -0.237 |
xual | -0.235 |
icle | -0.218 |
rogens | -0.217 |
stealth | -0.208 |
Token | to |
Token ID | 284 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
� | +0.886 |
Rudolph | +0.876 |
steen | +0.846 |
之 | +0.845 |
ahime | +0.820 |
Neg logit contributions | |
honour | -0.755 |
xual | -0.750 |
icle | -0.692 |
rogens | -0.690 |
stealth | -0.659 |
Token | turn |
Token ID | 1210 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
honour | +0.142 |
xual | +0.139 |
icle | +0.128 |
rogens | +0.128 |
stealth | +0.123 |
Neg logit contributions | |
� | -0.178 |
Rudolph | -0.175 |
之 | -0.170 |
steen | -0.169 |
ahime | -0.165 |
Token | off |
Token ID | 572 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
� | +0.349 |
Rudolph | +0.346 |
steen | +0.334 |
之 | +0.334 |
ahime | +0.324 |
Neg logit contributions | |
honour | -0.270 |
xual | -0.270 |
rogens | -0.247 |
icle | -0.247 |
stealth | -0.234 |
Token | the |
Token ID | 262 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
honour | +1.115 |
xual | +1.082 |
icle | +1.010 |
rogens | +1.008 |
stealth | +0.974 |
Neg logit contributions | |
� | -1.452 |
Rudolph | -1.428 |
steen | -1.396 |
之 | -1.396 |
ahime | -1.367 |
Token | cable |
Token ID | 7862 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
honour | +0.106 |
xual | +0.104 |
icle | +0.097 |
rogens | +0.097 |
stealth | +0.093 |
Neg logit contributions | |
� | -0.113 |
Rudolph | -0.111 |
steen | -0.108 |
之 | -0.108 |
ahime | -0.105 |
Token | news |
Token ID | 1705 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
Rudolph | +3.369 |
� | +3.362 |
之 | +3.204 |
steen | +3.166 |
rh | +3.066 |
Neg logit contributions | |
xual | -3.993 |
honour | -3.871 |
icle | -3.663 |
rogens | -3.660 |
stealth | -3.436 |
Token | shows |
Token ID | 2523 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
honour | +0.416 |
xual | +0.413 |
icle | +0.386 |
rogens | +0.386 |
stealth | +0.367 |
Neg logit contributions | |
� | -0.441 |
Rudolph | -0.439 |
steen | -0.424 |
之 | -0.423 |
ahime | -0.411 |
Token | and |
Token ID | 290 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
� | +0.272 |
Rudolph | +0.268 |
之 | +0.259 |
steen | +0.259 |
ahime | +0.251 |
Neg logit contributions | |
honour | -0.242 |
xual | -0.242 |
icle | -0.224 |
rogens | -0.223 |
stealth | -0.212 |
Token | crack |
Token ID | 8469 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
� | +0.032 |
Rudolph | +0.032 |
之 | +0.031 |
steen | +0.031 |
ahime | +0.030 |
Neg logit contributions | |
honour | -0.028 |
xual | -0.027 |
rogens | -0.025 |
icle | -0.025 |
stealth | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
� | +0.299 |
Rudolph | +0.296 |
之 | +0.286 |
steen | +0.285 |
ahime | +0.276 |
Neg logit contributions | |
honour | -0.246 |
xual | -0.245 |
icle | -0.227 |
rogens | -0.226 |
stealth | -0.216 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
� | +0.278 |
Rudolph | +0.275 |
之 | +0.265 |
steen | +0.265 |
ahime | +0.257 |
Neg logit contributions | |
honour | -0.253 |
xual | -0.252 |
icle | -0.233 |
rogens | -0.233 |
stealth | -0.221 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
� | +0.119 |
Rudolph | +0.118 |
steen | +0.114 |
之 | +0.114 |
ahime | +0.111 |
Neg logit contributions | |
honour | -0.105 |
xual | -0.105 |
icle | -0.097 |
rogens | -0.097 |
stealth | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
xual | +0.087 |
honour | +0.085 |
rogens | +0.080 |
icle | +0.079 |
stealth | +0.075 |
Neg logit contributions | |
� | -0.089 |
Rudolph | -0.088 |
之 | -0.085 |
steen | -0.085 |
Myr | -0.081 |
Token | The |
Token ID | 464 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
honour | +0.138 |
xual | +0.137 |
icle | +0.128 |
rogens | +0.128 |
stealth | +0.121 |
Neg logit contributions | |
� | -0.144 |
Rudolph | -0.143 |
steen | -0.137 |
之 | -0.137 |
ahime | -0.133 |
Token | book |
Token ID | 1492 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
� | +0.105 |
Rudolph | +0.104 |
之 | +0.100 |
steen | +0.100 |
ahime | +0.097 |
Neg logit contributions | |
honour | -0.103 |
xual | -0.103 |
icle | -0.095 |
rogens | -0.095 |
stealth | -0.091 |
Token | Haunted |
Token ID | 43884 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
� | +0.161 |
Rudolph | +0.159 |
之 | +0.153 |
steen | +0.153 |
ahime | +0.148 |
Neg logit contributions | |
xual | -0.157 |
honour | -0.157 |
icle | -0.146 |
rogens | -0.146 |
stealth | -0.139 |
Token | Se |
Token ID | 1001 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
Rudolph | +3.676 |
� | +3.667 |
steen | +3.532 |
之 | +3.486 |
Myr | +3.352 |
Neg logit contributions | |
xual | -3.610 |
honour | -3.576 |
rogens | -3.342 |
icle | -3.281 |
stealth | -3.149 |
Token | gu |
Token ID | 5162 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
� | +0.790 |
Rudolph | +0.789 |
steen | +0.766 |
之 | +0.763 |
ahime | +0.744 |
Neg logit contributions | |
honour | -0.424 |
xual | -0.423 |
rogens | -0.380 |
icle | -0.377 |
stealth | -0.354 |
Token | in |
Token ID | 259 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
xual | +0.851 |
honour | +0.850 |
icle | +0.771 |
rogens | +0.771 |
stealth | +0.713 |
Neg logit contributions | |
� | -1.517 |
Rudolph | -1.498 |
steen | -1.453 |
之 | -1.451 |
ahime | -1.407 |
Token | traces |
Token ID | 20675 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
� | +0.101 |
Rudolph | +0.100 |
之 | +0.096 |
steen | +0.095 |
ahime | +0.092 |
Neg logit contributions | |
honour | -0.103 |
xual | -0.102 |
icle | -0.096 |
rogens | -0.095 |
stealth | -0.091 |
Token | the |
Token ID | 262 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
honour | +0.513 |
xual | +0.509 |
icle | +0.474 |
rogens | +0.471 |
stealth | +0.456 |
Neg logit contributions | |
� | -0.550 |
Rudolph | -0.535 |
steen | -0.524 |
之 | -0.524 |
ahime | -0.507 |
Token | identified |
Token ID | 5174 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
� | +1.309 |
Rudolph | +1.289 |
之 | +1.242 |
steen | +1.242 |
ahime | +1.202 |
Neg logit contributions | |
honour | -1.283 |
xual | -1.278 |
rogens | -1.183 |
icle | -1.183 |
stealth | -1.133 |
Token | as |
Token ID | 355 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
honour | +0.355 |
xual | +0.351 |
rogens | +0.326 |
icle | +0.324 |
stealth | +0.314 |
Neg logit contributions | |
� | -0.384 |
Rudolph | -0.378 |
steen | -0.365 |
之 | -0.364 |
ahime | -0.357 |
Token | Joshua |
Token ID | 20700 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
� | +0.445 |
Rudolph | +0.434 |
之 | +0.421 |
steen | +0.420 |
ahime | +0.410 |
Neg logit contributions | |
honour | -0.455 |
xual | -0.451 |
icle | -0.419 |
rogens | -0.418 |
stealth | -0.403 |
Token | E |
Token ID | 412 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
honour | +0.545 |
xual | +0.538 |
icle | +0.506 |
rogens | +0.502 |
stealth | +0.480 |
Neg logit contributions | |
� | -0.550 |
Rudolph | -0.528 |
之 | -0.521 |
steen | -0.515 |
ahime | -0.505 |
Token | ern |
Token ID | 1142 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
honour | +1.101 |
xual | +1.096 |
icle | +1.030 |
rogens | +1.025 |
stealth | +0.974 |
Neg logit contributions | |
� | -1.107 |
Rudolph | -1.083 |
之 | -1.050 |
steen | -1.025 |
ahime | -1.010 |
Token | isse |
Token ID | 20782 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
� | +1.421 |
Rudolph | +1.412 |
steen | +1.353 |
之 | +1.349 |
ahime | +1.298 |
Neg logit contributions | |
xual | -1.571 |
honour | -1.568 |
rogens | -1.460 |
icle | -1.457 |
stealth | -1.394 |
Token | and |
Token ID | 290 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
Rudolph | +3.734 |
� | +3.674 |
steen | +3.585 |
之 | +3.510 |
Myr | +3.391 |
Neg logit contributions | |
honour | -3.454 |
xual | -3.446 |
rogens | -3.197 |
icle | -3.185 |
stealth | -3.046 |
Token | Beau |
Token ID | 32831 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
honour | +0.014 |
xual | +0.014 |
icle | +0.013 |
rogens | +0.013 |
stealth | +0.012 |
Neg logit contributions | |
� | -0.013 |
Rudolph | -0.012 |
之 | -0.012 |
steen | -0.012 |
ahime | -0.012 |
Token | Sch |
Token ID | 3059 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
� | +1.146 |
Rudolph | +1.134 |
之 | +1.091 |
steen | +1.089 |
ahime | +1.052 |
Neg logit contributions | |
xual | -1.152 |
honour | -1.152 |
rogens | -1.069 |
icle | -1.067 |
stealth | -1.018 |
Token | oen |
Token ID | 6571 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
xual | +0.443 |
honour | +0.443 |
icle | +0.419 |
rogens | +0.416 |
stealth | +0.392 |
Neg logit contributions | |
� | -0.400 |
Rudolph | -0.394 |
之 | -0.379 |
steen | -0.373 |
ahime | -0.362 |
Token | hard |
Token ID | 10424 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
� | +0.348 |
Rudolph | +0.342 |
之 | +0.329 |
steen | +0.326 |
ahime | +0.316 |
Neg logit contributions | |
xual | -0.401 |
honour | -0.400 |
icle | -0.374 |
rogens | -0.373 |
stealth | -0.357 |
Token | his |
Token ID | 465 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
honour | +0.101 |
xual | +0.100 |
rogens | +0.092 |
icle | +0.092 |
stealth | +0.088 |
Neg logit contributions | |
� | -0.122 |
Rudolph | -0.120 |
steen | -0.116 |
之 | -0.116 |
ahime | -0.113 |
Token | gift |
Token ID | 6979 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
� | +0.211 |
Rudolph | +0.209 |
steen | +0.202 |
之 | +0.201 |
ahime | +0.195 |
Neg logit contributions | |
honour | -0.174 |
xual | -0.174 |
rogens | -0.160 |
icle | -0.160 |
stealth | -0.152 |
Token | at |
Token ID | 379 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
� | +0.525 |
Rudolph | +0.522 |
steen | +0.502 |
之 | +0.501 |
ahime | +0.484 |
Neg logit contributions | |
xual | -0.469 |
honour | -0.468 |
rogens | -0.433 |
icle | -0.432 |
stealth | -0.411 |
Token | rhythms |
Token ID | 39804 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
� | +0.406 |
Rudolph | +0.398 |
之 | +0.386 |
steen | +0.386 |
ahime | +0.373 |
Neg logit contributions | |
honour | -0.359 |
xual | -0.355 |
icle | -0.330 |
rogens | -0.329 |
stealth | -0.315 |
Token | and |
Token ID | 290 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
� | +1.732 |
Rudolph | +1.727 |
steen | +1.659 |
之 | +1.656 |
ahime | +1.588 |
Neg logit contributions | |
xual | -1.602 |
honour | -1.598 |
rogens | -1.485 |
icle | -1.472 |
stealth | -1.409 |
Token | rh |
Token ID | 9529 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
� | +0.100 |
Rudolph | +0.099 |
steen | +0.095 |
之 | +0.095 |
ahime | +0.092 |
Neg logit contributions | |
honour | -0.099 |
xual | -0.098 |
rogens | -0.091 |
icle | -0.091 |
stealth | -0.087 |
Token | ymes |
Token ID | 22009 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
� | +2.124 |
Rudolph | +2.114 |
steen | +1.965 |
之 | +1.948 |
rh | +1.820 |
Neg logit contributions | |
xual | -4.981 |
honour | -4.972 |
rogens | -4.707 |
icle | -4.678 |
stealth | -4.568 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
� | +1.429 |
Rudolph | +1.422 |
steen | +1.366 |
之 | +1.365 |
ahime | +1.314 |
Neg logit contributions | |
xual | -1.331 |
honour | -1.329 |
rogens | -1.233 |
icle | -1.227 |
stealth | -1.169 |
Token | When |
Token ID | 1649 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
� | +0.232 |
Rudolph | +0.229 |
steen | +0.221 |
之 | +0.221 |
ahime | +0.215 |
Neg logit contributions | |
honour | -0.202 |
xual | -0.201 |
icle | -0.186 |
rogens | -0.185 |
stealth | -0.176 |
Token | she |
Token ID | 673 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
honour | +1.286 |
xual | +1.270 |
rogens | +1.186 |
icle | +1.186 |
stealth | +1.132 |
Neg logit contributions | |
� | -1.314 |
Rudolph | -1.268 |
之 | -1.237 |
steen | -1.233 |
ahime | -1.210 |
Token | would |
Token ID | 561 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
honour | +0.300 |
xual | +0.298 |
rogens | +0.280 |
icle | +0.279 |
stealth | +0.268 |
Neg logit contributions | |
� | -0.250 |
Rudolph | -0.245 |
之 | -0.235 |
steen | -0.235 |
ahime | -0.228 |
Token |
|
Token ID | 198 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
Rudolph | +0.540 |
� | +0.539 |
之 | +0.519 |
steen | +0.518 |
Myr | +0.497 |
Neg logit contributions | |
xual | -0.562 |
honour | -0.541 |
rogens | -0.513 |
icle | -0.503 |
stealth | -0.482 |
Token | Most |
Token ID | 6943 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
� | +0.459 |
Rudolph | +0.457 |
steen | +0.438 |
之 | +0.436 |
ahime | +0.425 |
Neg logit contributions | |
honour | -0.457 |
xual | -0.453 |
icle | -0.425 |
rogens | -0.423 |
stealth | -0.403 |
Token | GOP |
Token ID | 6796 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
honour | +0.539 |
xual | +0.535 |
icle | +0.498 |
rogens | +0.496 |
stealth | +0.477 |
Neg logit contributions | |
� | -0.555 |
Rudolph | -0.548 |
之 | -0.529 |
steen | -0.528 |
ahime | -0.511 |
Token | lawmakers |
Token ID | 10191 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
honour | +0.359 |
xual | +0.356 |
icle | +0.327 |
rogens | +0.326 |
stealth | +0.311 |
Neg logit contributions | |
� | -0.480 |
Rudolph | -0.475 |
steen | -0.460 |
之 | -0.459 |
ahime | -0.446 |
Token | are |
Token ID | 389 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
� | +0.476 |
Rudolph | +0.475 |
steen | +0.456 |
之 | +0.455 |
ahime | +0.437 |
Neg logit contributions | |
xual | -0.467 |
honour | -0.463 |
rogens | -0.431 |
icle | -0.430 |
stealth | -0.409 |
Token | coales |
Token ID | 46064 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
� | +0.408 |
Rudolph | +0.404 |
之 | +0.389 |
steen | +0.388 |
ahime | +0.376 |
Neg logit contributions | |
honour | -0.377 |
xual | -0.375 |
rogens | -0.348 |
icle | -0.347 |
stealth | -0.332 |
Token | cing |
Token ID | 2259 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
Rudolph | +2.531 |
� | +2.517 |
steen | +2.396 |
之 | +2.373 |
ahime | +2.209 |
Neg logit contributions | |
xual | -4.435 |
honour | -4.416 |
rogens | -4.224 |
icle | -4.173 |
stealth | -4.004 |
Token | around |
Token ID | 1088 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
honour | +0.038 |
xual | +0.037 |
rogens | +0.034 |
icle | +0.034 |
stealth | +0.033 |
Neg logit contributions | |
� | -0.047 |
Rudolph | -0.047 |
之 | -0.045 |
steen | -0.045 |
ahime | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
� | +1.093 |
Rudolph | +1.086 |
steen | +1.044 |
之 | +1.042 |
ahime | +1.006 |
Neg logit contributions | |
xual | -1.001 |
honour | -0.997 |
rogens | -0.924 |
icle | -0.922 |
stealth | -0.876 |
Token | proposal |
Token ID | 6961 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
honour | +0.055 |
xual | +0.055 |
icle | +0.050 |
rogens | +0.050 |
stealth | +0.048 |
Neg logit contributions | |
� | -0.059 |
Rudolph | -0.059 |
steen | -0.056 |
之 | -0.056 |
ahime | -0.054 |
Token | under |
Token ID | 739 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
� | +1.044 |
Rudolph | +1.037 |
steen | +0.996 |
之 | +0.995 |
ahime | +0.960 |
Neg logit contributions | |
xual | -0.979 |
honour | -0.978 |
rogens | -0.905 |
icle | -0.904 |
stealth | -0.861 |
Token | all |
Token ID | 477 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
� | +0.018 |
Rudolph | +0.018 |
steen | +0.018 |
之 | +0.018 |
ahime | +0.017 |
Neg logit contributions | |
xual | -0.016 |
honour | -0.016 |
rogens | -0.015 |
icle | -0.015 |
stealth | -0.014 |
Token | life |
Token ID | 1204 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
� | +0.530 |
Rudolph | +0.527 |
steen | +0.507 |
之 | +0.507 |
ahime | +0.490 |
Neg logit contributions | |
xual | -0.443 |
honour | -0.442 |
rogens | -0.407 |
icle | -0.406 |
stealth | -0.385 |
Token |
|
Token ID | 198 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
honour | +0.060 |
xual | +0.060 |
rogens | +0.056 |
icle | +0.055 |
stealth | +0.053 |
Neg logit contributions | |
� | -0.069 |
Rudolph | -0.068 |
steen | -0.065 |
之 | -0.065 |
ahime | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
xual | +0.335 |
honour | +0.327 |
rogens | +0.307 |
icle | +0.303 |
stealth | +0.289 |
Neg logit contributions | |
Rudolph | -0.341 |
� | -0.340 |
steen | -0.327 |
之 | -0.327 |
Myr | -0.312 |
Token | - |
Token ID | 12 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
honour | +0.388 |
xual | +0.386 |
icle | +0.359 |
rogens | +0.358 |
stealth | +0.342 |
Neg logit contributions | |
� | -0.389 |
Rudolph | -0.388 |
steen | -0.373 |
之 | -0.371 |
ahime | -0.360 |
Token | Haunted |
Token ID | 43884 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
� | +0.086 |
Rudolph | +0.085 |
steen | +0.082 |
之 | +0.082 |
ahime | +0.079 |
Neg logit contributions | |
honour | -0.083 |
xual | -0.082 |
icle | -0.077 |
rogens | -0.076 |
stealth | -0.073 |
Token | , |
Token ID | 11 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
Rudolph | +3.399 |
� | +3.390 |
steen | +3.244 |
之 | +3.243 |
Myr | +3.093 |
Neg logit contributions | |
xual | -3.497 |
honour | -3.492 |
rogens | -3.295 |
icle | -3.257 |
stealth | -3.058 |
Token | Tor |
Token ID | 4022 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
honour | +0.304 |
xual | +0.300 |
icle | +0.279 |
rogens | +0.278 |
stealth | +0.269 |
Neg logit contributions | |
� | -0.305 |
Rudolph | -0.299 |
steen | -0.290 |
之 | -0.289 |
ahime | -0.281 |
Token | mented |
Token ID | 12061 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
� | +0.527 |
Rudolph | +0.518 |
之 | +0.496 |
steen | +0.496 |
ahime | +0.476 |
Neg logit contributions | |
xual | -0.649 |
honour | -0.647 |
icle | -0.608 |
rogens | -0.606 |
stealth | -0.581 |
Token | , |
Token ID | 11 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
xual | +0.052 |
honour | +0.052 |
icle | +0.048 |
rogens | +0.048 |
stealth | +0.045 |
Neg logit contributions | |
� | -0.058 |
Rudolph | -0.058 |
steen | -0.056 |
之 | -0.055 |
ahime | -0.054 |
Token | Difficulty |
Token ID | 27419 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
honour | +0.348 |
xual | +0.343 |
icle | +0.321 |
rogens | +0.319 |
stealth | +0.309 |
Neg logit contributions | |
� | -0.352 |
Rudolph | -0.344 |
steen | -0.336 |
之 | -0.334 |
ahime | -0.326 |
Token | ( |
Token ID | 357 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
� | +0.713 |
Rudolph | +0.705 |
steen | +0.679 |
之 | +0.677 |
ahime | +0.656 |
Neg logit contributions | |
honour | -0.655 |
xual | -0.651 |
icle | -0.603 |
rogens | -0.602 |
stealth | -0.575 |
Token | extremely |
Token ID | 41073 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
honour | +0.254 |
xual | +0.252 |
icle | +0.234 |
rogens | +0.233 |
stealth | +0.222 |
Neg logit contributions | |
� | -0.293 |
Rudolph | -0.291 |
steen | -0.280 |
之 | -0.279 |
ahime | -0.271 |
Token | ), |
Token ID | 828 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
honour | +1.297 |
xual | +1.263 |
icle | +1.160 |
rogens | +1.156 |
stealth | +1.130 |
Neg logit contributions | |
� | -1.545 |
Rudolph | -1.511 |
steen | -1.467 |
之 | -1.456 |
ahime | -1.436 |
Token | while |
Token ID | 981 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
� | +0.488 |
Rudolph | +0.484 |
steen | +0.466 |
之 | +0.465 |
ahime | +0.451 |
Neg logit contributions | |
honour | -0.437 |
xual | -0.436 |
rogens | -0.402 |
icle | -0.402 |
stealth | -0.383 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
honour | +0.934 |
xual | +0.922 |
icle | +0.854 |
rogens | +0.851 |
stealth | +0.818 |
Neg logit contributions | |
� | -1.059 |
Rudolph | -1.040 |
steen | -1.010 |
之 | -1.005 |
ahime | -0.986 |
Token | Apostle |
Token ID | 29748 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
� | +0.144 |
Rudolph | +0.143 |
之 | +0.137 |
steen | +0.137 |
ahime | +0.133 |
Neg logit contributions | |
xual | -0.115 |
honour | -0.114 |
rogens | -0.105 |
icle | -0.105 |
stealth | -0.099 |
Token | of |
Token ID | 286 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
Rudolph | +3.305 |
� | +3.226 |
之 | +3.147 |
steen | +3.088 |
Myr | +2.986 |
Neg logit contributions | |
xual | -3.602 |
honour | -3.459 |
rogens | -3.335 |
icle | -3.296 |
gallery | -3.126 |
Token | Allah |
Token ID | 11475 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
� | +0.250 |
Rudolph | +0.248 |
steen | +0.239 |
之 | +0.239 |
ahime | +0.231 |
Neg logit contributions | |
xual | -0.199 |
honour | -0.199 |
rogens | -0.183 |
icle | -0.182 |
stealth | -0.173 |
Token | ( |
Token ID | 357 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
honour | +0.737 |
xual | +0.720 |
rogens | +0.671 |
icle | +0.670 |
stealth | +0.651 |
Neg logit contributions | |
� | -0.729 |
Rudolph | -0.713 |
steen | -0.692 |
之 | -0.686 |
ahime | -0.670 |
Token | peace |
Token ID | 22988 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
honour | +0.314 |
xual | +0.309 |
icle | +0.291 |
rogens | +0.289 |
stealth | +0.278 |
Neg logit contributions | |
� | -0.307 |
Rudolph | -0.305 |
steen | -0.292 |
之 | -0.291 |
ahime | -0.284 |
Token | be |
Token ID | 307 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
honour | +0.590 |
xual | +0.585 |
icle | +0.544 |
rogens | +0.540 |
stealth | +0.520 |
Neg logit contributions | |
� | -0.579 |
Rudolph | -0.570 |
steen | -0.549 |
之 | -0.548 |
ahime | -0.530 |
Token | in |
Token ID | 287 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
� | +0.871 |
Rudolph | +0.866 |
steen | +0.834 |
之 | +0.833 |
ahime | +0.805 |
Neg logit contributions | |
xual | -0.727 |
honour | -0.726 |
rogens | -0.668 |
icle | -0.667 |
stealth | -0.633 |
Token | blood |
Token ID | 2910 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
honour | +0.030 |
xual | +0.030 |
icle | +0.028 |
rogens | +0.028 |
stealth | +0.027 |
Neg logit contributions | |
� | -0.033 |
Rudolph | -0.033 |
steen | -0.032 |
之 | -0.032 |
ahime | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
honour | +0.107 |
xual | +0.107 |
icle | +0.101 |
rogens | +0.099 |
stealth | +0.096 |
Neg logit contributions | |
� | -0.101 |
Rudolph | -0.099 |
之 | -0.096 |
steen | -0.095 |
ahime | -0.093 |
Token | missing |
Token ID | 4814 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
honour | +0.078 |
xual | +0.078 |
icle | +0.072 |
rogens | +0.072 |
stealth | +0.069 |
Neg logit contributions | |
� | -0.084 |
Rudolph | -0.083 |
steen | -0.080 |
之 | -0.080 |
ahime | -0.078 |
Token | a |
Token ID | 257 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
honour | +0.600 |
xual | +0.592 |
icle | +0.549 |
rogens | +0.545 |
stealth | +0.523 |
Neg logit contributions | |
� | -0.743 |
Rudolph | -0.726 |
steen | -0.712 |
之 | -0.708 |
ahime | -0.688 |
Token | tooth |
Token ID | 16162 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
� | +0.162 |
Rudolph | +0.161 |
steen | +0.155 |
之 | +0.155 |
ahime | +0.150 |
Neg logit contributions | |
xual | -0.129 |
honour | -0.129 |
rogens | -0.118 |
icle | -0.118 |
stealth | -0.112 |
Token | , |
Token ID | 11 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
Rudolph | +3.463 |
� | +3.449 |
steen | +3.327 |
之 | +3.310 |
ahime | +3.176 |
Neg logit contributions | |
xual | -3.405 |
honour | -3.368 |
rogens | -3.156 |
icle | -3.094 |
stealth | -2.956 |
Token | and |
Token ID | 290 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
honour | +0.215 |
xual | +0.213 |
icle | +0.197 |
rogens | +0.196 |
stealth | +0.188 |
Neg logit contributions | |
� | -0.258 |
Rudolph | -0.253 |
steen | -0.246 |
之 | -0.244 |
ahime | -0.239 |
Token | drinking |
Token ID | 7722 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
� | +0.315 |
Rudolph | +0.311 |
steen | +0.301 |
之 | +0.300 |
ahime | +0.291 |
Neg logit contributions | |
honour | -0.288 |
xual | -0.286 |
rogens | -0.266 |
icle | -0.265 |
stealth | -0.253 |
Token | bitterly |
Token ID | 40608 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
honour | +0.089 |
xual | +0.089 |
rogens | +0.082 |
icle | +0.082 |
stealth | +0.079 |
Neg logit contributions | |
� | -0.103 |
Rudolph | -0.102 |
steen | -0.099 |
之 | -0.099 |
ahime | -0.096 |
Token | in |
Token ID | 287 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
� | +0.016 |
Rudolph | +0.016 |
steen | +0.015 |
之 | +0.015 |
ahime | +0.015 |
Neg logit contributions | |
honour | -0.015 |
xual | -0.015 |
rogens | -0.014 |
icle | -0.014 |
stealth | -0.013 |
Token | US |
Token ID | 1294 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
� | +0.125 |
Rudolph | +0.123 |
之 | +0.118 |
steen | +0.118 |
ahime | +0.115 |
Neg logit contributions | |
honour | -0.151 |
xual | -0.148 |
icle | -0.138 |
rogens | -0.137 |
stealth | -0.134 |
Token | , |
Token ID | 11 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
� | +0.719 |
Rudolph | +0.713 |
steen | +0.685 |
之 | +0.684 |
ahime | +0.664 |
Neg logit contributions | |
honour | -0.668 |
xual | -0.664 |
icle | -0.613 |
rogens | -0.613 |
stealth | -0.586 |
Token | where |
Token ID | 810 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
honour | +0.112 |
xual | +0.109 |
icle | +0.101 |
rogens | +0.101 |
stealth | +0.097 |
Neg logit contributions | |
� | -0.121 |
Rudolph | -0.119 |
之 | -0.116 |
steen | -0.115 |
ahime | -0.112 |
Token | 11 |
Token ID | 1367 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
honour | +0.570 |
xual | +0.563 |
icle | +0.518 |
rogens | +0.517 |
stealth | +0.498 |
Neg logit contributions | |
� | -0.647 |
Rudolph | -0.637 |
之 | -0.618 |
steen | -0.616 |
ahime | -0.601 |
Token | b |
Token ID | 275 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
honour | +0.869 |
xual | +0.852 |
icle | +0.798 |
rogens | +0.787 |
stealth | +0.759 |
Neg logit contributions | |
� | -0.949 |
Rudolph | -0.946 |
之 | -0.908 |
steen | -0.900 |
ahime | -0.885 |
Token | idd |
Token ID | 1638 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
honour | +0.071 |
xual | +0.070 |
icle | +0.067 |
rogens | +0.067 |
stealth | +0.065 |
Neg logit contributions | |
� | -0.028 |
Rudolph | -0.028 |
steen | -0.026 |
之 | -0.026 |
ahime | -0.024 |
Token | ers |
Token ID | 364 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
Rudolph | +2.753 |
� | +2.710 |
steen | +2.629 |
之 | +2.585 |
rh | +2.465 |
Neg logit contributions | |
xual | -4.021 |
honour | -3.977 |
icle | -3.745 |
rogens | -3.725 |
stealth | -3.602 |
Token | have |
Token ID | 423 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
honour | +0.477 |
xual | +0.475 |
icle | +0.440 |
rogens | +0.439 |
stealth | +0.419 |
Neg logit contributions | |
� | -0.519 |
Rudolph | -0.514 |
之 | -0.494 |
steen | -0.494 |
ahime | -0.478 |
Token | sent |
Token ID | 1908 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
� | +0.323 |
Rudolph | +0.320 |
steen | +0.307 |
之 | +0.307 |
ahime | +0.296 |
Neg logit contributions | |
honour | -0.335 |
xual | -0.334 |
rogens | -0.311 |
icle | -0.310 |
stealth | -0.297 |
Token | the |
Token ID | 262 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
honour | +0.976 |
xual | +0.965 |
rogens | +0.891 |
icle | +0.890 |
stealth | +0.852 |
Neg logit contributions | |
� | -1.127 |
Rudolph | -1.107 |
之 | -1.075 |
steen | -1.074 |
ahime | -1.044 |
Token | price |
Token ID | 2756 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
� | +0.030 |
Rudolph | +0.030 |
steen | +0.029 |
之 | +0.029 |
ahime | +0.028 |
Neg logit contributions | |
honour | -0.029 |
xual | -0.029 |
icle | -0.027 |
rogens | -0.026 |
stealth | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -5.53e-03 |
Pos logit contributions | |
honour | +0.660 |
xual | +0.652 |
icle | +0.607 |
rogens | +0.604 |
stealth | +0.575 |
Neg logit contributions | |
� | -0.772 |
Rudolph | -0.762 |
steen | -0.735 |
之 | -0.734 |
ahime | -0.712 |
Token | drew |
Token ID | 9859 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
� | +0.004 |
Rudolph | +0.004 |
steen | +0.004 |
之 | +0.004 |
ahime | +0.004 |
Neg logit contributions | |
honour | -0.004 |
xual | -0.004 |
rogens | -0.004 |
icle | -0.004 |
stealth | -0.004 |
Token | just |
Token ID | 655 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
honour | +1.104 |
xual | +1.093 |
rogens | +1.007 |
icle | +1.006 |
stealth | +0.963 |
Neg logit contributions | |
� | -1.330 |
Rudolph | -1.303 |
之 | -1.263 |
steen | -1.263 |
ahime | -1.229 |
Token | eight |
Token ID | 3624 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
� | +0.074 |
Rudolph | +0.073 |
steen | +0.070 |
之 | +0.070 |
ahime | +0.068 |
Neg logit contributions | |
honour | -0.061 |
xual | -0.061 |
rogens | -0.056 |
icle | -0.056 |
stealth | -0.053 |
Token | b |
Token ID | 275 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
honour | +0.432 |
xual | +0.426 |
icle | +0.399 |
rogens | +0.395 |
stealth | +0.380 |
Neg logit contributions | |
� | -0.496 |
Rudolph | -0.486 |
之 | -0.471 |
steen | -0.468 |
ahime | -0.458 |
Token | idd |
Token ID | 1638 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
honour | +0.536 |
xual | +0.532 |
rogens | +0.515 |
icle | +0.515 |
stealth | +0.490 |
Neg logit contributions | |
� | -0.219 |
Rudolph | -0.211 |
之 | -0.197 |
steen | -0.193 |
ahime | -0.185 |
Token | ers |
Token ID | 364 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
Rudolph | +2.647 |
� | +2.569 |
steen | +2.530 |
之 | +2.486 |
rh | +2.374 |
Neg logit contributions | |
xual | -4.088 |
honour | -4.047 |
icle | -3.796 |
rogens | -3.773 |
stealth | -3.649 |
Token | when |
Token ID | 618 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
honour | +0.571 |
xual | +0.569 |
icle | +0.524 |
rogens | +0.522 |
stealth | +0.498 |
Neg logit contributions | |
� | -0.673 |
Rudolph | -0.664 |
之 | -0.641 |
steen | -0.641 |
ahime | -0.623 |
Token | auction |
Token ID | 14389 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
honour | +1.285 |
xual | +1.252 |
icle | +1.174 |
rogens | +1.172 |
stealth | +1.132 |
Neg logit contributions | |
� | -1.474 |
Rudolph | -1.427 |
steen | -1.392 |
之 | -1.392 |
ahime | -1.375 |
Token | ed |
Token ID | 276 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
honour | +0.134 |
xual | +0.134 |
icle | +0.123 |
rogens | +0.123 |
stealth | +0.117 |
Neg logit contributions | |
� | -0.156 |
Rudolph | -0.155 |
steen | -0.149 |
之 | -0.149 |
ahime | -0.145 |
Token | by |
Token ID | 416 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
� | +0.015 |
Rudolph | +0.014 |
steen | +0.014 |
之 | +0.014 |
ahime | +0.014 |
Neg logit contributions | |
honour | -0.011 |
xual | -0.011 |
rogens | -0.010 |
icle | -0.010 |
stealth | -0.010 |
Token | presidential |
Token ID | 4787 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
� | +0.269 |
Rudolph | +0.259 |
steen | +0.253 |
之 | +0.253 |
ahime | +0.244 |
Neg logit contributions | |
honour | -0.304 |
xual | -0.294 |
rogens | -0.280 |
icle | -0.280 |
stealth | -0.273 |
Token | race |
Token ID | 3234 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
� | +1.604 |
Rudolph | +1.588 |
steen | +1.533 |
之 | +1.530 |
ahime | +1.479 |
Neg logit contributions | |
honour | -1.365 |
xual | -1.360 |
rogens | -1.255 |
icle | -1.254 |
stealth | -1.194 |
Token | , |
Token ID | 11 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
� | +0.230 |
Rudolph | +0.225 |
steen | +0.219 |
之 | +0.218 |
ahime | +0.213 |
Neg logit contributions | |
honour | -0.201 |
xual | -0.199 |
icle | -0.184 |
rogens | -0.184 |
stealth | -0.176 |
Token | Republican |
Token ID | 3415 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
� | +0.284 |
Rudolph | +0.278 |
steen | +0.270 |
之 | +0.269 |
ahime | +0.261 |
Neg logit contributions | |
honour | -0.287 |
xual | -0.285 |
rogens | -0.265 |
icle | -0.264 |
stealth | -0.254 |
Token | candidate |
Token ID | 4540 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
� | +0.437 |
Rudolph | +0.420 |
steen | +0.409 |
之 | +0.406 |
ahime | +0.394 |
Neg logit contributions | |
honour | -0.631 |
xual | -0.622 |
rogens | -0.587 |
icle | -0.586 |
stealth | -0.571 |
Token | Mitt |
Token ID | 16627 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
� | +0.383 |
Rudolph | +0.375 |
steen | +0.349 |
之 | +0.348 |
ahime | +0.326 |
Neg logit contributions | |
honour | -1.037 |
xual | -1.036 |
rogens | -0.985 |
icle | -0.984 |
stealth | -0.955 |
Token | Romney |
Token ID | 8431 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Rudolph | +2.413 |
� | +2.267 |
steen | +2.175 |
之 | +2.159 |
Myr | +2.100 |
Neg logit contributions | |
xual | -4.599 |
honour | -4.403 |
rogens | -4.218 |
icle | -4.169 |
stealth | -4.002 |
Token | won |
Token ID | 1839 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
� | +0.819 |
Rudolph | +0.811 |
steen | +0.779 |
之 | +0.778 |
ahime | +0.750 |
Neg logit contributions | |
honour | -0.863 |
xual | -0.862 |
rogens | -0.801 |
icle | -0.801 |
stealth | -0.766 |
Token | just |
Token ID | 655 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
� | +0.756 |
Rudolph | +0.748 |
steen | +0.721 |
之 | +0.720 |
ahime | +0.697 |
Neg logit contributions | |
honour | -0.671 |
xual | -0.670 |
rogens | -0.619 |
icle | -0.617 |
stealth | -0.589 |
Token | 27 |
Token ID | 2681 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
� | +0.440 |
Rudolph | +0.439 |
steen | +0.422 |
之 | +0.422 |
ahime | +0.407 |
Neg logit contributions | |
xual | -0.362 |
honour | -0.358 |
rogens | -0.331 |
icle | -0.330 |
stealth | -0.311 |
Token | % |
Token ID | 4 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
honour | +0.397 |
xual | +0.395 |
icle | +0.360 |
rogens | +0.359 |
stealth | +0.343 |
Neg logit contributions | |
� | -0.550 |
Rudolph | -0.544 |
之 | -0.526 |
steen | -0.525 |
ahime | -0.513 |
Token | here |
Token ID | 994 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
honour | +0.790 |
xual | +0.782 |
rogens | +0.733 |
icle | +0.730 |
stealth | +0.693 |
Neg logit contributions | |
� | -0.915 |
Rudolph | -0.894 |
之 | -0.867 |
steen | -0.866 |
ahime | -0.841 |
Token | is |
Token ID | 318 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
honour | +0.410 |
xual | +0.406 |
rogens | +0.379 |
icle | +0.379 |
stealth | +0.362 |
Neg logit contributions | |
� | -0.444 |
Rudolph | -0.434 |
之 | -0.420 |
steen | -0.419 |
ahime | -0.408 |
Token | the |
Token ID | 262 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
honour | +0.033 |
xual | +0.033 |
icle | +0.030 |
rogens | +0.030 |
stealth | +0.029 |
Neg logit contributions | |
� | -0.037 |
Rudolph | -0.037 |
之 | -0.036 |
steen | -0.036 |
ahime | -0.035 |
Token | fl |
Token ID | 781 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
honour | +0.258 |
xual | +0.255 |
icle | +0.237 |
rogens | +0.236 |
stealth | +0.228 |
Neg logit contributions | |
� | -0.285 |
Rudolph | -0.281 |
steen | -0.272 |
之 | -0.272 |
ahime | -0.263 |
Token | asher |
Token ID | 31218 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
� | +0.162 |
Rudolph | +0.161 |
steen | +0.155 |
之 | +0.155 |
ahime | +0.150 |
Neg logit contributions | |
xual | -0.140 |
honour | -0.140 |
rogens | -0.129 |
icle | -0.129 |
stealth | -0.122 |
Token | cable |
Token ID | 7862 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
� | +0.038 |
Rudolph | +0.038 |
steen | +0.037 |
之 | +0.037 |
ahime | +0.035 |
Neg logit contributions | |
honour | -0.035 |
xual | -0.035 |
icle | -0.032 |
rogens | -0.032 |
stealth | -0.031 |
Token | Alright |
Token ID | 31442 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Rudolph | +3.379 |
� | +3.360 |
steen | +3.242 |
之 | +3.236 |
ahime | +3.141 |
Neg logit contributions | |
xual | -3.411 |
honour | -3.367 |
rogens | -3.154 |
icle | -3.121 |
stealth | -2.961 |
Token | , |
Token ID | 11 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
� | +1.336 |
Rudolph | +1.324 |
steen | +1.274 |
之 | +1.273 |
ahime | +1.231 |
Neg logit contributions | |
honour | -1.190 |
xual | -1.190 |
icle | -1.098 |
rogens | -1.097 |
stealth | -1.045 |
Token | with |
Token ID | 351 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
� | +0.079 |
Rudolph | +0.078 |
steen | +0.075 |
之 | +0.075 |
ahime | +0.073 |
Neg logit contributions | |
honour | -0.069 |
xual | -0.068 |
icle | -0.063 |
rogens | -0.063 |
stealth | -0.061 |
Token | that |
Token ID | 326 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
� | +0.142 |
Rudolph | +0.139 |
之 | +0.135 |
steen | +0.135 |
ahime | +0.130 |
Neg logit contributions | |
honour | -0.126 |
xual | -0.124 |
icle | -0.115 |
rogens | -0.115 |
stealth | -0.111 |
Token | cover |
Token ID | 3002 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
� | +0.047 |
Rudolph | +0.046 |
steen | +0.045 |
之 | +0.044 |
ahime | +0.043 |
Neg logit contributions | |
honour | -0.043 |
xual | -0.042 |
icle | -0.040 |
rogens | -0.039 |
stealth | -0.038 |
Token | argument |
Token ID | 4578 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
� | +0.116 |
Rudolph | +0.115 |
之 | +0.111 |
steen | +0.111 |
ahime | +0.107 |
Neg logit contributions | |
honour | -0.110 |
xual | -0.109 |
icle | -0.101 |
rogens | -0.101 |
stealth | -0.097 |
Token | goes |
Token ID | 2925 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
� | +0.535 |
Rudolph | +0.527 |
steen | +0.508 |
之 | +0.507 |
ahime | +0.500 |
Neg logit contributions | |
honour | -0.543 |
xual | -0.537 |
rogens | -0.501 |
icle | -0.500 |
stealth | -0.482 |
Token | , |
Token ID | 11 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
� | +0.470 |
Rudolph | +0.468 |
steen | +0.449 |
之 | +0.449 |
ahime | +0.431 |
Neg logit contributions | |
xual | -0.437 |
honour | -0.435 |
rogens | -0.404 |
icle | -0.402 |
stealth | -0.382 |
Token | the |
Token ID | 262 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
honour | +0.177 |
xual | +0.174 |
icle | +0.162 |
rogens | +0.161 |
stealth | +0.155 |
Neg logit contributions | |
� | -0.197 |
Rudolph | -0.193 |
steen | -0.188 |
之 | -0.187 |
ahime | -0.183 |
Token | American |
Token ID | 1605 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
� | +0.098 |
Rudolph | +0.097 |
steen | +0.093 |
之 | +0.093 |
ahime | +0.090 |
Neg logit contributions | |
honour | -0.098 |
xual | -0.097 |
icle | -0.090 |
rogens | -0.090 |
stealth | -0.087 |
Token | mainstream |
Token ID | 8661 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
� | +0.562 |
Rudolph | +0.559 |
steen | +0.540 |
之 | +0.540 |
ahime | +0.522 |
Neg logit contributions | |
honour | -0.483 |
xual | -0.478 |
icle | -0.443 |
rogens | -0.437 |
stealth | -0.423 |
Token | will |
Token ID | 481 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
� | +3.119 |
Rudolph | +3.084 |
steen | +2.949 |
之 | +2.947 |
ahime | +2.798 |
Neg logit contributions | |
xual | -3.663 |
honour | -3.632 |
rogens | -3.420 |
icle | -3.386 |
stealth | -3.234 |
Token | love |
Token ID | 1842 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
honour | +0.340 |
xual | +0.333 |
rogens | +0.309 |
icle | +0.308 |
stealth | +0.298 |
Neg logit contributions | |
� | -0.375 |
Rudolph | -0.367 |
之 | -0.356 |
steen | -0.355 |
ahime | -0.346 |
Token | the |
Token ID | 262 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
honour | +0.576 |
xual | +0.567 |
icle | +0.527 |
rogens | +0.525 |
stealth | +0.506 |
Neg logit contributions | |
� | -0.667 |
Rudolph | -0.655 |
之 | -0.637 |
steen | -0.634 |
ahime | -0.619 |
Token | Republican |
Token ID | 3415 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
honour | +0.074 |
xual | +0.072 |
icle | +0.068 |
rogens | +0.067 |
stealth | +0.065 |
Neg logit contributions | |
� | -0.076 |
Rudolph | -0.075 |
之 | -0.072 |
steen | -0.072 |
ahime | -0.070 |
Token | bill |
Token ID | 2855 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
� | +0.724 |
Rudolph | +0.717 |
steen | +0.690 |
之 | +0.688 |
ahime | +0.663 |
Neg logit contributions | |
honour | -0.761 |
xual | -0.756 |
icle | -0.703 |
rogens | -0.702 |
stealth | -0.676 |
Token |
|
Token ID | 198 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
Rudolph | +2.251 |
� | +2.247 |
steen | +2.150 |
之 | +2.146 |
ahime | +2.061 |
Neg logit contributions | |
xual | -2.055 |
honour | -2.049 |
rogens | -1.897 |
icle | -1.890 |
stealth | -1.794 |
Token |
|
Token ID | 198 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
xual | +0.158 |
honour | +0.155 |
rogens | +0.145 |
icle | +0.143 |
stealth | +0.137 |
Neg logit contributions | |
� | -0.162 |
Rudolph | -0.162 |
steen | -0.156 |
之 | -0.156 |
Myr | -0.149 |
Token | I |
Token ID | 40 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
honour | +0.208 |
xual | +0.206 |
icle | +0.194 |
rogens | +0.192 |
stealth | +0.183 |
Neg logit contributions | |
� | -0.230 |
Rudolph | -0.229 |
steen | -0.220 |
之 | -0.219 |
ahime | -0.215 |
Token | smile |
Token ID | 8212 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
Rudolph | +0.642 |
� | +0.639 |
之 | +0.614 |
steen | +0.612 |
Myr | +0.588 |
Neg logit contributions | |
xual | -0.590 |
honour | -0.580 |
rogens | -0.542 |
icle | -0.540 |
stealth | -0.507 |
Token | g |
Token ID | 308 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
� | +0.446 |
Rudolph | +0.443 |
steen | +0.426 |
之 | +0.426 |
ahime | +0.412 |
Neg logit contributions | |
xual | -0.395 |
honour | -0.394 |
rogens | -0.364 |
icle | -0.364 |
stealth | -0.346 |
Token | idd |
Token ID | 1638 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
� | +0.233 |
Rudolph | +0.231 |
steen | +0.220 |
之 | +0.220 |
ahime | +0.210 |
Neg logit contributions | |
xual | -0.302 |
honour | -0.302 |
rogens | -0.282 |
icle | -0.282 |
stealth | -0.271 |
Token | ily |
Token ID | 813 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Rudolph | +4.156 |
� | +4.087 |
steen | +3.989 |
之 | +3.946 |
rh | +3.828 |
Neg logit contributions | |
xual | -2.615 |
honour | -2.600 |
rogens | -2.409 |
icle | -2.258 |
stealth | -2.149 |
Token | as |
Token ID | 355 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
honour | +0.951 |
xual | +0.942 |
icle | +0.872 |
rogens | +0.863 |
stealth | +0.836 |
Neg logit contributions | |
� | -1.104 |
Rudolph | -1.082 |
steen | -1.050 |
之 | -1.047 |
ahime | -1.021 |
Token | I |
Token ID | 314 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
� | +0.241 |
Rudolph | +0.239 |
steen | +0.231 |
之 | +0.230 |
ahime | +0.223 |
Neg logit contributions | |
honour | -0.200 |
xual | -0.200 |
rogens | -0.184 |
icle | -0.184 |
stealth | -0.175 |
Token | cut |
Token ID | 2005 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
xual | +0.020 |
honour | +0.020 |
rogens | +0.018 |
icle | +0.018 |
stealth | +0.017 |
Neg logit contributions | |
� | -0.021 |
Rudolph | -0.021 |
之 | -0.020 |
steen | -0.020 |
ahime | -0.020 |
Token | her |
Token ID | 607 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
Rudolph | +0.990 |
� | +0.986 |
之 | +0.947 |
steen | +0.947 |
Myr | +0.925 |
Neg logit contributions | |
xual | -0.588 |
honour | -0.581 |
rogens | -0.530 |
icle | -0.522 |
stealth | -0.486 |
Token | mouse |
Token ID | 10211 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
� | +0.008 |
Rudolph | +0.008 |
steen | +0.008 |
之 | +0.008 |
ahime | +0.008 |
Neg logit contributions | |
honour | -0.006 |
xual | -0.006 |
icle | -0.005 |
rogens | -0.005 |
stealth | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
honour | +0.719 |
xual | +0.713 |
icle | +0.660 |
rogens | +0.656 |
stealth | +0.628 |
Neg logit contributions | |
� | -0.852 |
Rudolph | -0.835 |
之 | -0.810 |
steen | -0.806 |
ahime | -0.783 |
Token | then |
Token ID | 788 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
� | +0.032 |
Rudolph | +0.032 |
之 | +0.031 |
steen | +0.031 |
ahime | +0.030 |
Neg logit contributions | |
honour | -0.028 |
xual | -0.028 |
rogens | -0.026 |
icle | -0.026 |
stealth | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
� | +0.027 |
Rudolph | +0.026 |
之 | +0.026 |
steen | +0.026 |
ahime | +0.025 |
Neg logit contributions | |
honour | -0.024 |
xual | -0.024 |
rogens | -0.023 |
icle | -0.023 |
stealth | -0.022 |
Token | serial |
Token ID | 11389 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
� | +0.029 |
Rudolph | +0.028 |
steen | +0.027 |
之 | +0.027 |
ahime | +0.027 |
Neg logit contributions | |
honour | -0.021 |
xual | -0.021 |
rogens | -0.019 |
icle | -0.019 |
stealth | -0.018 |
Token | cable |
Token ID | 7862 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
honour | +0.547 |
xual | +0.546 |
icle | +0.515 |
rogens | +0.513 |
stealth | +0.495 |
Neg logit contributions | |
� | -0.362 |
Rudolph | -0.357 |
steen | -0.341 |
之 | -0.340 |
ahime | -0.324 |
Token | , |
Token ID | 11 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
Rudolph | +3.341 |
� | +3.311 |
steen | +3.180 |
之 | +3.174 |
ahime | +3.058 |
Neg logit contributions | |
xual | -3.389 |
honour | -3.339 |
rogens | -3.124 |
icle | -3.115 |
stealth | -2.935 |
Token | the |
Token ID | 262 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
honour | +0.020 |
xual | +0.020 |
rogens | +0.018 |
icle | +0.018 |
stealth | +0.017 |
Neg logit contributions | |
� | -0.024 |
Rudolph | -0.024 |
之 | -0.023 |
steen | -0.023 |
ahime | -0.022 |
Token | parallel |
Token ID | 10730 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
� | +0.201 |
Rudolph | +0.199 |
之 | +0.193 |
steen | +0.193 |
ahime | +0.187 |
Neg logit contributions | |
honour | -0.154 |
xual | -0.153 |
rogens | -0.141 |
icle | -0.141 |
stealth | -0.134 |
Token | cable |
Token ID | 7862 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
� | +0.139 |
Rudolph | +0.137 |
之 | +0.132 |
steen | +0.132 |
ahime | +0.127 |
Neg logit contributions | |
honour | -0.152 |
xual | -0.152 |
icle | -0.142 |
rogens | -0.141 |
stealth | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Rudolph | +3.248 |
� | +3.226 |
之 | +3.096 |
steen | +3.094 |
ahime | +2.980 |
Neg logit contributions | |
xual | -3.149 |
honour | -3.105 |
rogens | -2.896 |
icle | -2.887 |
stealth | -2.722 |
Token | incompetence |
Token ID | 39674 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
� | +0.087 |
Rudolph | +0.086 |
steen | +0.083 |
之 | +0.083 |
ahime | +0.080 |
Neg logit contributions | |
honour | -0.075 |
xual | -0.075 |
rogens | -0.069 |
icle | -0.069 |
stealth | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
� | +0.600 |
Rudolph | +0.595 |
steen | +0.571 |
之 | +0.570 |
ahime | +0.550 |
Neg logit contributions | |
xual | -0.587 |
honour | -0.587 |
icle | -0.544 |
rogens | -0.543 |
stealth | -0.518 |
Token |
|
Token ID | 198 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
honour | +0.008 |
xual | +0.008 |
icle | +0.007 |
rogens | +0.007 |
stealth | +0.007 |
Neg logit contributions | |
� | -0.010 |
Rudolph | -0.009 |
steen | -0.009 |
之 | -0.009 |
ahime | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
xual | +0.267 |
honour | +0.263 |
rogens | +0.245 |
icle | +0.243 |
stealth | +0.232 |
Neg logit contributions | |
� | -0.280 |
Rudolph | -0.279 |
steen | -0.269 |
之 | -0.269 |
ahime | -0.256 |
Token | Republican |
Token ID | 25777 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
honour | +0.225 |
xual | +0.219 |
icle | +0.210 |
rogens | +0.207 |
gallery | +0.197 |
Neg logit contributions | |
� | -0.237 |
Rudolph | -0.237 |
steen | -0.226 |
之 | -0.224 |
ahime | -0.223 |
Token | incumb |
Token ID | 19742 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
� | +0.829 |
Rudolph | +0.819 |
steen | +0.792 |
之 | +0.790 |
ahime | +0.766 |
Neg logit contributions | |
honour | -0.674 |
xual | -0.670 |
icle | -0.618 |
rogens | -0.617 |
stealth | -0.589 |
Token | ents |
Token ID | 658 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
Rudolph | +2.788 |
� | +2.769 |
steen | +2.657 |
之 | +2.614 |
ahime | +2.499 |
Neg logit contributions | |
xual | -3.930 |
honour | -3.882 |
rogens | -3.659 |
icle | -3.638 |
stealth | -3.509 |
Token | are |
Token ID | 389 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
� | +0.588 |
Rudolph | +0.584 |
steen | +0.561 |
之 | +0.561 |
ahime | +0.541 |
Neg logit contributions | |
xual | -0.544 |
honour | -0.543 |
rogens | -0.502 |
icle | -0.501 |
stealth | -0.477 |
Token | sure |
Token ID | 1654 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
� | +0.353 |
Rudolph | +0.348 |
之 | +0.336 |
steen | +0.336 |
ahime | +0.325 |
Neg logit contributions | |
honour | -0.335 |
xual | -0.331 |
rogens | -0.309 |
icle | -0.308 |
stealth | -0.296 |
Token | to |
Token ID | 284 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
honour | +0.279 |
xual | +0.278 |
icle | +0.256 |
rogens | +0.256 |
stealth | +0.243 |
Neg logit contributions | |
� | -0.326 |
Rudolph | -0.322 |
steen | -0.311 |
之 | -0.311 |
ahime | -0.301 |
Token | be |
Token ID | 307 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
honour | +0.079 |
xual | +0.079 |
rogens | +0.073 |
icle | +0.072 |
stealth | +0.069 |
Neg logit contributions | |
� | -0.092 |
Rudolph | -0.091 |
之 | -0.087 |
steen | -0.087 |
ahime | -0.085 |
Token | beginners |
Token ID | 31729 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
� | +0.233 |
Rudolph | +0.231 |
steen | +0.223 |
之 | +0.222 |
ahime | +0.216 |
Neg logit contributions | |
honour | -0.199 |
xual | -0.198 |
icle | -0.183 |
rogens | -0.182 |
stealth | -0.174 |
Token | ( |
Token ID | 357 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
honour | +0.319 |
xual | +0.316 |
icle | +0.292 |
rogens | +0.290 |
stealth | +0.278 |
Neg logit contributions | |
� | -0.372 |
Rudolph | -0.366 |
steen | -0.354 |
之 | -0.351 |
ahime | -0.344 |
Token | according |
Token ID | 38169 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
honour | +0.151 |
xual | +0.150 |
icle | +0.139 |
rogens | +0.139 |
stealth | +0.132 |
Neg logit contributions | |
� | -0.155 |
Rudolph | -0.154 |
steen | -0.148 |
之 | -0.147 |
ahime | -0.142 |
Token | to |
Token ID | 284 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
honour | +0.395 |
xual | +0.393 |
rogens | +0.362 |
icle | +0.361 |
stealth | +0.344 |
Neg logit contributions | |
� | -0.478 |
Rudolph | -0.473 |
steen | -0.457 |
之 | -0.455 |
ahime | -0.444 |
Token | the |
Token ID | 262 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
honour | +0.085 |
xual | +0.084 |
icle | +0.078 |
rogens | +0.078 |
stealth | +0.074 |
Neg logit contributions | |
� | -0.093 |
Rudolph | -0.091 |
steen | -0.089 |
之 | -0.088 |
ahime | -0.086 |
Token | Apostle |
Token ID | 29748 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
� | +0.144 |
Rudolph | +0.142 |
steen | +0.138 |
之 | +0.137 |
ahime | +0.133 |
Neg logit contributions | |
honour | -0.130 |
xual | -0.129 |
icle | -0.119 |
rogens | -0.119 |
stealth | -0.113 |
Token | : |
Token ID | 25 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
Rudolph | +3.292 |
� | +3.209 |
之 | +3.142 |
steen | +3.087 |
Myr | +2.984 |
Neg logit contributions | |
xual | -3.454 |
honour | -3.372 |
rogens | -3.211 |
icle | -3.153 |
stealth | -3.017 |
Token | As |
Token ID | 1081 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
� | +0.702 |
Rudolph | +0.697 |
steen | +0.671 |
之 | +0.670 |
ahime | +0.648 |
Neg logit contributions | |
xual | -0.606 |
honour | -0.606 |
rogens | -0.559 |
icle | -0.558 |
stealth | -0.530 |
Token | unto |
Token ID | 12722 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
� | +0.166 |
Rudolph | +0.165 |
steen | +0.159 |
之 | +0.158 |
ahime | +0.153 |
Neg logit contributions | |
honour | -0.155 |
xual | -0.154 |
icle | -0.143 |
rogens | -0.143 |
stealth | -0.136 |
Token | little |
Token ID | 1310 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
honour | +0.689 |
xual | +0.682 |
rogens | +0.630 |
icle | +0.630 |
stealth | +0.602 |
Neg logit contributions | |
� | -0.779 |
Rudolph | -0.766 |
steen | -0.741 |
之 | -0.738 |
ahime | -0.717 |
Token | ones |
Token ID | 3392 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
� | +0.091 |
Rudolph | +0.091 |
steen | +0.087 |
之 | +0.087 |
ahime | +0.084 |
Neg logit contributions | |
honour | -0.082 |
xual | -0.082 |
rogens | -0.076 |
icle | -0.075 |
stealth | -0.072 |
Token | Irvine |
Token ID | 37277 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
� | +0.300 |
Rudolph | +0.297 |
steen | +0.284 |
之 | +0.283 |
ahime | +0.272 |
Neg logit contributions | |
honour | -0.376 |
xual | -0.375 |
rogens | -0.351 |
icle | -0.351 |
stealth | -0.336 |
Token | , |
Token ID | 11 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
� | +0.330 |
Rudolph | +0.326 |
steen | +0.314 |
之 | +0.314 |
ahime | +0.304 |
Neg logit contributions | |
honour | -0.295 |
xual | -0.294 |
icle | -0.272 |
rogens | -0.271 |
stealth | -0.258 |
Token | California |
Token ID | 3442 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
honour | +0.284 |
xual | +0.281 |
icle | +0.264 |
rogens | +0.262 |
stealth | +0.252 |
Neg logit contributions | |
� | -0.289 |
Rudolph | -0.283 |
steen | -0.276 |
之 | -0.273 |
ahime | -0.267 |
Token | . |
Token ID | 13 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
� | +1.458 |
Rudolph | +1.454 |
steen | +1.394 |
之 | +1.387 |
ahime | +1.325 |
Neg logit contributions | |
xual | -1.582 |
honour | -1.571 |
rogens | -1.468 |
icle | -1.460 |
stealth | -1.398 |
Token | Hide |
Token ID | 10415 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
� | +0.259 |
Rudolph | +0.258 |
之 | +0.250 |
steen | +0.250 |
ahime | +0.243 |
Neg logit contributions | |
xual | -0.124 |
honour | -0.123 |
rogens | -0.110 |
icle | -0.109 |
stealth | -0.101 |
Token | Caption |
Token ID | 11260 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
xual | +0.928 |
honour | +0.922 |
rogens | +0.807 |
icle | +0.803 |
stealth | +0.733 |
Neg logit contributions | |
� | -2.341 |
Rudolph | -2.332 |
steen | -2.265 |
之 | -2.263 |
ahime | -2.205 |
Token | 9 |
Token ID | 860 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
xual | +2.384 |
honour | +2.383 |
rogens | +2.207 |
icle | +2.205 |
stealth | +2.100 |
Neg logit contributions | |
� | -2.487 |
Rudolph | -2.468 |
steen | -2.371 |
之 | -2.368 |
ahime | -2.288 |
Token | of |
Token ID | 286 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Rudolph | +0.516 |
� | +0.513 |
之 | +0.494 |
steen | +0.489 |
Myr | +0.470 |
Neg logit contributions | |
xual | -0.656 |
honour | -0.633 |
rogens | -0.607 |
icle | -0.586 |
stealth | -0.570 |
Token | 15 |
Token ID | 1315 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
xual | +0.109 |
honour | +0.102 |
rogens | +0.099 |
icle | +0.096 |
stealth | +0.090 |
Neg logit contributions | |
Rudolph | -0.129 |
� | -0.126 |
steen | -0.126 |
之 | -0.125 |
Myr | -0.122 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
xual | +0.706 |
honour | +0.695 |
rogens | +0.645 |
icle | +0.638 |
stealth | +0.611 |
Neg logit contributions | |
Rudolph | -0.800 |
� | -0.800 |
steen | -0.769 |
之 | -0.766 |
Myr | -0.734 |
Token | : |
Token ID | 25 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
xual | +1.181 |
honour | +1.156 |
rogens | +1.079 |
icle | +1.062 |
stealth | +1.016 |
Neg logit contributions | |
� | -1.360 |
Rudolph | -1.359 |
之 | -1.308 |
steen | -1.303 |
Myr | -1.251 |
Token | benefit |
Token ID | 4414 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
honour | +0.112 |
xual | +0.110 |
icle | +0.101 |
rogens | +0.101 |
stealth | +0.096 |
Neg logit contributions | |
� | -0.151 |
Rudolph | -0.150 |
steen | -0.145 |
之 | -0.144 |
ahime | -0.140 |
Token | of |
Token ID | 286 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
honour | +1.924 |
xual | +1.892 |
icle | +1.772 |
rogens | +1.756 |
stealth | +1.687 |
Neg logit contributions | |
� | -2.011 |
Rudolph | -1.989 |
steen | -1.916 |
之 | -1.907 |
ahime | -1.862 |
Token | doubt |
Token ID | 4719 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
� | +0.028 |
Rudolph | +0.028 |
steen | +0.027 |
之 | +0.027 |
ahime | +0.026 |
Neg logit contributions | |
xual | -0.027 |
honour | -0.027 |
rogens | -0.025 |
icle | -0.025 |
stealth | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
honour | +1.386 |
xual | +1.363 |
icle | +1.259 |
rogens | +1.252 |
stealth | +1.208 |
Neg logit contributions | |
� | -1.575 |
Rudolph | -1.529 |
steen | -1.485 |
之 | -1.479 |
ahime | -1.442 |
Token | The |
Token ID | 383 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
honour | +0.262 |
xual | +0.259 |
icle | +0.241 |
rogens | +0.239 |
stealth | +0.228 |
Neg logit contributions | |
� | -0.304 |
Rudolph | -0.300 |
之 | -0.290 |
steen | -0.290 |
ahime | -0.282 |
Token | ICC |
Token ID | 32300 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
honour | +0.112 |
xual | +0.111 |
rogens | +0.102 |
icle | +0.102 |
stealth | +0.097 |
Neg logit contributions | |
� | -0.133 |
Rudolph | -0.132 |
之 | -0.127 |
steen | -0.127 |
ahime | -0.123 |
Token | is |
Token ID | 318 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
honour | +2.685 |
xual | +2.615 |
rogens | +2.444 |
icle | +2.418 |
stealth | +2.352 |
Neg logit contributions | |
� | -2.630 |
Rudolph | -2.579 |
之 | -2.507 |
steen | -2.487 |
ahime | -2.417 |
Token | being |
Token ID | 852 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
xual | +0.056 |
honour | +0.056 |
rogens | +0.052 |
icle | +0.052 |
stealth | +0.049 |
Neg logit contributions | |
� | -0.061 |
Rudolph | -0.060 |
steen | -0.058 |
之 | -0.058 |
ahime | -0.056 |
Token | more |
Token ID | 517 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
� | +0.163 |
Rudolph | +0.162 |
steen | +0.156 |
之 | +0.156 |
ahime | +0.151 |
Neg logit contributions | |
xual | -0.132 |
honour | -0.132 |
rogens | -0.121 |
icle | -0.121 |
stealth | -0.115 |
Token | vigilant |
Token ID | 30257 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
honour | +0.174 |
xual | +0.174 |
rogens | +0.160 |
icle | +0.160 |
stealth | +0.152 |
Neg logit contributions | |
� | -0.211 |
Rudolph | -0.210 |
steen | -0.202 |
之 | -0.202 |
ahime | -0.195 |
Token | and |
Token ID | 290 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
honour | +0.365 |
xual | +0.364 |
icle | +0.336 |
rogens | +0.335 |
stealth | +0.320 |
Neg logit contributions | |
� | -0.413 |
Rudolph | -0.408 |
steen | -0.394 |
之 | -0.392 |
ahime | -0.380 |
Token | � |
Token ID | 247 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
� | +0.278 |
Rudolph | +0.276 |
steen | +0.265 |
之 | +0.265 |
ahime | +0.255 |
Neg logit contributions | |
xual | -0.260 |
honour | -0.260 |
rogens | -0.241 |
icle | -0.240 |
stealth | -0.229 |
Token | s |
Token ID | 82 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
� | +0.218 |
Rudolph | +0.216 |
之 | +0.208 |
steen | +0.207 |
ahime | +0.201 |
Neg logit contributions | |
xual | -0.218 |
honour | -0.218 |
icle | -0.202 |
rogens | -0.201 |
stealth | -0.192 |
Token | catastrophic |
Token ID | 22694 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
honour | +0.462 |
xual | +0.459 |
icle | +0.427 |
rogens | +0.425 |
stealth | +0.406 |
Neg logit contributions | |
� | -0.481 |
Rudolph | -0.478 |
之 | -0.461 |
steen | -0.459 |
ahime | -0.445 |
Token | takeover |
Token ID | 27011 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
� | +0.469 |
Rudolph | +0.466 |
steen | +0.449 |
之 | +0.448 |
ahime | +0.433 |
Neg logit contributions | |
xual | -0.412 |
honour | -0.411 |
rogens | -0.379 |
icle | -0.379 |
stealth | -0.360 |
Token | of |
Token ID | 286 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
� | +0.939 |
Rudolph | +0.934 |
steen | +0.895 |
之 | +0.894 |
ahime | +0.860 |
Neg logit contributions | |
xual | -0.940 |
honour | -0.938 |
rogens | -0.873 |
icle | -0.870 |
stealth | -0.829 |
Token | Blackburn |
Token ID | 42603 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
� | +0.209 |
Rudolph | +0.207 |
之 | +0.199 |
steen | +0.198 |
ahime | +0.193 |
Neg logit contributions | |
honour | -0.196 |
xual | -0.193 |
icle | -0.180 |
rogens | -0.179 |
stealth | -0.172 |
Token | Ro |
Token ID | 5564 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
honour | +2.239 |
xual | +2.205 |
icle | +2.016 |
rogens | +2.006 |
stealth | +1.918 |
Neg logit contributions | |
� | -2.570 |
Rudolph | -2.567 |
之 | -2.472 |
steen | -2.440 |
ahime | -2.420 |
Token | vers |
Token ID | 690 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
� | +0.430 |
Rudolph | +0.426 |
之 | +0.406 |
steen | +0.398 |
ahime | +0.393 |
Neg logit contributions | |
honour | -0.447 |
xual | -0.443 |
icle | -0.415 |
rogens | -0.413 |
stealth | -0.394 |
Token | would |
Token ID | 561 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
honour | +0.227 |
xual | +0.227 |
rogens | +0.209 |
icle | +0.209 |
stealth | +0.199 |
Neg logit contributions | |
� | -0.257 |
Rudolph | -0.255 |
之 | -0.246 |
steen | -0.245 |
ahime | -0.238 |
Token | still |
Token ID | 991 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
� | +0.494 |
Rudolph | +0.492 |
steen | +0.472 |
之 | +0.471 |
ahime | +0.453 |
Neg logit contributions | |
xual | -0.479 |
honour | -0.474 |
rogens | -0.444 |
icle | -0.442 |
stealth | -0.419 |
Token | be |
Token ID | 307 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
xual | +0.021 |
honour | +0.021 |
rogens | +0.020 |
icle | +0.020 |
stealth | +0.019 |
Neg logit contributions | |
� | -0.022 |
Rudolph | -0.021 |
steen | -0.021 |
之 | -0.021 |
ahime | -0.020 |
Token | Western |
Token ID | 4885 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
honour | +0.014 |
xual | +0.014 |
rogens | +0.013 |
icle | +0.013 |
stealth | +0.013 |
Neg logit contributions | |
� | -0.015 |
Rudolph | -0.015 |
steen | -0.014 |
之 | -0.014 |
ahime | -0.014 |
Token | tourists |
Token ID | 15930 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
� | +0.980 |
Rudolph | +0.971 |
steen | +0.928 |
之 | +0.927 |
ahime | +0.892 |
Neg logit contributions | |
honour | -1.150 |
xual | -1.149 |
rogens | -1.070 |
icle | -1.069 |
stealth | -1.026 |
Token | are |
Token ID | 389 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
� | +0.150 |
Rudolph | +0.149 |
steen | +0.143 |
之 | +0.143 |
ahime | +0.138 |
Neg logit contributions | |
xual | -0.135 |
honour | -0.134 |
rogens | -0.124 |
icle | -0.124 |
stealth | -0.118 |
Token | not |
Token ID | 407 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
� | +0.251 |
Rudolph | +0.248 |
steen | +0.239 |
之 | +0.239 |
ahime | +0.231 |
Neg logit contributions | |
honour | -0.224 |
xual | -0.223 |
rogens | -0.206 |
icle | -0.205 |
stealth | -0.196 |
Token | arrested |
Token ID | 5169 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
� | +0.167 |
Rudolph | +0.165 |
之 | +0.159 |
steen | +0.159 |
ahime | +0.154 |
Neg logit contributions | |
honour | -0.149 |
xual | -0.148 |
rogens | -0.137 |
icle | -0.137 |
stealth | -0.131 |
Token | randomly |
Token ID | 15456 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
honour | +0.317 |
xual | +0.313 |
icle | +0.290 |
rogens | +0.289 |
stealth | +0.277 |
Neg logit contributions | |
� | -0.378 |
Rudolph | -0.371 |
之 | -0.359 |
steen | -0.359 |
ahime | -0.352 |
Token | in |
Token ID | 287 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
honour | +3.415 |
xual | +3.282 |
icle | +3.064 |
stealth | +2.982 |
rogens | +2.978 |
Neg logit contributions | |
� | -4.422 |
Rudolph | -4.211 |
ahime | -4.166 |
之 | -4.127 |
steen | -4.107 |
Token | North |
Token ID | 2258 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
honour | +0.208 |
xual | +0.207 |
rogens | +0.192 |
icle | +0.192 |
stealth | +0.185 |
Neg logit contributions | |
� | -0.194 |
Rudolph | -0.192 |
steen | -0.185 |
之 | -0.184 |
ahime | -0.178 |
Token | Korea |
Token ID | 4969 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
� | +0.140 |
Rudolph | +0.138 |
steen | +0.132 |
之 | +0.132 |
ahime | +0.126 |
Neg logit contributions | |
honour | -0.184 |
xual | -0.184 |
rogens | -0.172 |
icle | -0.172 |
stealth | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
� | +0.727 |
Rudolph | +0.724 |
steen | +0.696 |
之 | +0.695 |
ahime | +0.669 |
Neg logit contributions | |
xual | -0.684 |
honour | -0.681 |
rogens | -0.633 |
icle | -0.630 |
stealth | -0.599 |
Token | If |
Token ID | 1002 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
honour | +0.090 |
xual | +0.089 |
icle | +0.082 |
rogens | +0.082 |
stealth | +0.078 |
Neg logit contributions | |
� | -0.115 |
Rudolph | -0.113 |
steen | -0.110 |
之 | -0.110 |
ahime | -0.107 |
Token | announces |
Token ID | 26459 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
honour | +0.392 |
xual | +0.391 |
rogens | +0.363 |
icle | +0.362 |
stealth | +0.346 |
Neg logit contributions | |
� | -0.391 |
Rudolph | -0.387 |
steen | -0.372 |
之 | -0.372 |
ahime | -0.359 |
Token | her |
Token ID | 607 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
� | +0.057 |
Rudolph | +0.057 |
steen | +0.055 |
之 | +0.055 |
ahime | +0.053 |
Neg logit contributions | |
honour | -0.056 |
xual | -0.056 |
rogens | -0.052 |
icle | -0.052 |
stealth | -0.050 |
Token | real |
Token ID | 1103 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
� | +0.274 |
Rudolph | +0.272 |
steen | +0.262 |
之 | +0.261 |
ahime | +0.253 |
Neg logit contributions | |
honour | -0.242 |
xual | -0.242 |
rogens | -0.223 |
icle | -0.223 |
stealth | -0.213 |
Token | job |
Token ID | 1693 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
� | +0.488 |
Rudolph | +0.482 |
steen | +0.466 |
之 | +0.464 |
ahime | +0.451 |
Neg logit contributions | |
honour | -0.439 |
xual | -0.435 |
icle | -0.403 |
rogens | -0.402 |
stealth | -0.384 |
Token | : |
Token ID | 25 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
� | +0.442 |
Rudolph | +0.437 |
steen | +0.422 |
之 | +0.421 |
ahime | +0.408 |
Neg logit contributions | |
honour | -0.389 |
xual | -0.386 |
icle | -0.357 |
rogens | -0.356 |
stealth | -0.341 |
Token | keeping |
Token ID | 5291 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
� | +0.142 |
Rudolph | +0.140 |
steen | +0.135 |
之 | +0.135 |
ahime | +0.131 |
Neg logit contributions | |
honour | -0.122 |
xual | -0.122 |
rogens | -0.112 |
icle | -0.112 |
stealth | -0.107 |
Token | him |
Token ID | 683 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
honour | +2.093 |
xual | +2.023 |
icle | +1.884 |
rogens | +1.873 |
stealth | +1.828 |
Neg logit contributions | |
� | -2.730 |
Rudolph | -2.611 |
之 | -2.602 |
steen | -2.595 |
ahime | -2.564 |
Token | from |
Token ID | 422 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
� | +0.472 |
Rudolph | +0.470 |
steen | +0.452 |
之 | +0.452 |
ahime | +0.436 |
Neg logit contributions | |
xual | -0.402 |
honour | -0.400 |
rogens | -0.370 |
icle | -0.369 |
stealth | -0.349 |
Token | going |
Token ID | 1016 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
honour | +0.029 |
xual | +0.029 |
rogens | +0.027 |
icle | +0.027 |
stealth | +0.025 |
Neg logit contributions | |
� | -0.030 |
Rudolph | -0.030 |
steen | -0.029 |
之 | -0.029 |
ahime | -0.028 |
Token | " |
Token ID | 366 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Rudolph | +1.436 |
� | +1.433 |
之 | +1.371 |
steen | +1.368 |
Myr | +1.317 |
Neg logit contributions | |
xual | -1.245 |
honour | -1.228 |
rogens | -1.137 |
icle | -1.136 |
stealth | -1.063 |
Token | king |
Token ID | 3364 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
honour | +0.920 |
xual | +0.919 |
icle | +0.853 |
rogens | +0.852 |
stealth | +0.811 |
Neg logit contributions | |
Rudolph | -1.041 |
� | -1.041 |
之 | -0.996 |
steen | -0.995 |
ahime | -0.965 |
Token | increased |
Token ID | 3220 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
xual | +0.191 |
honour | +0.190 |
rogens | +0.175 |
icle | +0.175 |
stealth | +0.166 |
Neg logit contributions | |
� | -0.235 |
Rudolph | -0.234 |
steen | -0.225 |
之 | -0.225 |
ahime | -0.218 |
Token | by |
Token ID | 416 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
honour | +0.679 |
xual | +0.679 |
rogens | +0.632 |
icle | +0.631 |
stealth | +0.604 |
Neg logit contributions | |
� | -0.615 |
Rudolph | -0.609 |
steen | -0.584 |
之 | -0.583 |
ahime | -0.562 |
Token | nearly |
Token ID | 3016 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
xual | +0.027 |
honour | +0.026 |
rogens | +0.024 |
icle | +0.024 |
stealth | +0.023 |
Neg logit contributions | |
� | -0.032 |
Rudolph | -0.032 |
steen | -0.031 |
之 | -0.030 |
ahime | -0.029 |
Token | 50 |
Token ID | 2026 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
honour | +0.696 |
xual | +0.691 |
icle | +0.636 |
rogens | +0.635 |
stealth | +0.607 |
Neg logit contributions | |
� | -0.857 |
Rudolph | -0.847 |
之 | -0.820 |
steen | -0.819 |
ahime | -0.793 |
Token | %. |
Token ID | 7225 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
� | +0.407 |
Rudolph | +0.406 |
steen | +0.389 |
之 | +0.389 |
ahime | +0.376 |
Neg logit contributions | |
honour | -0.374 |
xual | -0.374 |
icle | -0.346 |
rogens | -0.345 |
stealth | -0.328 |
Token | But |
Token ID | 887 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
� | +0.686 |
Rudolph | +0.678 |
steen | +0.656 |
之 | +0.655 |
ahime | +0.637 |
Neg logit contributions | |
honour | -0.576 |
xual | -0.573 |
icle | -0.529 |
rogens | -0.527 |
stealth | -0.501 |
Token | the |
Token ID | 262 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
honour | +0.562 |
xual | +0.553 |
rogens | +0.514 |
icle | +0.513 |
stealth | +0.492 |
Neg logit contributions | |
� | -0.633 |
Rudolph | -0.615 |
steen | -0.603 |
之 | -0.600 |
ahime | -0.585 |
Token | congestion |
Token ID | 28014 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
honour | +0.140 |
xual | +0.138 |
icle | +0.128 |
rogens | +0.128 |
stealth | +0.123 |
Neg logit contributions | |
� | -0.150 |
Rudolph | -0.148 |
steen | -0.143 |
之 | -0.143 |
ahime | -0.138 |
Token | is |
Token ID | 318 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
honour | +0.557 |
xual | +0.553 |
rogens | +0.515 |
icle | +0.513 |
stealth | +0.492 |
Neg logit contributions | |
� | -0.558 |
Rudolph | -0.550 |
steen | -0.533 |
之 | -0.530 |
ahime | -0.514 |
Token | also |
Token ID | 635 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
� | +0.025 |
Rudolph | +0.024 |
steen | +0.024 |
之 | +0.024 |
ahime | +0.023 |
Neg logit contributions | |
honour | -0.022 |
xual | -0.022 |
rogens | -0.020 |
icle | -0.020 |
stealth | -0.019 |
Token | spreading |
Token ID | 14342 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
honour | +0.215 |
xual | +0.215 |
rogens | +0.199 |
icle | +0.198 |
stealth | +0.189 |
Neg logit contributions | |
� | -0.245 |
Rudolph | -0.243 |
steen | -0.234 |
之 | -0.233 |
ahime | -0.226 |
Token | the |
Token ID | 262 |
Feature activation | +7.85e-02 |
Pos logit contributions | |
honour | +0.150 |
xual | +0.149 |
icle | +0.137 |
rogens | +0.137 |
stealth | +0.132 |
Neg logit contributions | |
� | -0.167 |
Rudolph | -0.164 |
之 | -0.159 |
steen | -0.159 |
ahime | -0.155 |
Token | Republican |
Token ID | 3415 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
honour | +0.058 |
xual | +0.057 |
icle | +0.053 |
rogens | +0.053 |
stealth | +0.051 |
Neg logit contributions | |
� | -0.060 |
Rudolph | -0.059 |
之 | -0.058 |
steen | -0.057 |
ahime | -0.056 |
Token | Party |
Token ID | 3615 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
� | +0.608 |
Rudolph | +0.600 |
之 | +0.581 |
steen | +0.580 |
ahime | +0.561 |
Neg logit contributions | |
honour | -0.486 |
xual | -0.483 |
icle | -0.444 |
rogens | -0.442 |
stealth | -0.424 |
Token | 's |
Token ID | 338 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
honour | +0.180 |
xual | +0.179 |
icle | +0.165 |
rogens | +0.165 |
stealth | +0.158 |
Neg logit contributions | |
� | -0.198 |
Rudolph | -0.194 |
之 | -0.187 |
steen | -0.187 |
ahime | -0.181 |
Token | successful |
Token ID | 4388 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
� | +0.640 |
Rudolph | +0.632 |
之 | +0.611 |
steen | +0.610 |
ahime | +0.590 |
Neg logit contributions | |
honour | -0.557 |
xual | -0.554 |
icle | -0.511 |
rogens | -0.510 |
stealth | -0.488 |
Token | strategy |
Token ID | 4811 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
� | +1.537 |
Rudolph | +1.527 |
steen | +1.467 |
之 | +1.465 |
ahime | +1.414 |
Neg logit contributions | |
xual | -1.435 |
honour | -1.432 |
rogens | -1.326 |
icle | -1.323 |
stealth | -1.259 |
Token | to |
Token ID | 284 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
honour | +0.206 |
xual | +0.206 |
icle | +0.190 |
rogens | +0.189 |
stealth | +0.182 |
Neg logit contributions | |
� | -0.228 |
Rudolph | -0.223 |
之 | -0.215 |
steen | -0.215 |
ahime | -0.207 |
Token | block |
Token ID | 2512 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
� | +0.012 |
Rudolph | +0.012 |
steen | +0.012 |
之 | +0.012 |
ahime | +0.011 |
Neg logit contributions | |
honour | -0.010 |
xual | -0.010 |
rogens | -0.009 |
icle | -0.009 |
stealth | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
honour | +0.302 |
xual | +0.299 |
icle | +0.278 |
rogens | +0.277 |
stealth | +0.265 |
Neg logit contributions | |
� | -0.348 |
Rudolph | -0.343 |
之 | -0.333 |
steen | -0.333 |
ahime | -0.322 |
Token | blame |
Token ID | 8138 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
� | +0.015 |
Rudolph | +0.015 |
steen | +0.014 |
之 | +0.014 |
ahime | +0.014 |
Neg logit contributions | |
xual | -0.011 |
honour | -0.011 |
rogens | -0.010 |
icle | -0.010 |
stealth | -0.009 |
Token | President |
Token ID | 1992 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
� | +0.742 |
Rudolph | +0.736 |
steen | +0.708 |
之 | +0.708 |
ahime | +0.684 |
Neg logit contributions | |
honour | -0.670 |
xual | -0.669 |
rogens | -0.618 |
icle | -0.617 |
stealth | -0.588 |
Token | about |
Token ID | 546 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
� | +0.498 |
Rudolph | +0.496 |
之 | +0.475 |
steen | +0.475 |
ahime | +0.457 |
Neg logit contributions | |
xual | -0.467 |
honour | -0.466 |
rogens | -0.432 |
icle | -0.430 |
stealth | -0.410 |
Token | unseen |
Token ID | 29587 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
� | +0.425 |
Rudolph | +0.422 |
steen | +0.405 |
之 | +0.405 |
ahime | +0.391 |
Neg logit contributions | |
xual | -0.394 |
honour | -0.394 |
rogens | -0.364 |
icle | -0.364 |
stealth | -0.346 |
Token | environments |
Token ID | 12493 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
honour | +1.284 |
xual | +1.249 |
rogens | +1.177 |
icle | +1.174 |
stealth | +1.128 |
Neg logit contributions | |
� | -1.588 |
Rudolph | -1.559 |
steen | -1.513 |
之 | -1.502 |
ahime | -1.480 |
Token | and |
Token ID | 290 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
honour | +0.765 |
xual | +0.762 |
icle | +0.705 |
rogens | +0.704 |
stealth | +0.672 |
Neg logit contributions | |
� | -0.886 |
Rudolph | -0.870 |
steen | -0.842 |
之 | -0.839 |
ahime | -0.818 |
Token | planetary |
Token ID | 27047 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
xual | +0.024 |
honour | +0.024 |
rogens | +0.022 |
icle | +0.022 |
stealth | +0.021 |
Neg logit contributions | |
� | -0.028 |
Rudolph | -0.028 |
steen | -0.027 |
之 | -0.027 |
ahime | -0.026 |
Token | processes |
Token ID | 7767 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
honour | +0.419 |
xual | +0.412 |
icle | +0.385 |
rogens | +0.384 |
stealth | +0.366 |
Neg logit contributions | |
� | -0.501 |
Rudolph | -0.493 |
steen | -0.478 |
之 | -0.477 |
ahime | -0.463 |
Token | . |
Token ID | 13 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
honour | +0.542 |
xual | +0.541 |
rogens | +0.502 |
icle | +0.502 |
stealth | +0.479 |
Neg logit contributions | |
� | -0.580 |
Rudolph | -0.572 |
steen | -0.552 |
之 | -0.550 |
ahime | -0.534 |
Token |
|
Token ID | 198 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
honour | +0.057 |
xual | +0.057 |
rogens | +0.052 |
icle | +0.052 |
stealth | +0.050 |
Neg logit contributions | |
� | -0.066 |
Rudolph | -0.065 |
steen | -0.063 |
之 | -0.063 |
ahime | -0.061 |
Token |
|
Token ID | 198 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
Rudolph | +0.468 |
� | +0.466 |
之 | +0.450 |
steen | +0.450 |
Myr | +0.430 |
Neg logit contributions | |
xual | -0.494 |
honour | -0.476 |
rogens | -0.451 |
icle | -0.442 |
stealth | -0.424 |
Token | " |
Token ID | 1 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
� | +0.450 |
Rudolph | +0.448 |
steen | +0.430 |
之 | +0.428 |
ahime | +0.416 |
Neg logit contributions | |
honour | -0.454 |
xual | -0.450 |
icle | -0.422 |
rogens | -0.421 |
stealth | -0.401 |
Token | This |
Token ID | 1212 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
honour | +0.405 |
xual | +0.396 |
icle | +0.376 |
rogens | +0.373 |
stealth | +0.355 |
Neg logit contributions | |
� | -0.435 |
Rudolph | -0.433 |
steen | -0.417 |
之 | -0.413 |
ahime | -0.408 |
Token | to |
Token ID | 284 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
honour | +0.940 |
xual | +0.935 |
icle | +0.868 |
rogens | +0.864 |
stealth | +0.823 |
Neg logit contributions | |
� | -1.143 |
Rudolph | -1.135 |
steen | -1.094 |
之 | -1.094 |
ahime | -1.063 |
Token | 12 |
Token ID | 1105 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
honour | +0.220 |
xual | +0.219 |
rogens | +0.202 |
icle | +0.202 |
stealth | +0.193 |
Neg logit contributions | |
� | -0.246 |
Rudolph | -0.243 |
之 | -0.235 |
steen | -0.235 |
ahime | -0.227 |
Token | beers |
Token ID | 16800 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
honour | +0.338 |
xual | +0.337 |
icle | +0.314 |
rogens | +0.312 |
stealth | +0.299 |
Neg logit contributions | |
� | -0.366 |
Rudolph | -0.364 |
之 | -0.350 |
steen | -0.350 |
ahime | -0.341 |
Token | . |
Token ID | 13 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
honour | +0.830 |
xual | +0.828 |
icle | +0.769 |
rogens | +0.768 |
stealth | +0.731 |
Neg logit contributions | |
� | -0.947 |
Rudolph | -0.938 |
steen | -0.902 |
之 | -0.902 |
ahime | -0.879 |
Token | 1 |
Token ID | 352 |
Feature activation | +9.86e-02 |
Pos logit contributions | |
honour | +0.413 |
xual | +0.408 |
icle | +0.381 |
rogens | +0.377 |
stealth | +0.358 |
Neg logit contributions | |
� | -0.491 |
Rudolph | -0.486 |
steen | -0.473 |
之 | -0.470 |
ahime | -0.462 |
Token | beer |
Token ID | 6099 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
honour | +0.070 |
xual | +0.070 |
icle | +0.065 |
rogens | +0.064 |
stealth | +0.061 |
Neg logit contributions | |
� | -0.078 |
Rudolph | -0.078 |
之 | -0.075 |
steen | -0.074 |
ahime | -0.072 |
Token | is |
Token ID | 318 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
honour | +0.871 |
xual | +0.867 |
icle | +0.808 |
rogens | +0.804 |
stealth | +0.770 |
Neg logit contributions | |
� | -0.918 |
Rudolph | -0.909 |
steen | -0.876 |
之 | -0.875 |
ahime | -0.848 |
Token | just |
Token ID | 655 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
honour | +0.100 |
xual | +0.099 |
rogens | +0.092 |
icle | +0.092 |
stealth | +0.087 |
Neg logit contributions | |
� | -0.113 |
Rudolph | -0.112 |
steen | -0.108 |
之 | -0.108 |
ahime | -0.104 |
Token | enough |
Token ID | 1576 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
� | +0.093 |
Rudolph | +0.092 |
steen | +0.089 |
之 | +0.089 |
ahime | +0.086 |
Neg logit contributions | |
honour | -0.080 |
xual | -0.080 |
rogens | -0.073 |
icle | -0.073 |
stealth | -0.070 |
Token | that |
Token ID | 326 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
� | +2.529 |
Rudolph | +2.517 |
之 | +2.410 |
steen | +2.410 |
ahime | +2.318 |
Neg logit contributions | |
xual | -2.309 |
honour | -2.288 |
rogens | -2.123 |
icle | -2.116 |
stealth | -2.002 |
Token | you |
Token ID | 345 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
honour | +0.198 |
xual | +0.197 |
rogens | +0.183 |
icle | +0.183 |
stealth | +0.175 |
Neg logit contributions | |
� | -0.224 |
Rudolph | -0.220 |
steen | -0.214 |
之 | -0.213 |
ahime | -0.208 |
Token | reverse |
Token ID | 9575 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
honour | +0.423 |
xual | +0.420 |
icle | +0.390 |
rogens | +0.386 |
stealth | +0.370 |
Neg logit contributions | |
� | -0.512 |
Rudolph | -0.506 |
之 | -0.489 |
steen | -0.487 |
ahime | -0.472 |
Token | while |
Token ID | 981 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
� | +0.866 |
Rudolph | +0.864 |
steen | +0.833 |
之 | +0.829 |
ahime | +0.801 |
Neg logit contributions | |
xual | -0.745 |
honour | -0.741 |
rogens | -0.684 |
icle | -0.680 |
stealth | -0.645 |
Token | on |
Token ID | 319 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
honour | +1.136 |
xual | +1.108 |
icle | +1.041 |
rogens | +1.033 |
stealth | +1.005 |
Neg logit contributions | |
� | -1.382 |
Rudolph | -1.345 |
之 | -1.313 |
steen | -1.297 |
ahime | -1.277 |
Token | the |
Token ID | 262 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
� | +0.454 |
Rudolph | +0.450 |
之 | +0.433 |
steen | +0.433 |
ahime | +0.419 |
Neg logit contributions | |
honour | -0.400 |
xual | -0.399 |
icle | -0.369 |
rogens | -0.369 |
stealth | -0.352 |
Token | highway |
Token ID | 12763 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
� | +0.063 |
Rudolph | +0.062 |
之 | +0.060 |
steen | +0.060 |
ahime | +0.059 |
Neg logit contributions | |
honour | -0.054 |
xual | -0.053 |
icle | -0.049 |
rogens | -0.049 |
stealth | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
� | +0.304 |
Rudolph | +0.300 |
之 | +0.289 |
steen | +0.288 |
ahime | +0.279 |
Neg logit contributions | |
honour | -0.285 |
xual | -0.285 |
icle | -0.265 |
rogens | -0.264 |
stealth | -0.252 |
Token | If |
Token ID | 1532 |
Feature activation | -7.64e-02 |
Pos logit contributions | |
honour | +0.241 |
xual | +0.238 |
icle | +0.223 |
rogens | +0.220 |
stealth | +0.212 |
Neg logit contributions | |
� | -0.270 |
Rudolph | -0.266 |
之 | -0.257 |
steen | -0.256 |
ahime | -0.252 |
Token | after |
Token ID | 706 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
� | +0.063 |
Rudolph | +0.062 |
之 | +0.060 |
steen | +0.060 |
ahime | +0.058 |
Neg logit contributions | |
honour | -0.053 |
xual | -0.052 |
icle | -0.049 |
rogens | -0.048 |
stealth | -0.047 |
Token | all |
Token ID | 477 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
� | +0.446 |
Rudolph | +0.437 |
之 | +0.424 |
steen | +0.421 |
ahime | +0.411 |
Neg logit contributions | |
honour | -0.397 |
xual | -0.393 |
icle | -0.364 |
rogens | -0.363 |
stealth | -0.351 |
Token | that |
Token ID | 326 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
� | +0.812 |
Rudolph | +0.796 |
之 | +0.772 |
steen | +0.769 |
ahime | +0.756 |
Neg logit contributions | |
honour | -0.776 |
xual | -0.763 |
icle | -0.719 |
rogens | -0.711 |
stealth | -0.693 |
Token | , |
Token ID | 11 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
honour | +0.157 |
xual | +0.152 |
icle | +0.144 |
rogens | +0.144 |
stealth | +0.141 |
Neg logit contributions | |
� | -0.167 |
Rudolph | -0.163 |
之 | -0.159 |
steen | -0.158 |
ahime | -0.156 |
Token | had |
Token ID | 550 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
� | +0.250 |
Rudolph | +0.249 |
steen | +0.238 |
之 | +0.238 |
ahime | +0.228 |
Neg logit contributions | |
xual | -0.279 |
honour | -0.278 |
rogens | -0.259 |
icle | -0.259 |
stealth | -0.247 |
Token | a |
Token ID | 257 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
honour | +0.332 |
xual | +0.331 |
rogens | +0.307 |
icle | +0.307 |
stealth | +0.293 |
Neg logit contributions | |
� | -0.335 |
Rudolph | -0.332 |
steen | -0.319 |
之 | -0.319 |
ahime | -0.308 |
Token | meeting |
Token ID | 3249 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
� | +0.038 |
Rudolph | +0.038 |
steen | +0.036 |
之 | +0.036 |
ahime | +0.035 |
Neg logit contributions | |
xual | -0.033 |
honour | -0.033 |
rogens | -0.031 |
icle | -0.030 |
stealth | -0.029 |
Token | scheduled |
Token ID | 7530 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
honour | +0.377 |
xual | +0.375 |
icle | +0.349 |
rogens | +0.348 |
stealth | +0.334 |
Neg logit contributions | |
� | -0.366 |
Rudolph | -0.361 |
steen | -0.348 |
之 | -0.346 |
ahime | -0.337 |
Token | with |
Token ID | 351 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
� | +0.052 |
Rudolph | +0.051 |
steen | +0.049 |
之 | +0.049 |
ahime | +0.048 |
Neg logit contributions | |
honour | -0.050 |
xual | -0.050 |
icle | -0.046 |
rogens | -0.046 |
stealth | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -8.64e-02 |
Pos logit contributions | |
honour | +0.164 |
xual | +0.164 |
rogens | +0.151 |
icle | +0.151 |
stealth | +0.144 |
Neg logit contributions | |
� | -0.191 |
Rudolph | -0.188 |
steen | -0.182 |
之 | -0.182 |
ahime | -0.176 |
Token | FBI |
Token ID | 5349 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
� | +0.066 |
Rudolph | +0.066 |
steen | +0.063 |
之 | +0.063 |
ahime | +0.061 |
Neg logit contributions | |
honour | -0.064 |
xual | -0.063 |
rogens | -0.059 |
icle | -0.059 |
stealth | -0.056 |
Token | for |
Token ID | 329 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
� | +0.675 |
Rudolph | +0.670 |
steen | +0.645 |
之 | +0.644 |
ahime | +0.623 |
Neg logit contributions | |
honour | -0.600 |
xual | -0.600 |
rogens | -0.553 |
icle | -0.553 |
stealth | -0.526 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
� | +0.070 |
Rudolph | +0.070 |
之 | +0.067 |
steen | +0.067 |
ahime | +0.064 |
Neg logit contributions | |
xual | -0.063 |
honour | -0.063 |
rogens | -0.058 |
icle | -0.058 |
stealth | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
� | +0.153 |
Rudolph | +0.151 |
steen | +0.145 |
之 | +0.145 |
ahime | +0.141 |
Neg logit contributions | |
honour | -0.134 |
xual | -0.134 |
rogens | -0.123 |
icle | -0.123 |
stealth | -0.117 |
Token | which |
Token ID | 543 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
� | +0.095 |
Rudolph | +0.094 |
steen | +0.091 |
之 | +0.091 |
ahime | +0.088 |
Neg logit contributions | |
honour | -0.084 |
xual | -0.084 |
rogens | -0.078 |
icle | -0.077 |
stealth | -0.074 |
Token | going |
Token ID | 1016 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
� | +0.209 |
Rudolph | +0.207 |
steen | +0.198 |
之 | +0.198 |
ahime | +0.191 |
Neg logit contributions | |
honour | -0.221 |
xual | -0.221 |
icle | -0.206 |
rogens | -0.205 |
stealth | -0.197 |
Token | to |
Token ID | 284 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
� | +1.175 |
Rudolph | +1.166 |
steen | +1.118 |
之 | +1.118 |
ahime | +1.073 |
Neg logit contributions | |
xual | -1.048 |
honour | -1.040 |
rogens | -0.965 |
icle | -0.961 |
stealth | -0.908 |
Token | cost |
Token ID | 1575 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
honour | +0.220 |
xual | +0.219 |
icle | +0.202 |
rogens | +0.202 |
stealth | +0.193 |
Neg logit contributions | |
� | -0.253 |
Rudolph | -0.250 |
之 | -0.241 |
steen | -0.241 |
ahime | -0.234 |
Token | anywhere |
Token ID | 6609 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
honour | +0.625 |
xual | +0.620 |
rogens | +0.573 |
icle | +0.571 |
stealth | +0.552 |
Neg logit contributions | |
� | -0.716 |
Rudolph | -0.704 |
之 | -0.683 |
steen | -0.682 |
ahime | -0.662 |
Token | near |
Token ID | 1474 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
honour | +0.565 |
xual | +0.555 |
icle | +0.514 |
rogens | +0.510 |
stealth | +0.489 |
Neg logit contributions | |
� | -0.745 |
Rudolph | -0.737 |
steen | -0.715 |
之 | -0.711 |
ahime | -0.698 |
Token | that |
Token ID | 326 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
honour | +1.219 |
xual | +1.199 |
rogens | +1.116 |
icle | +1.113 |
stealth | +1.085 |
Neg logit contributions | |
� | -1.216 |
Rudolph | -1.188 |
之 | -1.150 |
steen | -1.144 |
ahime | -1.119 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
honour | +0.076 |
xual | +0.076 |
icle | +0.070 |
rogens | +0.070 |
stealth | +0.067 |
Neg logit contributions | |
� | -0.080 |
Rudolph | -0.079 |
steen | -0.076 |
之 | -0.076 |
ahime | -0.073 |
Token | The |
Token ID | 383 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
honour | +0.175 |
xual | +0.175 |
icle | +0.162 |
rogens | +0.161 |
stealth | +0.153 |
Neg logit contributions | |
� | -0.194 |
Rudolph | -0.193 |
steen | -0.186 |
之 | -0.186 |
ahime | -0.182 |
Token | Democrats |
Token ID | 4956 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
honour | +0.022 |
xual | +0.022 |
icle | +0.020 |
rogens | +0.020 |
stealth | +0.019 |
Neg logit contributions | |
� | -0.025 |
Rudolph | -0.025 |
之 | -0.024 |
steen | -0.024 |
ahime | -0.023 |
Token | are |
Token ID | 389 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
� | +0.160 |
Rudolph | +0.158 |
之 | +0.153 |
steen | +0.152 |
ahime | +0.147 |
Neg logit contributions | |
honour | -0.145 |
xual | -0.144 |
rogens | -0.133 |
icle | -0.133 |
stealth | -0.127 |
Token | saying |
Token ID | 2282 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
� | +0.342 |
Rudolph | +0.338 |
之 | +0.323 |
steen | +0.322 |
ahime | +0.310 |
Neg logit contributions | |
honour | -0.450 |
xual | -0.448 |
rogens | -0.420 |
icle | -0.420 |
stealth | -0.405 |
Token | his |
Token ID | 465 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
honour | +0.614 |
xual | +0.602 |
icle | +0.569 |
rogens | +0.563 |
stealth | +0.545 |
Neg logit contributions | |
� | -0.611 |
Rudolph | -0.595 |
steen | -0.580 |
之 | -0.579 |
ahime | -0.565 |
Token | finances |
Token ID | 20903 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
� | +0.467 |
Rudolph | +0.462 |
steen | +0.445 |
之 | +0.444 |
ahime | +0.430 |
Neg logit contributions | |
honour | -0.458 |
xual | -0.454 |
icle | -0.423 |
rogens | -0.422 |
stealth | -0.404 |
Token | President |
Token ID | 1992 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
� | +0.211 |
Rudolph | +0.208 |
之 | +0.201 |
steen | +0.200 |
ahime | +0.195 |
Neg logit contributions | |
honour | -0.185 |
xual | -0.184 |
icle | -0.171 |
rogens | -0.170 |
stealth | -0.162 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
� | +0.921 |
Rudolph | +0.906 |
steen | +0.863 |
之 | +0.862 |
ahime | +0.830 |
Neg logit contributions | |
honour | -1.364 |
xual | -1.361 |
rogens | -1.278 |
icle | -1.277 |
stealth | -1.231 |
Token | warned |
Token ID | 7728 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
� | +1.150 |
Rudolph | +1.139 |
steen | +1.091 |
之 | +1.090 |
ahime | +1.051 |
Neg logit contributions | |
honour | -1.270 |
xual | -1.270 |
rogens | -1.182 |
icle | -1.181 |
stealth | -1.130 |
Token | the |
Token ID | 262 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
� | +1.333 |
Rudolph | +1.329 |
steen | +1.273 |
之 | +1.273 |
ahime | +1.225 |
Neg logit contributions | |
xual | -1.241 |
honour | -1.235 |
rogens | -1.145 |
icle | -1.142 |
stealth | -1.086 |
Token | special |
Token ID | 2041 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
� | +0.345 |
Rudolph | +0.338 |
之 | +0.328 |
steen | +0.327 |
ahime | +0.317 |
Neg logit contributions | |
honour | -0.343 |
xual | -0.339 |
icle | -0.317 |
rogens | -0.316 |
stealth | -0.304 |
Token | counsel |
Token ID | 7739 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
honour | +0.678 |
xual | +0.674 |
icle | +0.616 |
rogens | +0.615 |
stealth | +0.581 |
Neg logit contributions | |
� | -0.992 |
Rudolph | -0.982 |
steen | -0.951 |
之 | -0.949 |
ahime | -0.924 |
Token | investigating |
Token ID | 10240 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
honour | +2.012 |
xual | +1.968 |
icle | +1.862 |
rogens | +1.829 |
stealth | +1.753 |
Neg logit contributions | |
� | -2.203 |
Rudolph | -2.094 |
steen | -2.074 |
之 | -2.063 |
ahime | -2.042 |
Token | Russia |
Token ID | 3284 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
honour | +0.330 |
xual | +0.324 |
icle | +0.304 |
rogens | +0.302 |
stealth | +0.290 |
Neg logit contributions | |
� | -0.360 |
Rudolph | -0.349 |
steen | -0.343 |
之 | -0.339 |
ahime | -0.333 |
Token | not |
Token ID | 407 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
� | +0.492 |
Rudolph | +0.488 |
steen | +0.468 |
之 | +0.467 |
ahime | +0.450 |
Neg logit contributions | |
xual | -0.528 |
honour | -0.528 |
rogens | -0.491 |
icle | -0.491 |
stealth | -0.469 |
Token | Let |
Token ID | 3914 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
� | +0.725 |
Rudolph | +0.715 |
steen | +0.692 |
之 | +0.692 |
ahime | +0.672 |
Neg logit contributions | |
honour | -0.637 |
xual | -0.632 |
icle | -0.587 |
rogens | -0.584 |
stealth | -0.557 |
Token | � |
Token ID | 447 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
� | +0.247 |
Rudolph | +0.244 |
steen | +0.234 |
之 | +0.233 |
ahime | +0.227 |
Neg logit contributions | |
honour | -0.274 |
xual | -0.274 |
rogens | -0.255 |
icle | -0.255 |
stealth | -0.244 |
Token | � |
Token ID | 247 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
xual | +0.175 |
honour | +0.175 |
rogens | +0.164 |
icle | +0.164 |
stealth | +0.158 |
Neg logit contributions | |
� | -0.112 |
Rudolph | -0.111 |
steen | -0.106 |
之 | -0.106 |
ahime | -0.101 |
Token | s |
Token ID | 82 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
xual | +0.055 |
honour | +0.055 |
rogens | +0.052 |
icle | +0.052 |
stealth | +0.050 |
Neg logit contributions | |
� | -0.040 |
Rudolph | -0.040 |
steen | -0.038 |
之 | -0.038 |
ahime | -0.037 |
Token | give |
Token ID | 1577 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
honour | +0.430 |
xual | +0.429 |
rogens | +0.393 |
icle | +0.392 |
stealth | +0.372 |
Neg logit contributions | |
� | -0.567 |
Rudolph | -0.563 |
steen | -0.543 |
之 | -0.542 |
ahime | -0.526 |
Token | Trump |
Token ID | 1301 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
honour | +1.150 |
xual | +1.125 |
icle | +1.045 |
rogens | +1.041 |
stealth | +1.010 |
Neg logit contributions | |
� | -1.304 |
Rudolph | -1.268 |
之 | -1.242 |
steen | -1.239 |
ahime | -1.208 |
Token | the |
Token ID | 262 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
� | +0.478 |
Rudolph | +0.474 |
steen | +0.456 |
之 | +0.455 |
ahime | +0.442 |
Neg logit contributions | |
honour | -0.430 |
xual | -0.428 |
icle | -0.398 |
rogens | -0.396 |
stealth | -0.378 |
Token | benefit |
Token ID | 4414 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
honour | +0.205 |
xual | +0.201 |
icle | +0.186 |
rogens | +0.185 |
stealth | +0.178 |
Neg logit contributions | |
� | -0.268 |
Rudolph | -0.264 |
steen | -0.256 |
之 | -0.255 |
ahime | -0.248 |
Token | of |
Token ID | 286 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
honour | +1.624 |
xual | +1.608 |
icle | +1.515 |
rogens | +1.498 |
stealth | +1.430 |
Neg logit contributions | |
� | -1.706 |
Rudolph | -1.695 |
steen | -1.634 |
之 | -1.621 |
ahime | -1.593 |
Token | the |
Token ID | 262 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
honour | +0.113 |
xual | +0.113 |
rogens | +0.104 |
icle | +0.104 |
stealth | +0.100 |
Neg logit contributions | |
� | -0.120 |
Rudolph | -0.119 |
之 | -0.114 |
steen | -0.114 |
ahime | -0.110 |
Token | doubt |
Token ID | 4719 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
honour | +0.262 |
xual | +0.261 |
rogens | +0.234 |
icle | +0.233 |
stealth | +0.217 |
Neg logit contributions | |
� | -0.525 |
Rudolph | -0.522 |
steen | -0.506 |
之 | -0.505 |
ahime | -0.493 |
Token | or |
Token ID | 393 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
xual | +0.287 |
honour | +0.287 |
icle | +0.264 |
rogens | +0.264 |
stealth | +0.252 |
Neg logit contributions | |
� | -0.330 |
Rudolph | -0.328 |
之 | -0.316 |
steen | -0.316 |
ahime | -0.305 |
Token | if |
Token ID | 611 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
honour | +0.157 |
xual | +0.156 |
icle | +0.146 |
rogens | +0.145 |
stealth | +0.140 |
Neg logit contributions | |
� | -0.153 |
Rudolph | -0.152 |
steen | -0.146 |
之 | -0.146 |
ahime | -0.141 |
Token | we |
Token ID | 356 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
honour | +0.391 |
xual | +0.389 |
icle | +0.356 |
rogens | +0.355 |
stealth | +0.339 |
Neg logit contributions | |
� | -0.532 |
Rudolph | -0.528 |
steen | -0.511 |
之 | -0.510 |
ahime | -0.496 |
Token | didn |
Token ID | 1422 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
honour | +0.655 |
xual | +0.652 |
icle | +0.608 |
rogens | +0.608 |
stealth | +0.583 |
Neg logit contributions | |
� | -0.607 |
Rudolph | -0.603 |
steen | -0.577 |
之 | -0.576 |
ahime | -0.556 |
Token | � |
Token ID | 447 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
xual | +0.180 |
honour | +0.178 |
rogens | +0.166 |
icle | +0.165 |
stealth | +0.158 |
Neg logit contributions | |
� | -0.176 |
Rudolph | -0.173 |
之 | -0.167 |
steen | -0.167 |
ahime | -0.159 |
Token | � |
Token ID | 247 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
xual | +0.058 |
honour | +0.058 |
rogens | +0.054 |
icle | +0.054 |
stealth | +0.052 |
Neg logit contributions | |
� | -0.037 |
Rudolph | -0.037 |
steen | -0.035 |
之 | -0.035 |
ahime | -0.033 |
Token | t |
Token ID | 83 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
� | +0.238 |
Rudolph | +0.234 |
之 | +0.225 |
steen | +0.224 |
ahime | +0.217 |
Neg logit contributions | |
xual | -0.236 |
honour | -0.235 |
icle | -0.218 |
rogens | -0.216 |
stealth | -0.207 |
Token | work |
Token ID | 670 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
honour | +0.172 |
xual | +0.170 |
rogens | +0.157 |
icle | +0.157 |
stealth | +0.150 |
Neg logit contributions | |
� | -0.194 |
Rudolph | -0.193 |
之 | -0.186 |
steen | -0.185 |
ahime | -0.180 |
Token | hard |
Token ID | 1327 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
honour | +1.000 |
xual | +0.986 |
icle | +0.908 |
rogens | +0.899 |
stealth | +0.862 |
Neg logit contributions | |
� | -1.449 |
Rudolph | -1.439 |
steen | -1.396 |
之 | -1.394 |
ahime | -1.356 |
Token | , |
Token ID | 11 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
xual | +0.016 |
honour | +0.016 |
icle | +0.014 |
rogens | +0.014 |
stealth | +0.014 |
Neg logit contributions | |
� | -0.018 |
Rudolph | -0.018 |
steen | -0.018 |
之 | -0.018 |
ahime | -0.017 |
Token | we |
Token ID | 356 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
honour | +0.158 |
xual | +0.158 |
rogens | +0.145 |
icle | +0.145 |
stealth | +0.138 |
Neg logit contributions | |
� | -0.197 |
Rudolph | -0.196 |
steen | -0.189 |
之 | -0.189 |
ahime | -0.183 |
Token | treacher |
Token ID | 32550 |
Feature activation | -9.16e-03 |
Pos logit contributions | |
� | +0.121 |
Rudolph | +0.120 |
steen | +0.116 |
之 | +0.116 |
ahime | +0.112 |
Neg logit contributions | |
honour | -0.098 |
xual | -0.097 |
rogens | -0.090 |
icle | -0.089 |
stealth | -0.085 |
Token | y |
Token ID | 88 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
� | +0.008 |
Rudolph | +0.007 |
之 | +0.007 |
steen | +0.007 |
ahime | +0.007 |
Neg logit contributions | |
honour | -0.006 |
xual | -0.006 |
icle | -0.006 |
rogens | -0.006 |
stealth | -0.005 |
Token | : |
Token ID | 25 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
honour | +0.039 |
xual | +0.039 |
rogens | +0.036 |
icle | +0.036 |
stealth | +0.034 |
Neg logit contributions | |
� | -0.041 |
Rudolph | -0.041 |
steen | -0.039 |
之 | -0.039 |
ahime | -0.038 |
Token | When |
Token ID | 1649 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
� | +0.101 |
Rudolph | +0.100 |
steen | +0.097 |
之 | +0.096 |
ahime | +0.094 |
Neg logit contributions | |
honour | -0.089 |
xual | -0.088 |
rogens | -0.082 |
icle | -0.082 |
stealth | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
honour | +1.148 |
xual | +1.127 |
icle | +1.050 |
rogens | +1.045 |
stealth | +1.009 |
Neg logit contributions | |
� | -1.288 |
Rudolph | -1.264 |
steen | -1.228 |
之 | -1.222 |
ahime | -1.191 |
Token | Lord |
Token ID | 4453 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
� | +0.227 |
Rudolph | +0.225 |
steen | +0.216 |
之 | +0.216 |
ahime | +0.209 |
Neg logit contributions | |
xual | -0.200 |
honour | -0.199 |
rogens | -0.184 |
icle | -0.183 |
stealth | -0.174 |
Token | thy |
Token ID | 11906 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
Rudolph | +2.109 |
� | +2.079 |
之 | +2.001 |
steen | +1.992 |
Myr | +1.909 |
Neg logit contributions | |
xual | -2.181 |
honour | -2.119 |
rogens | -2.003 |
icle | -1.993 |
gallery | -1.887 |
Token | God |
Token ID | 1793 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Rudolph | +0.524 |
� | +0.520 |
steen | +0.503 |
之 | +0.501 |
ahime | +0.477 |
Neg logit contributions | |
xual | -0.575 |
honour | -0.563 |
rogens | -0.533 |
icle | -0.532 |
stealth | -0.503 |
Token | hath |
Token ID | 22027 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
Rudolph | +1.130 |
� | +1.124 |
之 | +1.084 |
steen | +1.078 |
ahime | +1.039 |
Neg logit contributions | |
xual | -1.114 |
honour | -1.096 |
rogens | -1.027 |
icle | -1.022 |
stealth | -0.965 |
Token | delivered |
Token ID | 6793 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Rudolph | +0.472 |
� | +0.470 |
之 | +0.453 |
steen | +0.450 |
ahime | +0.436 |
Neg logit contributions | |
xual | -0.414 |
honour | -0.405 |
rogens | -0.380 |
icle | -0.378 |
stealth | -0.354 |
Token | it |
Token ID | 340 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
xual | +0.154 |
honour | +0.152 |
rogens | +0.141 |
icle | +0.140 |
stealth | +0.132 |
Neg logit contributions | |
� | -0.187 |
Rudolph | -0.187 |
之 | -0.180 |
steen | -0.180 |
ahime | -0.173 |
Token | only |
Token ID | 691 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
� | +0.195 |
Rudolph | +0.193 |
steen | +0.187 |
之 | +0.186 |
ahime | +0.181 |
Neg logit contributions | |
honour | -0.158 |
xual | -0.157 |
rogens | -0.144 |
icle | -0.144 |
stealth | -0.138 |
Token | his |
Token ID | 465 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
� | +1.896 |
Rudolph | +1.887 |
steen | +1.813 |
之 | +1.813 |
ahime | +1.748 |
Neg logit contributions | |
xual | -1.622 |
honour | -1.617 |
rogens | -1.493 |
icle | -1.490 |
stealth | -1.411 |
Token | trousers |
Token ID | 37191 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
� | +0.389 |
Rudolph | +0.383 |
steen | +0.371 |
之 | +0.369 |
ahime | +0.359 |
Neg logit contributions | |
honour | -0.334 |
xual | -0.330 |
icle | -0.306 |
rogens | -0.305 |
stealth | -0.293 |
Token | , |
Token ID | 11 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
� | +1.142 |
Rudolph | +1.129 |
steen | +1.088 |
之 | +1.084 |
ahime | +1.050 |
Neg logit contributions | |
honour | -1.024 |
xual | -1.021 |
rogens | -0.942 |
icle | -0.941 |
stealth | -0.900 |
Token | and |
Token ID | 290 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
� | +0.054 |
Rudolph | +0.053 |
steen | +0.052 |
之 | +0.051 |
ahime | +0.050 |
Neg logit contributions | |
honour | -0.048 |
xual | -0.047 |
icle | -0.043 |
rogens | -0.043 |
stealth | -0.042 |
Token | spread |
Token ID | 4104 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
� | +0.411 |
Rudolph | +0.405 |
steen | +0.392 |
之 | +0.389 |
ahime | +0.381 |
Neg logit contributions | |
honour | -0.376 |
xual | -0.371 |
rogens | -0.346 |
icle | -0.344 |
stealth | -0.332 |
Token | them |
Token ID | 606 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
� | +2.770 |
Rudolph | +2.765 |
之 | +2.653 |
steen | +2.647 |
ahime | +2.550 |
Neg logit contributions | |
xual | -2.307 |
honour | -2.288 |
rogens | -2.121 |
icle | -2.105 |
stealth | -1.986 |
Token | near |
Token ID | 1474 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
� | +0.820 |
Rudolph | +0.811 |
steen | +0.784 |
之 | +0.782 |
ahime | +0.760 |
Neg logit contributions | |
honour | -0.657 |
xual | -0.653 |
icle | -0.601 |
rogens | -0.601 |
stealth | -0.572 |
Token | the |
Token ID | 262 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
honour | +1.170 |
xual | +1.143 |
icle | +1.066 |
rogens | +1.061 |
stealth | +1.026 |
Neg logit contributions | |
� | -1.404 |
Rudolph | -1.375 |
steen | -1.342 |
之 | -1.337 |
ahime | -1.319 |
Token | sunk |
Token ID | 24790 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
� | +0.293 |
Rudolph | +0.290 |
steen | +0.282 |
之 | +0.280 |
ahime | +0.272 |
Neg logit contributions | |
honour | -0.223 |
xual | -0.220 |
rogens | -0.203 |
icle | -0.203 |
stealth | -0.193 |
Token | en |
Token ID | 268 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
Rudolph | +1.750 |
� | +1.750 |
steen | +1.699 |
之 | +1.688 |
ahime | +1.649 |
Neg logit contributions | |
xual | -0.973 |
honour | -0.959 |
rogens | -0.866 |
icle | -0.860 |
stealth | -0.798 |
Token |
|
Token ID | 198 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
� | +0.215 |
Rudolph | +0.213 |
steen | +0.205 |
之 | +0.204 |
ahime | +0.199 |
Neg logit contributions | |
honour | -0.187 |
xual | -0.187 |
icle | -0.173 |
rogens | -0.172 |
stealth | -0.164 |
Token |
|
Token ID | 198 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Rudolph | +0.287 |
� | +0.285 |
steen | +0.275 |
之 | +0.275 |
Myr | +0.263 |
Neg logit contributions | |
xual | -0.295 |
honour | -0.285 |
rogens | -0.270 |
icle | -0.265 |
stealth | -0.254 |
Token | Here |
Token ID | 4342 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
� | +0.164 |
Rudolph | +0.163 |
steen | +0.156 |
之 | +0.156 |
ahime | +0.151 |
Neg logit contributions | |
honour | -0.170 |
xual | -0.170 |
icle | -0.158 |
rogens | -0.158 |
stealth | -0.150 |
Token | 's |
Token ID | 338 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
� | +0.023 |
Rudolph | +0.022 |
之 | +0.021 |
steen | +0.021 |
ahime | +0.021 |
Neg logit contributions | |
honour | -0.025 |
xual | -0.025 |
icle | -0.023 |
rogens | -0.023 |
stealth | -0.022 |
Token | Dinosaur |
Token ID | 47808 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
� | +0.786 |
Rudolph | +0.781 |
steen | +0.751 |
之 | +0.750 |
ahime | +0.724 |
Neg logit contributions | |
xual | -0.703 |
honour | -0.701 |
rogens | -0.648 |
icle | -0.647 |
stealth | -0.615 |
Token | Jr |
Token ID | 7504 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
honour | +0.777 |
xual | +0.775 |
icle | +0.728 |
rogens | +0.726 |
stealth | +0.699 |
Neg logit contributions | |
� | -0.548 |
Rudolph | -0.541 |
之 | -0.518 |
steen | -0.516 |
ahime | -0.501 |
Token | . |
Token ID | 13 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
� | +2.011 |
Rudolph | +2.004 |
steen | +1.916 |
之 | +1.910 |
rh | +1.792 |
Neg logit contributions | |
xual | -2.554 |
honour | -2.537 |
rogens | -2.387 |
icle | -2.360 |
stealth | -2.269 |
Token | in |
Token ID | 287 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
� | +0.572 |
Rudolph | +0.568 |
steen | +0.546 |
之 | +0.545 |
ahime | +0.526 |
Neg logit contributions | |
xual | -0.536 |
honour | -0.536 |
rogens | -0.496 |
icle | -0.495 |
stealth | -0.471 |
Token | the |
Token ID | 262 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
� | +0.100 |
Rudolph | +0.100 |
steen | +0.096 |
之 | +0.096 |
ahime | +0.092 |
Neg logit contributions | |
xual | -0.080 |
honour | -0.080 |
rogens | -0.074 |
icle | -0.073 |
stealth | -0.069 |
Token | studio |
Token ID | 8034 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
honour | +0.111 |
xual | +0.111 |
icle | +0.102 |
rogens | +0.102 |
stealth | +0.097 |
Neg logit contributions | |
� | -0.122 |
Rudolph | -0.121 |
steen | -0.116 |
之 | -0.116 |
ahime | -0.112 |
Token | with |
Token ID | 351 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
� | +0.835 |
Rudolph | +0.832 |
steen | +0.797 |
之 | +0.796 |
ahime | +0.765 |
Neg logit contributions | |
xual | -0.842 |
honour | -0.838 |
rogens | -0.780 |
icle | -0.776 |
stealth | -0.741 |
Token | mouse |
Token ID | 10211 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
� | +0.008 |
Rudolph | +0.008 |
steen | +0.008 |
之 | +0.008 |
ahime | +0.008 |
Neg logit contributions | |
honour | -0.006 |
xual | -0.006 |
icle | -0.005 |
rogens | -0.005 |
stealth | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
honour | +0.719 |
xual | +0.713 |
icle | +0.660 |
rogens | +0.656 |
stealth | +0.628 |
Neg logit contributions | |
� | -0.852 |
Rudolph | -0.835 |
之 | -0.810 |
steen | -0.806 |
ahime | -0.783 |
Token | then |
Token ID | 788 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
� | +0.032 |
Rudolph | +0.032 |
之 | +0.031 |
steen | +0.031 |
ahime | +0.030 |
Neg logit contributions | |
honour | -0.028 |
xual | -0.028 |
rogens | -0.026 |
icle | -0.026 |
stealth | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
� | +0.027 |
Rudolph | +0.026 |
之 | +0.026 |
steen | +0.026 |
ahime | +0.025 |
Neg logit contributions | |
honour | -0.024 |
xual | -0.024 |
rogens | -0.023 |
icle | -0.023 |
stealth | -0.022 |
Token | serial |
Token ID | 11389 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
� | +0.029 |
Rudolph | +0.028 |
steen | +0.027 |
之 | +0.027 |
ahime | +0.027 |
Neg logit contributions | |
honour | -0.021 |
xual | -0.021 |
rogens | -0.019 |
icle | -0.019 |
stealth | -0.018 |
Token | cable |
Token ID | 7862 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
honour | +0.547 |
xual | +0.546 |
icle | +0.515 |
rogens | +0.513 |
stealth | +0.495 |
Neg logit contributions | |
� | -0.362 |
Rudolph | -0.357 |
steen | -0.341 |
之 | -0.340 |
ahime | -0.324 |
Token | , |
Token ID | 11 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
Rudolph | +3.341 |
� | +3.311 |
steen | +3.180 |
之 | +3.174 |
ahime | +3.058 |
Neg logit contributions | |
xual | -3.389 |
honour | -3.339 |
rogens | -3.124 |
icle | -3.115 |
stealth | -2.935 |
Token | the |
Token ID | 262 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
honour | +0.020 |
xual | +0.020 |
rogens | +0.018 |
icle | +0.018 |
stealth | +0.017 |
Neg logit contributions | |
� | -0.024 |
Rudolph | -0.024 |
之 | -0.023 |
steen | -0.023 |
ahime | -0.022 |
Token | parallel |
Token ID | 10730 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
� | +0.201 |
Rudolph | +0.199 |
之 | +0.193 |
steen | +0.193 |
ahime | +0.187 |
Neg logit contributions | |
honour | -0.154 |
xual | -0.153 |
rogens | -0.141 |
icle | -0.141 |
stealth | -0.134 |
Token | cable |
Token ID | 7862 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
� | +0.139 |
Rudolph | +0.137 |
之 | +0.132 |
steen | +0.132 |
ahime | +0.127 |
Neg logit contributions | |
honour | -0.152 |
xual | -0.152 |
icle | -0.142 |
rogens | -0.141 |
stealth | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Rudolph | +3.248 |
� | +3.226 |
之 | +3.096 |
steen | +3.094 |
ahime | +2.980 |
Neg logit contributions | |
xual | -3.149 |
honour | -3.105 |
rogens | -2.896 |
icle | -2.887 |
stealth | -2.722 |
Token | Crosby |
Token ID | 33098 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
� | +1.171 |
Rudolph | +1.170 |
steen | +1.131 |
之 | +1.108 |
Myr | +1.084 |
Neg logit contributions | |
xual | -0.942 |
honour | -0.913 |
rogens | -0.850 |
icle | -0.849 |
stealth | -0.795 |
Token | , |
Token ID | 11 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
honour | +0.256 |
xual | +0.254 |
icle | +0.235 |
rogens | +0.235 |
stealth | +0.224 |
Neg logit contributions | |
� | -0.292 |
Rudolph | -0.290 |
之 | -0.279 |
steen | -0.279 |
ahime | -0.271 |
Token | Ev |
Token ID | 4319 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
� | +0.030 |
Rudolph | +0.030 |
steen | +0.029 |
之 | +0.029 |
ahime | +0.028 |
Neg logit contributions | |
honour | -0.031 |
xual | -0.031 |
rogens | -0.029 |
icle | -0.029 |
stealth | -0.028 |
Token | gen |
Token ID | 5235 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
honour | +0.392 |
xual | +0.387 |
icle | +0.366 |
rogens | +0.365 |
stealth | +0.346 |
Neg logit contributions | |
� | -0.393 |
Rudolph | -0.387 |
之 | -0.376 |
steen | -0.373 |
ahime | -0.359 |
Token | i |
Token ID | 72 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
xual | +0.333 |
honour | +0.329 |
rogens | +0.283 |
icle | +0.280 |
stealth | +0.253 |
Neg logit contributions | |
� | -0.998 |
Rudolph | -0.996 |
steen | -0.968 |
之 | -0.965 |
ahime | -0.941 |
Token | Malk |
Token ID | 41980 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
Rudolph | +0.506 |
� | +0.501 |
steen | +0.469 |
之 | +0.467 |
Myr | +0.446 |
Neg logit contributions | |
xual | -0.803 |
honour | -0.788 |
rogens | -0.746 |
icle | -0.744 |
stealth | -0.711 |
Token | in |
Token ID | 259 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Rudolph | +2.475 |
� | +2.441 |
steen | +2.397 |
之 | +2.359 |
Myr | +2.278 |
Neg logit contributions | |
xual | -1.666 |
honour | -1.627 |
icle | -1.464 |
rogens | -1.462 |
stealth | -1.391 |
Token | , |
Token ID | 11 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
honour | +0.081 |
xual | +0.081 |
rogens | +0.075 |
icle | +0.075 |
stealth | +0.071 |
Neg logit contributions | |
� | -0.094 |
Rudolph | -0.093 |
之 | -0.090 |
steen | -0.090 |
ahime | -0.087 |
Token | Phil |
Token ID | 4543 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
honour | +0.183 |
xual | +0.181 |
icle | +0.169 |
rogens | +0.169 |
stealth | +0.161 |
Neg logit contributions | |
� | -0.181 |
Rudolph | -0.178 |
之 | -0.172 |
steen | -0.172 |
ahime | -0.166 |
Token | K |
Token ID | 509 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
honour | +0.721 |
xual | +0.691 |
icle | +0.667 |
rogens | +0.648 |
stealth | +0.622 |
Neg logit contributions | |
� | -0.851 |
之 | -0.821 |
Rudolph | -0.816 |
steen | -0.806 |
ahime | -0.784 |
Token | essel |
Token ID | 7878 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
honour | +0.021 |
xual | +0.020 |
icle | +0.019 |
rogens | +0.018 |
stealth | +0.017 |
Neg logit contributions | |
� | -0.048 |
Rudolph | -0.047 |
之 | -0.046 |
steen | -0.046 |
ahime | -0.045 |