Token | . |
Token ID | 13 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
anders | +6.180 |
ourke | +5.383 |
[+ | +5.340 |
onent | +5.237 |
defences | +5.213 |
Neg logit contributions | |
MRI | -4.057 |
NH | -3.820 |
MO | -3.754 |
MR | -3.678 |
blu | -3.616 |
Token | ( |
Token ID | 357 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
anders | +5.172 |
[+ | +4.412 |
ourke | +4.356 |
onent | +4.263 |
defences | +4.197 |
Neg logit contributions | |
MRI | -4.744 |
NH | -4.534 |
MO | -4.470 |
MR | -4.392 |
blu | -4.317 |
Token | John |
Token ID | 7554 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
anders | +0.667 |
ourke | +0.583 |
[+ | +0.576 |
defences | +0.570 |
onent | +0.564 |
Neg logit contributions | |
MRI | -0.450 |
NH | -0.425 |
MO | -0.420 |
MR | -0.411 |
PLE | -0.401 |
Token | McDonnell |
Token ID | 39441 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
anders | +0.910 |
ourke | +0.800 |
[+ | +0.793 |
defences | +0.778 |
onent | +0.776 |
Neg logit contributions | |
MRI | -0.520 |
NH | -0.488 |
MO | -0.481 |
MR | -0.468 |
PLE | -0.457 |
Token | / |
Token ID | 14 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
MRI | +0.227 |
NH | +0.206 |
MO | +0.199 |
MR | +0.192 |
NR | +0.188 |
Neg logit contributions | |
anders | -0.756 |
ourke | -0.680 |
[+ | -0.671 |
defences | -0.670 |
iris | -0.665 |
Token | The |
Token ID | 464 |
Feature activation | +1.99e+01 |
Pos logit contributions | |
anders | +5.944 |
[+ | +5.126 |
ourke | +5.076 |
onent | +5.037 |
iris | +4.995 |
Neg logit contributions | |
MRI | -3.798 |
shepherd | -3.622 |
blu | -3.587 |
MO | -3.570 |
NH | -3.547 |
Token | Washington |
Token ID | 2669 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
anders | +9.524 |
Capitals | +7.569 |
[+ | +7.282 |
Founding | +7.155 |
ourke | +7.154 |
Neg logit contributions | |
MRI | -17.196 |
NH | -16.134 |
MO | -16.116 |
phys | -16.029 |
TYPE | -15.926 |
Token | Post |
Token ID | 2947 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
anders | +6.945 |
[+ | +5.944 |
onent | +5.546 |
ourke | +5.485 |
Founding | +5.371 |
Neg logit contributions | |
MRI | -8.718 |
NH | -8.141 |
MO | -8.119 |
MR | -8.001 |
blu | -7.819 |
Token | ) |
Token ID | 8 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
anders | +0.822 |
ourke | +0.714 |
[+ | +0.707 |
defences | +0.692 |
onent | +0.690 |
Neg logit contributions | |
MRI | -0.574 |
NH | -0.543 |
MO | -0.536 |
MR | -0.523 |
PLE | -0.513 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
anders | +1.701 |
ourke | +1.498 |
[+ | +1.487 |
defences | +1.458 |
onent | +1.457 |
Neg logit contributions | |
MRI | -0.924 |
NH | -0.869 |
MO | -0.854 |
MR | -0.831 |
PLE | -0.809 |
Token |
|
Token ID | 198 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
MRI | +0.556 |
NH | +0.519 |
MO | +0.511 |
MR | +0.496 |
PLE | +0.482 |
Neg logit contributions | |
anders | -1.133 |
ourke | -1.004 |
[+ | -0.991 |
defences | -0.981 |
onent | -0.973 |
Token | 47 |
Token ID | 2857 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
MRI | +2.189 |
NH | +2.091 |
MR | +2.035 |
MO | +2.030 |
PLE | +1.966 |
Neg logit contributions | |
anders | -2.563 |
defences | -2.187 |
ourke | -2.171 |
[+ | -2.166 |
iris | -2.126 |
Token | ] |
Token ID | 60 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
anders | +0.080 |
ourke | +0.069 |
[+ | +0.069 |
defences | +0.067 |
onent | +0.067 |
Neg logit contributions | |
MRI | -0.057 |
NH | -0.054 |
MO | -0.053 |
MR | -0.052 |
PLE | -0.051 |
Token | < |
Token ID | 1279 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
MRI | +0.815 |
NH | +0.772 |
MO | +0.764 |
MR | +0.743 |
blu | +0.728 |
Neg logit contributions | |
anders | -1.296 |
ourke | -1.132 |
[+ | -1.111 |
defences | -1.100 |
onent | -1.097 |
Token | met |
Token ID | 4164 |
Feature activation | +5.86e+00 |
Pos logit contributions | |
MRI | +0.232 |
NH | +0.219 |
MO | +0.217 |
MR | +0.212 |
PLE | +0.206 |
Neg logit contributions | |
anders | -0.333 |
ourke | -0.292 |
[+ | -0.289 |
defences | -0.286 |
onent | -0.282 |
Token | ros |
Token ID | 4951 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
anders | +5.083 |
ourke | +4.378 |
[+ | +4.278 |
onent | +4.234 |
iris | +4.231 |
Neg logit contributions | |
MRI | -3.918 |
NH | -3.734 |
MO | -3.659 |
MR | -3.585 |
PLE | -3.580 |
Token | xual |
Token ID | 5541 |
Feature activation | +1.84e+01 |
Pos logit contributions | |
anders | +3.969 |
ourke | +3.258 |
[+ | +3.110 |
onent | +3.065 |
iris | +3.040 |
Neg logit contributions | |
MRI | -6.215 |
NH | -6.117 |
MO | -5.959 |
NR | -5.904 |
PLE | -5.886 |
Token | th |
Token ID | 400 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
anders | +8.311 |
uper | +6.198 |
ourke | +6.184 |
onent | +6.114 |
iris | +5.854 |
Neg logit contributions | |
MO | -16.622 |
shepherd | -16.574 |
MRI | -16.496 |
Skydragon | -16.384 |
PLE | -16.070 |
Token | ug |
Token ID | 1018 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
MRI | +0.491 |
NH | +0.464 |
MO | +0.459 |
MR | +0.449 |
NR | +0.436 |
Neg logit contributions | |
anders | -0.647 |
ourke | -0.557 |
defences | -0.552 |
[+ | -0.551 |
iris | -0.538 |
Token | > |
Token ID | 29 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
MRI | +0.160 |
NH | +0.152 |
MO | +0.150 |
MR | +0.147 |
PLE | +0.143 |
Neg logit contributions | |
anders | -0.228 |
ourke | -0.198 |
[+ | -0.196 |
defences | -0.193 |
onent | -0.191 |
Token | le |
Token ID | 443 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
anders | +1.697 |
ourke | +1.476 |
[+ | +1.457 |
defences | +1.431 |
onent | +1.428 |
Neg logit contributions | |
MRI | -1.182 |
NH | -1.117 |
MO | -1.106 |
MR | -1.079 |
PLE | -1.058 |
Token | l |
Token ID | 75 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
MRI | +2.895 |
MO | +2.800 |
NH | +2.771 |
MR | +2.695 |
blu | +2.654 |
Neg logit contributions | |
anders | -4.353 |
ourke | -3.800 |
defences | -3.743 |
[+ | -3.726 |
onent | -3.718 |
Token | Cody |
Token ID | 27035 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
anders | +2.502 |
ourke | +2.174 |
[+ | +2.153 |
defences | +2.110 |
onent | +2.102 |
Neg logit contributions | |
MRI | -1.758 |
NH | -1.662 |
MO | -1.641 |
MR | -1.603 |
PLE | -1.571 |
Token | Wester |
Token ID | 32104 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
anders | +2.658 |
ourke | +2.290 |
[+ | +2.278 |
defences | +2.217 |
onent | +2.210 |
Neg logit contributions | |
MRI | -1.970 |
NH | -1.850 |
MO | -1.833 |
MR | -1.782 |
PLE | -1.753 |
Token | lund |
Token ID | 37525 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
anders | +2.849 |
[+ | +2.423 |
ourke | +2.422 |
defences | +2.341 |
iris | +2.325 |
Neg logit contributions | |
MRI | -2.416 |
NH | -2.256 |
MO | -2.242 |
MR | -2.192 |
blu | -2.167 |
Token | (@ |
Token ID | 4275 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
anders | +0.162 |
ourke | +0.131 |
[+ | +0.127 |
defences | +0.126 |
onent | +0.124 |
Neg logit contributions | |
MRI | -0.235 |
NH | -0.228 |
MO | -0.225 |
MR | -0.221 |
NR | -0.219 |
Token | C |
Token ID | 34 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
anders | +3.665 |
ourke | +3.214 |
[+ | +3.169 |
defences | +3.115 |
onent | +3.110 |
Neg logit contributions | |
MRI | -2.157 |
NH | -2.017 |
MO | -1.994 |
MR | -1.938 |
blu | -1.897 |
Token | ody |
Token ID | 1118 |
Feature activation | +1.82e+01 |
Pos logit contributions | |
anders | +4.406 |
ourke | +3.724 |
[+ | +3.613 |
onent | +3.560 |
defences | +3.542 |
Neg logit contributions | |
MRI | -4.411 |
NH | -4.175 |
MO | -4.148 |
MR | -4.062 |
blu | -4.038 |
Token | W |
Token ID | 54 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
anders | +15.991 |
ourke | +13.242 |
uper | +12.663 |
wald | +12.630 |
る | +12.293 |
Neg logit contributions | |
shepherd | -9.542 |
Phant | -9.424 |
NR | -9.270 |
MRI | -9.264 |
blu | -9.185 |
Token | ester |
Token ID | 7834 |
Feature activation | +8.08e+00 |
Pos logit contributions | |
anders | +7.121 |
ourke | +5.671 |
onent | +5.329 |
iris | +5.204 |
[+ | +5.169 |
Neg logit contributions | |
MRI | -8.501 |
NH | -8.124 |
blu | -7.953 |
NR | -7.930 |
shepherd | -7.842 |
Token | lund |
Token ID | 37525 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
anders | +4.317 |
ourke | +3.298 |
[+ | +3.126 |
onent | +2.963 |
defences | +2.943 |
Neg logit contributions | |
MRI | -7.941 |
MO | -7.598 |
blu | -7.582 |
NH | -7.524 |
shepherd | -7.522 |
Token | ) |
Token ID | 8 |
Feature activation | +8.67e+00 |
Pos logit contributions | |
anders | +3.469 |
ourke | +3.002 |
[+ | +2.967 |
onent | +2.900 |
defences | +2.895 |
Neg logit contributions | |
MRI | -2.483 |
NH | -2.330 |
MO | -2.314 |
MR | -2.258 |
PLE | -2.232 |
Token | October |
Token ID | 3267 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
anders | +5.649 |
[+ | +4.869 |
ourke | +4.620 |
onent | +4.573 |
defences | +4.519 |
Neg logit contributions | |
MRI | -7.091 |
NH | -6.718 |
MO | -6.684 |
MR | -6.620 |
PLE | -6.575 |
Token | Jill |
Token ID | 22772 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
anders | +0.147 |
ourke | +0.127 |
[+ | +0.126 |
defences | +0.123 |
onent | +0.123 |
Neg logit contributions | |
MRI | -0.121 |
NH | -0.115 |
MO | -0.114 |
MR | -0.111 |
PLE | -0.110 |
Token | ian |
Token ID | 666 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
MRI | +6.446 |
NH | +5.813 |
MO | +5.680 |
MR | +5.616 |
NR | +5.562 |
Neg logit contributions | |
anders | -9.646 |
defences | -8.877 |
ourke | -8.628 |
ワン | -8.540 |
raviolet | -8.510 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
MRI | +2.522 |
MO | +2.329 |
NH | +2.325 |
MR | +2.235 |
NR | +2.217 |
Neg logit contributions | |
anders | -5.561 |
ourke | -4.927 |
defences | -4.868 |
iris | -4.810 |
[+ | -4.808 |
Token | we |
Token ID | 356 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
anders | +1.554 |
ourke | +1.351 |
[+ | +1.339 |
defences | +1.312 |
onent | +1.307 |
Neg logit contributions | |
MRI | -1.071 |
NH | -1.012 |
MO | -0.999 |
MR | -0.976 |
PLE | -0.957 |
Token | couldn |
Token ID | 3521 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
anders | +3.263 |
ourke | +2.823 |
[+ | +2.803 |
defences | +2.748 |
iris | +2.736 |
Neg logit contributions | |
MRI | -2.680 |
NH | -2.521 |
MO | -2.517 |
MR | -2.448 |
PLE | -2.415 |
Token | 't |
Token ID | 470 |
Feature activation | +1.80e+01 |
Pos logit contributions | |
anders | +0.516 |
ourke | +0.453 |
[+ | +0.447 |
defences | +0.443 |
onent | +0.438 |
Neg logit contributions | |
MRI | -0.307 |
NH | -0.287 |
MO | -0.283 |
MR | -0.276 |
NR | -0.268 |
Token | resist |
Token ID | 4180 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
anders | +8.266 |
[+ | +6.434 |
defences | +6.352 |
る | +6.251 |
onent | +6.200 |
Neg logit contributions | |
MRI | -16.335 |
MO | -15.896 |
NH | -15.840 |
PLE | -15.318 |
MR | -15.301 |
Token | the |
Token ID | 262 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
MRI | +0.522 |
NH | +0.493 |
MO | +0.486 |
MR | +0.476 |
NR | +0.467 |
Neg logit contributions | |
anders | -0.821 |
ourke | -0.717 |
[+ | -0.706 |
defences | -0.697 |
onent | -0.697 |
Token | temptation |
Token ID | 29062 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
anders | +3.039 |
ourke | +2.538 |
[+ | +2.469 |
defences | +2.440 |
iris | +2.383 |
Neg logit contributions | |
MRI | -4.173 |
NH | -4.036 |
MO | -3.936 |
MR | -3.887 |
PLE | -3.822 |
Token | to |
Token ID | 284 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
MRI | +2.667 |
NH | +2.552 |
MO | +2.536 |
NR | +2.442 |
blu | +2.428 |
Neg logit contributions | |
anders | -5.189 |
ourke | -4.551 |
defences | -4.420 |
iris | -4.419 |
onent | -4.396 |
Token | recall |
Token ID | 10014 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
MRI | +0.383 |
NH | +0.358 |
MO | +0.352 |
MR | +0.344 |
PLE | +0.336 |
Neg logit contributions | |
anders | -0.680 |
ourke | -0.598 |
[+ | -0.593 |
defences | -0.582 |
onent | -0.580 |
Token | Green |
Token ID | 3469 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
anders | +4.361 |
ourke | +3.761 |
[+ | +3.739 |
defences | +3.670 |
onent | +3.612 |
Neg logit contributions | |
MRI | -3.487 |
NH | -3.295 |
MO | -3.253 |
MR | -3.178 |
PLE | -3.118 |
Token | Park |
Token ID | 3250 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
anders | +0.454 |
ourke | +0.394 |
[+ | +0.391 |
defences | +0.381 |
onent | +0.378 |
Neg logit contributions | |
MRI | -0.369 |
MO | -0.355 |
NH | -0.354 |
MR | -0.344 |
NR | -0.339 |
Token | and |
Token ID | 290 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
anders | +2.670 |
ourke | +2.335 |
[+ | +2.313 |
defences | +2.267 |
onent | +2.261 |
Neg logit contributions | |
MRI | -1.685 |
NH | -1.588 |
MO | -1.567 |
MR | -1.528 |
PLE | -1.495 |
Token | the |
Token ID | 262 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
MRI | +0.015 |
NH | +0.015 |
MO | +0.014 |
MR | +0.014 |
NR | +0.014 |
Neg logit contributions | |
anders | -0.024 |
ourke | -0.021 |
[+ | -0.020 |
onent | -0.020 |
iris | -0.020 |
Token | Animals |
Token ID | 25390 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
anders | +1.640 |
ourke | +1.421 |
[+ | +1.402 |
onent | +1.373 |
iris | +1.367 |
Neg logit contributions | |
MRI | -1.217 |
NH | -1.160 |
MO | -1.146 |
MR | -1.122 |
NR | -1.108 |
Token | in |
Token ID | 287 |
Feature activation | +1.74e+01 |
Pos logit contributions | |
anders | +0.470 |
ourke | +0.408 |
[+ | +0.406 |
onent | +0.394 |
iris | +0.393 |
Neg logit contributions | |
MRI | -0.347 |
NH | -0.331 |
MO | -0.327 |
MR | -0.320 |
NR | -0.314 |
Token | War |
Token ID | 1810 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
anders | +7.218 |
[+ | +5.747 |
defences | +5.607 |
Founding | +5.528 |
ourke | +5.143 |
Neg logit contributions | |
MRI | -16.450 |
NH | -15.939 |
MO | -15.584 |
PLE | -15.528 |
phys | -15.280 |
Token | memorial |
Token ID | 17357 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
anders | +1.193 |
ourke | +1.017 |
[+ | +1.002 |
onent | +0.981 |
iris | +0.972 |
Neg logit contributions | |
MRI | -1.074 |
NH | -1.025 |
MO | -1.015 |
MR | -0.996 |
blu | -0.978 |
Token | in |
Token ID | 287 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
anders | +5.150 |
ourke | +4.432 |
[+ | +4.402 |
defences | +4.363 |
onent | +4.284 |
Neg logit contributions | |
MRI | -4.061 |
NH | -3.840 |
MO | -3.777 |
MR | -3.700 |
PLE | -3.625 |
Token | Park |
Token ID | 3250 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
anders | +4.228 |
ourke | +3.658 |
[+ | +3.630 |
defences | +3.570 |
onent | +3.508 |
Neg logit contributions | |
MRI | -3.382 |
NH | -3.191 |
MO | -3.149 |
MR | -3.075 |
PLE | -3.018 |
Token | Lane |
Token ID | 15016 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
anders | +3.970 |
ourke | +3.361 |
[+ | +3.306 |
defences | +3.256 |
iris | +3.246 |
Neg logit contributions | |
MRI | -3.654 |
NH | -3.470 |
MO | -3.426 |
MR | -3.357 |
PLE | -3.319 |
Token | box |
Token ID | 3091 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
MRI | +2.376 |
NH | +2.270 |
MO | +2.249 |
blu | +2.231 |
NR | +2.172 |
Neg logit contributions | |
anders | -5.756 |
ourke | -5.008 |
iris | -4.984 |
[+ | -4.887 |
onent | -4.881 |
Token | underneath |
Token ID | 14638 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
anders | +2.308 |
ourke | +1.975 |
[+ | +1.953 |
defences | +1.904 |
onent | +1.895 |
Neg logit contributions | |
MRI | -2.129 |
NH | -2.023 |
MO | -2.003 |
MR | -1.964 |
PLE | -1.928 |
Token | roughly |
Token ID | 7323 |
Feature activation | +8.98e+00 |
Pos logit contributions | |
anders | +4.883 |
ourke | +4.381 |
[+ | +4.368 |
defences | +4.242 |
onent | +4.193 |
Neg logit contributions | |
MRI | -2.619 |
NH | -2.446 |
MO | -2.412 |
MR | -2.337 |
blu | -2.245 |
Token | ( |
Token ID | 357 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
anders | +6.364 |
[+ | +5.500 |
ourke | +5.297 |
onent | +5.126 |
defences | +5.123 |
Neg logit contributions | |
MRI | -7.098 |
NH | -6.822 |
MO | -6.707 |
MR | -6.659 |
PLE | -6.563 |
Token | 6 |
Token ID | 21 |
Feature activation | +7.45e+00 |
Pos logit contributions | |
anders | +4.177 |
ourke | +3.562 |
[+ | +3.505 |
onent | +3.427 |
iris | +3.413 |
Neg logit contributions | |
MRI | -3.733 |
NH | -3.565 |
MO | -3.495 |
MR | -3.452 |
blu | -3.419 |
Token | ) |
Token ID | 8 |
Feature activation | +1.64e+01 |
Pos logit contributions | |
anders | +6.115 |
ourke | +5.196 |
[+ | +5.154 |
onent | +5.009 |
defences | +4.956 |
Neg logit contributions | |
MRI | -5.152 |
NH | -4.878 |
MO | -4.790 |
MR | -4.741 |
PLE | -4.601 |
Token | C |
Token ID | 327 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
anders | +11.831 |
[+ | +10.979 |
ourke | +10.011 |
defences | +9.914 |
onent | +9.730 |
Neg logit contributions | |
MRI | -10.686 |
NH | -10.215 |
MO | -10.172 |
MR | -9.691 |
PLE | -9.659 |
Token | – |
Token ID | 1906 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
anders | +5.114 |
ourke | +4.451 |
[+ | +4.407 |
onent | +4.297 |
defences | +4.291 |
Neg logit contributions | |
MRI | -3.444 |
NH | -3.228 |
MO | -3.162 |
MR | -3.090 |
blu | -3.056 |
Token | S |
Token ID | 50 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
anders | +3.188 |
ourke | +2.803 |
[+ | +2.780 |
defences | +2.728 |
onent | +2.719 |
Neg logit contributions | |
MRI | -1.795 |
NH | -1.682 |
MO | -1.656 |
MR | -1.612 |
PLE | -1.576 |
Token | –– |
Token ID | 25608 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
MRI | +0.559 |
NH | +0.531 |
MO | +0.530 |
MR | +0.513 |
PLE | +0.506 |
Neg logit contributions | |
anders | -0.826 |
ourke | -0.721 |
[+ | -0.710 |
defences | -0.704 |
iris | -0.704 |
Token | – |
Token ID | 1906 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
anders | +2.144 |
ourke | +1.868 |
[+ | +1.847 |
defences | +1.815 |
onent | +1.808 |
Neg logit contributions | |
MRI | -1.463 |
NH | -1.382 |
MO | -1.366 |
MR | -1.334 |
PLE | -1.307 |
Token | asphalt |
Token ID | 48292 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
MRI | +1.182 |
MO | +1.135 |
NH | +1.134 |
NR | +1.109 |
MR | +1.098 |
Neg logit contributions | |
anders | -1.757 |
ourke | -1.538 |
[+ | -1.513 |
iris | -1.497 |
onent | -1.483 |
Token | repairs |
Token ID | 20097 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
anders | +7.535 |
ourke | +6.475 |
[+ | +6.474 |
defences | +6.423 |
iris | +6.222 |
Neg logit contributions | |
MRI | -5.799 |
NH | -5.511 |
MO | -5.333 |
MR | -5.224 |
PLE | -5.150 |
Token | for |
Token ID | 329 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
anders | +4.673 |
ourke | +4.059 |
[+ | +4.048 |
defences | +3.947 |
onent | +3.905 |
Neg logit contributions | |
MRI | -3.117 |
NH | -2.910 |
MO | -2.867 |
MR | -2.806 |
PLE | -2.756 |
Token | streets |
Token ID | 6483 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
anders | +1.059 |
ourke | +0.915 |
[+ | +0.904 |
onent | +0.886 |
defences | +0.879 |
Neg logit contributions | |
MRI | -0.837 |
NH | -0.796 |
MO | -0.787 |
MR | -0.771 |
blu | -0.763 |
Token | , |
Token ID | 11 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
anders | +2.108 |
ourke | +1.851 |
[+ | +1.832 |
defences | +1.797 |
onent | +1.796 |
Neg logit contributions | |
MRI | -1.282 |
NH | -1.208 |
MO | -1.191 |
MR | -1.161 |
PLE | -1.134 |
Token | concrete |
Token ID | 10017 |
Feature activation | +1.63e+01 |
Pos logit contributions | |
anders | +2.786 |
ourke | +2.393 |
[+ | +2.368 |
defences | +2.317 |
onent | +2.306 |
Neg logit contributions | |
MRI | -2.312 |
NH | -2.196 |
MO | -2.171 |
MR | -2.126 |
PLE | -2.087 |
Token | sidewalk |
Token ID | 24058 |
Feature activation | +7.40e+00 |
Pos logit contributions | |
anders | +11.728 |
defences | +10.266 |
ourke | +9.842 |
[+ | +9.770 |
る | +9.587 |
Neg logit contributions | |
MRI | -11.002 |
NH | -10.536 |
MO | -10.266 |
PLE | -10.125 |
MR | -9.911 |
Token | repairs |
Token ID | 20097 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
anders | +4.909 |
[+ | +3.979 |
ourke | +3.967 |
defences | +3.964 |
iris | +3.775 |
Neg logit contributions | |
MRI | -6.382 |
NH | -6.155 |
MO | -6.035 |
MR | -5.941 |
PLE | -5.902 |
Token | are |
Token ID | 389 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
anders | +5.037 |
ourke | +4.391 |
[+ | +4.370 |
defences | +4.275 |
onent | +4.249 |
Neg logit contributions | |
MRI | -3.142 |
NH | -2.957 |
MO | -2.908 |
MR | -2.838 |
PLE | -2.784 |
Token | not |
Token ID | 407 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
anders | +1.772 |
ourke | +1.544 |
[+ | +1.528 |
defences | +1.498 |
onent | +1.494 |
Neg logit contributions | |
MRI | -1.189 |
NH | -1.123 |
MO | -1.108 |
MR | -1.082 |
PLE | -1.060 |
Token | done |
Token ID | 1760 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
anders | +2.421 |
ourke | +2.106 |
[+ | +2.091 |
defences | +2.048 |
onent | +2.038 |
Neg logit contributions | |
MRI | -1.689 |
NH | -1.598 |
MO | -1.576 |
MR | -1.538 |
PLE | -1.509 |
Token |
|
Token ID | 198 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
anders | +0.540 |
ourke | +0.476 |
[+ | +0.473 |
onent | +0.462 |
defences | +0.462 |
Neg logit contributions | |
MRI | -0.292 |
NH | -0.273 |
MO | -0.269 |
MR | -0.261 |
PLE | -0.255 |
Token | Think |
Token ID | 22073 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
MRI | +1.127 |
NH | +1.057 |
MO | +1.043 |
MR | +1.018 |
PLE | +1.004 |
Neg logit contributions | |
anders | -2.183 |
ourke | -1.942 |
[+ | -1.922 |
defences | -1.922 |
onent | -1.905 |
Token | about |
Token ID | 546 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
MRI | +1.343 |
NH | +1.275 |
MO | +1.267 |
MR | +1.230 |
PLE | +1.202 |
Neg logit contributions | |
anders | -2.265 |
ourke | -1.987 |
[+ | -1.973 |
onent | -1.940 |
defences | -1.938 |
Token | it |
Token ID | 340 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
MRI | +0.600 |
NH | +0.574 |
MO | +0.568 |
MR | +0.558 |
blu | +0.551 |
Neg logit contributions | |
anders | -0.953 |
ourke | -0.836 |
[+ | -0.819 |
onent | -0.813 |
defences | -0.808 |
Token | . |
Token ID | 13 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
MRI | +0.393 |
NH | +0.371 |
MO | +0.368 |
MR | +0.360 |
PLE | +0.353 |
Neg logit contributions | |
anders | -0.654 |
ourke | -0.576 |
[+ | -0.567 |
defences | -0.560 |
onent | -0.558 |
Token | - |
Token ID | 532 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
anders | +0.755 |
ourke | +0.659 |
[+ | +0.648 |
defences | +0.641 |
onent | +0.639 |
Neg logit contributions | |
MRI | -0.492 |
NH | -0.465 |
MO | -0.461 |
MR | -0.449 |
PLE | -0.440 |
Token | December |
Token ID | 3426 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
anders | +7.557 |
ourke | +5.717 |
[+ | +5.597 |
defences | +5.556 |
onent | +5.551 |
Neg logit contributions | |
MRI | -14.521 |
MO | -13.947 |
NH | -13.881 |
MR | -13.662 |
blu | -13.468 |
Token | 5 |
Token ID | 642 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
anders | +7.565 |
[+ | +6.804 |
ourke | +6.441 |
Founding | +6.106 |
defences | +6.083 |
Neg logit contributions | |
MRI | -8.019 |
NH | -7.542 |
MO | -7.328 |
MR | -7.296 |
Skydragon | -6.989 |
Token | , |
Token ID | 11 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
MRI | +0.346 |
NH | +0.325 |
MO | +0.321 |
MR | +0.312 |
PLE | +0.303 |
Neg logit contributions | |
anders | -0.618 |
ourke | -0.544 |
[+ | -0.537 |
defences | -0.532 |
onent | -0.528 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -8.55e+00 |
Pos logit contributions | |
anders | +4.218 |
[+ | +3.709 |
ourke | +3.600 |
defences | +3.494 |
iris | +3.457 |
Neg logit contributions | |
MRI | -3.414 |
NH | -3.211 |
MO | -3.177 |
PLE | -3.130 |
MR | -3.111 |
Token | Que |
Token ID | 15681 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
MRI | +2.832 |
MO | +2.757 |
MR | +2.520 |
NH | +2.482 |
PLE | +2.477 |
Neg logit contributions | |
anders | -10.141 |
defences | -9.408 |
intendent | -9.228 |
[+ | -9.201 |
onent | -9.183 |
Token | 5 |
Token ID | 20 |
Feature activation | +8.07e+00 |
Pos logit contributions | |
anders | +1.839 |
ourke | +1.608 |
[+ | +1.592 |
defences | +1.565 |
onent | +1.558 |
Neg logit contributions | |
MRI | -1.171 |
NH | -1.106 |
MO | -1.091 |
MR | -1.064 |
PLE | -1.039 |
Token | — |
Token ID | 851 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
anders | +5.818 |
[+ | +4.976 |
ourke | +4.925 |
defences | +4.689 |
iris | +4.688 |
Neg logit contributions | |
MRI | -6.347 |
NH | -5.912 |
MO | -5.856 |
blu | -5.759 |
MR | -5.731 |
Token | Ze |
Token ID | 9033 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
anders | +1.355 |
ourke | +1.184 |
[+ | +1.169 |
defences | +1.154 |
onent | +1.148 |
Neg logit contributions | |
MRI | -0.861 |
NH | -0.818 |
MO | -0.802 |
MR | -0.790 |
NR | -0.777 |
Token | ke |
Token ID | 365 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
MRI | +0.913 |
NH | +0.868 |
MO | +0.859 |
MR | +0.837 |
PLE | +0.815 |
Neg logit contributions | |
anders | -1.431 |
ourke | -1.254 |
[+ | -1.246 |
defences | -1.222 |
onent | -1.218 |
Token | Miller |
Token ID | 7920 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
MRI | +1.818 |
NH | +1.755 |
MO | +1.737 |
MR | +1.717 |
blu | +1.693 |
Neg logit contributions | |
anders | -1.272 |
ourke | -1.046 |
[+ | -1.033 |
defences | -0.995 |
onent | -0.994 |
Token | (@ |
Token ID | 4275 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
anders | +3.825 |
ourke | +3.100 |
[+ | +3.005 |
iris | +2.857 |
onent | +2.838 |
Neg logit contributions | |
MRI | -6.528 |
MO | -6.213 |
NH | -6.187 |
PLE | -6.076 |
MR | -6.064 |
Token | Ze |
Token ID | 36056 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
anders | +12.257 |
ourke | +10.285 |
iris | +9.959 |
wald | +9.922 |
onent | +9.772 |
Neg logit contributions | |
MRI | -9.563 |
NR | -9.033 |
shepherd | -9.032 |
Skydragon | -8.973 |
NH | -8.928 |
Token | ke |
Token ID | 365 |
Feature activation | +9.87e+00 |
Pos logit contributions | |
anders | +3.063 |
ourke | +2.649 |
[+ | +2.581 |
onent | +2.529 |
defences | +2.519 |
Neg logit contributions | |
MRI | -2.355 |
NH | -2.214 |
MO | -2.190 |
MR | -2.148 |
NR | -2.115 |
Token | J |
Token ID | 41 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
anders | +9.318 |
ourke | +8.052 |
[+ | +7.716 |
onent | +7.701 |
iris | +7.672 |
Neg logit contributions | |
MRI | -5.335 |
shepherd | -5.041 |
NR | -4.982 |
blu | -4.962 |
Skydragon | -4.904 |
Token | Miller |
Token ID | 33253 |
Feature activation | +9.48e+00 |
Pos logit contributions | |
anders | +1.535 |
ourke | +1.309 |
[+ | +1.295 |
defences | +1.268 |
onent | +1.259 |
Neg logit contributions | |
MRI | -1.426 |
NH | -1.359 |
MO | -1.346 |
MR | -1.321 |
PLE | -1.295 |
Token | ) |
Token ID | 8 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
anders | +7.785 |
ourke | +6.768 |
[+ | +6.499 |
onent | +6.368 |
iris | +6.359 |
Neg logit contributions | |
MRI | -6.334 |
shepherd | -5.921 |
blu | -5.883 |
MO | -5.860 |
PLE | -5.800 |
Token | parked |
Token ID | 19584 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
anders | +3.613 |
ourke | +3.117 |
[+ | +3.115 |
defences | +2.979 |
onent | +2.957 |
Neg logit contributions | |
MRI | -3.471 |
NH | -3.349 |
MO | -3.237 |
MR | -3.207 |
PLE | -3.163 |
Token | in |
Token ID | 287 |
Feature activation | +9.47e+00 |
Pos logit contributions | |
anders | +0.776 |
ourke | +0.670 |
[+ | +0.661 |
defences | +0.649 |
onent | +0.646 |
Neg logit contributions | |
MRI | -0.604 |
NH | -0.573 |
MO | -0.566 |
MR | -0.554 |
PLE | -0.543 |
Token | front |
Token ID | 2166 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
anders | +4.375 |
[+ | +3.348 |
ourke | +3.252 |
defences | +3.093 |
onent | +2.924 |
Neg logit contributions | |
MRI | -9.898 |
NH | -9.579 |
MO | -9.539 |
PLE | -9.362 |
MR | -9.229 |
Token | of |
Token ID | 286 |
Feature activation | +9.65e+00 |
Pos logit contributions | |
MRI | +0.438 |
NH | +0.413 |
MO | +0.408 |
MR | +0.398 |
NR | +0.389 |
Neg logit contributions | |
anders | -0.681 |
ourke | -0.593 |
[+ | -0.583 |
defences | -0.577 |
onent | -0.573 |
Token | buildings |
Token ID | 6832 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
anders | +5.129 |
defences | +4.166 |
[+ | +3.972 |
ourke | +3.909 |
onent | +3.679 |
Neg logit contributions | |
MRI | -9.393 |
NH | -8.908 |
MR | -8.818 |
MO | -8.792 |
PLE | -8.773 |
Token | like |
Token ID | 588 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
anders | +7.283 |
[+ | +6.450 |
ourke | +6.186 |
defences | +6.097 |
onent | +5.828 |
Neg logit contributions | |
MRI | -10.755 |
NH | -10.359 |
MO | -10.099 |
MR | -10.031 |
PLE | -9.991 |
Token | Sur |
Token ID | 4198 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
anders | +10.172 |
ourke | +8.893 |
[+ | +8.627 |
onent | +8.399 |
uper | +8.370 |
Neg logit contributions | |
MRI | -10.960 |
NH | -10.533 |
MO | -10.381 |
blu | -10.269 |
MR | -10.220 |
Token | rog |
Token ID | 3828 |
Feature activation | -9.42e+00 |
Pos logit contributions | |
MRI | +2.391 |
MO | +2.125 |
NH | +2.101 |
MR | +2.077 |
NR | +1.965 |
Neg logit contributions | |
anders | -5.796 |
defences | -5.163 |
[+ | -5.159 |
ourke | -5.097 |
iris | -5.065 |
Token | ate |
Token ID | 378 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
MRI | +4.231 |
NH | +3.901 |
MO | +3.834 |
MR | +3.721 |
NR | +3.594 |
Neg logit contributions | |
anders | -9.451 |
defences | -8.808 |
ワン | -8.527 |
iris | -8.445 |
ikuman | -8.429 |
Token | 's |
Token ID | 338 |
Feature activation | +8.56e+00 |
Pos logit contributions | |
anders | +0.808 |
ourke | +0.700 |
[+ | +0.691 |
defences | +0.680 |
onent | +0.677 |
Neg logit contributions | |
MRI | -0.587 |
NH | -0.555 |
MO | -0.549 |
MR | -0.537 |
PLE | -0.524 |
Token | Court |
Token ID | 3078 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
anders | +5.074 |
ourke | +4.094 |
[+ | +4.064 |
onent | +3.943 |
defences | +3.864 |
Neg logit contributions | |
MRI | -7.854 |
NH | -7.526 |
MO | -7.457 |
MR | -7.373 |
LESS | -7.139 |
Token | High |
Token ID | 11922 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
anders | +5.868 |
ourke | +4.758 |
[+ | +4.738 |
onent | +4.422 |
iris | +4.358 |
Neg logit contributions | |
MRI | -8.866 |
shepherd | -8.678 |
blu | -8.446 |
NR | -8.361 |
Skydragon | -8.301 |
Token | , |
Token ID | 11 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
anders | +0.114 |
ourke | +0.100 |
[+ | +0.099 |
defences | +0.097 |
onent | +0.097 |
Neg logit contributions | |
MRI | -0.066 |
NH | -0.062 |
MO | -0.061 |
MR | -0.059 |
PLE | -0.058 |
Token | Oliver |
Token ID | 15416 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
anders | +2.812 |
ourke | +2.416 |
[+ | +2.381 |
onent | +2.308 |
defences | +2.301 |
Neg logit contributions | |
MRI | -2.601 |
NH | -2.488 |
MO | -2.453 |
MR | -2.401 |
PLE | -2.373 |
Token | , |
Token ID | 11 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
anders | +1.735 |
ourke | +1.521 |
[+ | +1.510 |
onent | +1.475 |
defences | +1.474 |
Neg logit contributions | |
MRI | -1.069 |
NH | -1.003 |
MO | -0.988 |
MR | -0.964 |
PLE | -0.946 |
Token | Federal |
Token ID | 5618 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
anders | +8.519 |
[+ | +7.200 |
onent | +6.963 |
Founding | +6.960 |
ourke | +6.834 |
Neg logit contributions | |
MRI | -9.374 |
MO | -9.007 |
NH | -8.759 |
MR | -8.597 |
blu | -8.350 |
Token | and |
Token ID | 290 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
anders | +0.967 |
ourke | +0.848 |
[+ | +0.840 |
defences | +0.825 |
onent | +0.822 |
Neg logit contributions | |
MRI | -0.581 |
NH | -0.546 |
MO | -0.539 |
MR | -0.525 |
PLE | -0.513 |
Token | Franklin |
Token ID | 14021 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
anders | +10.160 |
Founding | +8.952 |
[+ | +8.552 |
onent | +8.397 |
ourke | +8.277 |
Neg logit contributions | |
MRI | -10.925 |
NH | -10.469 |
MR | -10.391 |
MO | -10.281 |
Skydragon | -10.159 |
Token | Streets |
Token ID | 27262 |
Feature activation | +6.49e+00 |
Pos logit contributions | |
anders | +2.151 |
ourke | +1.778 |
[+ | +1.762 |
defences | +1.714 |
onent | +1.697 |
Neg logit contributions | |
MRI | -2.629 |
NH | -2.520 |
MO | -2.493 |
MR | -2.455 |
PLE | -2.428 |
Token | ), |
Token ID | 828 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
anders | +4.686 |
ourke | +3.907 |
[+ | +3.837 |
onent | +3.816 |
iris | +3.765 |
Neg logit contributions | |
MRI | -5.176 |
MO | -4.926 |
NH | -4.924 |
MR | -4.841 |
PLE | -4.781 |
Token | the |
Token ID | 262 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
anders | +1.889 |
ourke | +1.636 |
[+ | +1.628 |
defences | +1.586 |
onent | +1.583 |
Neg logit contributions | |
MRI | -1.395 |
NH | -1.320 |
MO | -1.305 |
MR | -1.272 |
PLE | -1.254 |
Token | Stone |
Token ID | 8026 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
anders | +5.688 |
ourke | +4.876 |
[+ | +4.619 |
onent | +4.616 |
Founding | +4.563 |
Neg logit contributions | |
MRI | -8.873 |
NH | -8.437 |
MO | -8.321 |
MR | -8.165 |
PLE | -8.026 |
Token | years |
Token ID | 812 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
MRI | +2.027 |
NH | +1.913 |
MO | +1.910 |
blu | +1.906 |
NR | +1.888 |
Neg logit contributions | |
anders | -3.542 |
ourke | -3.165 |
[+ | -3.033 |
onent | -3.031 |
iris | -3.010 |
Token | , |
Token ID | 11 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
MRI | +0.509 |
NH | +0.483 |
MO | +0.477 |
MR | +0.464 |
NR | +0.453 |
Neg logit contributions | |
anders | -0.920 |
ourke | -0.816 |
[+ | -0.793 |
onent | -0.788 |
defences | -0.787 |
Token | under |
Token ID | 739 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
MRI | +0.272 |
NH | +0.259 |
MO | +0.256 |
MR | +0.248 |
blu | +0.246 |
Neg logit contributions | |
anders | -0.456 |
ourke | -0.402 |
[+ | -0.395 |
onent | -0.389 |
defences | -0.389 |
Token | one |
Token ID | 530 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
anders | +3.501 |
[+ | +3.024 |
ourke | +3.015 |
defences | +2.954 |
onent | +2.931 |
Neg logit contributions | |
MRI | -2.545 |
NH | -2.407 |
MO | -2.359 |
MR | -2.308 |
PLE | -2.256 |
Token | name |
Token ID | 1438 |
Feature activation | +7.34e+00 |
Pos logit contributions | |
anders | +5.558 |
[+ | +4.823 |
ourke | +4.790 |
defences | +4.730 |
onent | +4.653 |
Neg logit contributions | |
MRI | -4.668 |
NH | -4.387 |
MO | -4.255 |
MR | -4.231 |
PLE | -4.108 |
Token | or |
Token ID | 393 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
anders | +6.558 |
[+ | +5.767 |
ourke | +5.636 |
defences | +5.530 |
onent | +5.512 |
Neg logit contributions | |
MRI | -4.655 |
NH | -4.339 |
MO | -4.184 |
MR | -4.139 |
PLE | -4.086 |
Token | another |
Token ID | 1194 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
anders | +11.145 |
ourke | +9.825 |
[+ | +9.814 |
defences | +9.429 |
onent | +9.406 |
Neg logit contributions | |
MRI | -10.280 |
NH | -9.534 |
MR | -9.341 |
MO | -9.039 |
PLE | -8.886 |
Token | . |
Token ID | 13 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
anders | +4.820 |
[+ | +4.212 |
ourke | +4.203 |
defences | +4.109 |
onent | +4.079 |
Neg logit contributions | |
MRI | -3.045 |
NH | -2.846 |
MO | -2.788 |
MR | -2.730 |
PLE | -2.679 |
Token | App |
Token ID | 2034 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
anders | +2.465 |
ourke | +2.147 |
[+ | +2.136 |
defences | +2.085 |
onent | +2.082 |
Neg logit contributions | |
MRI | -1.637 |
NH | -1.542 |
MO | -1.518 |
MR | -1.484 |
PLE | -1.451 |
Token | Image |
Token ID | 5159 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
anders | +0.062 |
ourke | +0.054 |
[+ | +0.053 |
defences | +0.052 |
onent | +0.052 |
Neg logit contributions | |
MRI | -0.050 |
NH | -0.047 |
MO | -0.047 |
MR | -0.046 |
PLE | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
MRI | +0.495 |
NH | +0.471 |
MO | +0.471 |
MR | +0.459 |
blu | +0.457 |
Neg logit contributions | |
anders | -0.659 |
ourke | -0.572 |
[+ | -0.562 |
iris | -0.554 |
onent | -0.553 |
Token | tor |
Token ID | 13165 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
anders | +3.581 |
ourke | +3.025 |
[+ | +2.998 |
iris | +2.985 |
onent | +2.959 |
Neg logit contributions | |
MRI | -2.732 |
NH | -2.602 |
MO | -2.543 |
MR | -2.504 |
PLE | -2.477 |
Token | Sh |
Token ID | 911 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
anders | +1.737 |
ourke | +1.513 |
[+ | +1.497 |
defences | +1.469 |
onent | +1.464 |
Neg logit contributions | |
MRI | -1.187 |
NH | -1.121 |
MO | -1.107 |
MR | -1.081 |
PLE | -1.058 |
Token | kind |
Token ID | 11031 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
MRI | +0.289 |
NH | +0.273 |
MO | +0.271 |
MR | +0.265 |
PLE | +0.257 |
Neg logit contributions | |
anders | -0.376 |
[+ | -0.329 |
ourke | -0.326 |
defences | -0.323 |
onent | -0.315 |
Token | el |
Token ID | 417 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
anders | +0.120 |
ourke | +0.104 |
[+ | +0.103 |
defences | +0.101 |
onent | +0.100 |
Neg logit contributions | |
MRI | -0.090 |
NH | -0.085 |
MO | -0.084 |
MR | -0.082 |
PLE | -0.080 |
Token | , |
Token ID | 11 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
anders | +3.925 |
ourke | +3.358 |
[+ | +3.333 |
iris | +3.279 |
defences | +3.255 |
Neg logit contributions | |
MRI | -3.063 |
NH | -2.894 |
MO | -2.839 |
MR | -2.797 |
PLE | -2.760 |
Token | I |
Token ID | 314 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
anders | +3.444 |
ourke | +2.950 |
[+ | +2.927 |
defences | +2.860 |
iris | +2.840 |
Neg logit contributions | |
MRI | -3.054 |
NH | -2.884 |
MO | -2.833 |
MR | -2.784 |
PLE | -2.762 |
Token | hor |
Token ID | 17899 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
anders | +9.634 |
iris | +8.193 |
ourke | +8.087 |
[+ | +7.611 |
iar | +7.448 |
Neg logit contributions | |
MRI | -11.486 |
blu | -10.965 |
NH | -10.778 |
PLE | -10.717 |
MO | -10.614 |
Token | Mal |
Token ID | 4434 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
anders | +3.109 |
ourke | +2.747 |
[+ | +2.725 |
defences | +2.676 |
onent | +2.667 |
Neg logit contributions | |
MRI | -1.581 |
NH | -1.475 |
MO | -1.447 |
MR | -1.408 |
PLE | -1.375 |
Token | anch |
Token ID | 3702 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
anders | +1.304 |
ourke | +1.128 |
[+ | +1.123 |
defences | +1.101 |
onent | +1.088 |
Neg logit contributions | |
MRI | -1.054 |
NH | -0.998 |
MO | -0.991 |
MR | -0.966 |
PLE | -0.946 |
Token | ak |
Token ID | 461 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
anders | +4.615 |
ourke | +3.951 |
[+ | +3.882 |
iris | +3.840 |
onent | +3.821 |
Neg logit contributions | |
MRI | -3.704 |
NH | -3.520 |
MO | -3.465 |
MR | -3.406 |
PLE | -3.345 |
Token | and |
Token ID | 290 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
anders | +0.445 |
ourke | +0.389 |
[+ | +0.385 |
defences | +0.378 |
onent | +0.374 |
Neg logit contributions | |
MRI | -0.310 |
NH | -0.293 |
MO | -0.291 |
MR | -0.283 |
PLE | -0.277 |
Token | Reading |
Token ID | 36120 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
anders | +4.100 |
[+ | +2.892 |
ourke | +2.545 |
onent | +2.526 |
る | +2.521 |
Neg logit contributions | |
shepherd | -11.351 |
blu | -11.214 |
MRI | -11.135 |
Skydragon | -11.029 |
NH | -10.931 |
Token | 55 |
Token ID | 5996 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
anders | +0.463 |
ourke | +0.408 |
[+ | +0.403 |
defences | +0.397 |
onent | +0.395 |
Neg logit contributions | |
MRI | -0.253 |
NH | -0.238 |
MO | -0.233 |
MR | -0.228 |
NR | -0.223 |
Token | 80 |
Token ID | 1795 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
anders | +1.686 |
ourke | +1.451 |
[+ | +1.441 |
onent | +1.403 |
defences | +1.395 |
Neg logit contributions | |
MRI | -1.350 |
NH | -1.277 |
MO | -1.255 |
MR | -1.237 |
PLE | -1.225 |
Token | 953 |
Token ID | 49649 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
anders | +3.968 |
ourke | +3.251 |
[+ | +3.138 |
iris | +3.112 |
る | +3.037 |
Neg logit contributions | |
MRI | -5.327 |
NH | -5.221 |
MO | -5.171 |
blu | -5.054 |
MR | -5.027 |
Token | 16 |
Token ID | 1467 |
Feature activation | +9.32e+00 |
Pos logit contributions | |
anders | +1.443 |
[+ | +1.283 |
ourke | +1.282 |
defences | +1.254 |
onent | +1.254 |
Neg logit contributions | |
MRI | -0.602 |
NH | -0.555 |
MO | -0.548 |
MR | -0.526 |
PLE | -0.515 |
Token | 27 |
Token ID | 1983 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
anders | +6.072 |
[+ | +5.024 |
ourke | +4.865 |
onent | +4.786 |
る | +4.666 |
Neg logit contributions | |
MRI | -7.603 |
shepherd | -7.375 |
MO | -7.290 |
NH | -7.274 |
blu | -7.193 |
Token | 145 |
Token ID | 18781 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
anders | +6.017 |
[+ | +4.140 |
ourke | +4.048 |
onent | +4.026 |
る | +3.618 |
Neg logit contributions | |
MRI | -15.289 |
shepherd | -15.119 |
MO | -14.970 |
blu | -14.927 |
NR | -14.859 |
Token | Flat |
Token ID | 21939 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
anders | +2.465 |
[+ | +2.111 |
ourke | +2.104 |
onent | +2.045 |
defences | +2.042 |
Neg logit contributions | |
MRI | -2.122 |
NH | -2.018 |
MO | -1.992 |
MR | -1.952 |
PLE | -1.919 |
Token | buff |
Token ID | 36873 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
MRI | +0.321 |
NH | +0.295 |
MO | +0.290 |
MR | +0.283 |
blu | +0.272 |
Neg logit contributions | |
anders | -0.729 |
ourke | -0.649 |
[+ | -0.644 |
defences | -0.638 |
iris | -0.629 |
Token | ers |
Token ID | 364 |
Feature activation | +7.39e+00 |
Pos logit contributions | |
MRI | +1.282 |
NH | +1.160 |
MO | +1.150 |
MR | +1.127 |
NR | +1.088 |
Neg logit contributions | |
anders | -3.039 |
ourke | -2.755 |
[+ | -2.731 |
defences | -2.726 |
iris | -2.654 |
Token | Reading |
Token ID | 36120 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
anders | +2.711 |
[+ | +1.888 |
ourke | +1.694 |
onent | +1.640 |
iris | +1.604 |
Neg logit contributions | |
MRI | -8.298 |
NH | -8.104 |
blu | -8.086 |
MO | -8.082 |
shepherd | -8.070 |
Token | task |
Token ID | 4876 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
anders | +2.232 |
ourke | +1.856 |
[+ | +1.836 |
defences | +1.787 |
onent | +1.777 |
Neg logit contributions | |
MRI | -2.756 |
NH | -2.646 |
MO | -2.615 |
MR | -2.575 |
PLE | -2.540 |
Token | , |
Token ID | 11 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
MRI | +0.348 |
NH | +0.326 |
MO | +0.325 |
MR | +0.315 |
PLE | +0.307 |
Neg logit contributions | |
anders | -0.621 |
ourke | -0.548 |
[+ | -0.537 |
defences | -0.534 |
onent | -0.530 |
Token | unlike |
Token ID | 5023 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
MRI | +1.116 |
MO | +1.049 |
NH | +1.048 |
MR | +1.013 |
NR | +1.000 |
Neg logit contributions | |
anders | -1.845 |
ourke | -1.626 |
[+ | -1.588 |
onent | -1.571 |
iris | -1.569 |
Token | simply |
Token ID | 2391 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
anders | +1.753 |
ourke | +1.524 |
[+ | +1.502 |
defences | +1.468 |
onent | +1.467 |
Neg logit contributions | |
MRI | -1.275 |
NH | -1.203 |
MO | -1.194 |
MR | -1.164 |
blu | -1.145 |
Token | adding |
Token ID | 4375 |
Feature activation | +8.17e+00 |
Pos logit contributions | |
anders | +2.097 |
ourke | +1.814 |
[+ | +1.799 |
defences | +1.761 |
onent | +1.754 |
Neg logit contributions | |
MRI | -1.560 |
NH | -1.477 |
MO | -1.457 |
MR | -1.426 |
PLE | -1.398 |
Token | or |
Token ID | 393 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
anders | +7.139 |
[+ | +6.166 |
defences | +6.042 |
onent | +5.987 |
ourke | +5.974 |
Neg logit contributions | |
MRI | -5.292 |
NH | -5.006 |
MO | -4.946 |
MR | -4.852 |
PLE | -4.773 |
Token | removing |
Token ID | 10829 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
anders | +9.643 |
[+ | +8.472 |
ourke | +7.953 |
る | +7.869 |
onent | +7.768 |
Neg logit contributions | |
MRI | -11.676 |
NH | -10.997 |
MR | -10.419 |
PLE | -10.353 |
blu | -10.243 |
Token | pieces |
Token ID | 5207 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
anders | +3.488 |
[+ | +2.985 |
ourke | +2.974 |
defences | +2.929 |
onent | +2.905 |
Neg logit contributions | |
MRI | -2.773 |
NH | -2.637 |
MO | -2.605 |
MR | -2.552 |
PLE | -2.500 |
Token | from |
Token ID | 422 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
anders | +2.026 |
ourke | +1.778 |
[+ | +1.760 |
defences | +1.728 |
onent | +1.723 |
Neg logit contributions | |
MRI | -1.209 |
NH | -1.137 |
MO | -1.121 |
MR | -1.092 |
PLE | -1.068 |
Token | an |
Token ID | 281 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
anders | +4.744 |
[+ | +4.111 |
ourke | +4.062 |
defences | +4.034 |
onent | +3.999 |
Neg logit contributions | |
MRI | -3.418 |
NH | -3.242 |
MO | -3.197 |
MR | -3.113 |
PLE | -3.063 |
Token | array |
Token ID | 7177 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
anders | +2.743 |
[+ | +2.328 |
ourke | +2.324 |
onent | +2.266 |
defences | +2.261 |
Neg logit contributions | |
MRI | -2.521 |
NH | -2.407 |
MO | -2.376 |
MR | -2.328 |
PLE | -2.304 |
Token | of |
Token ID | 286 |
Feature activation | +8.38e+00 |
Pos logit contributions | |
anders | +3.360 |
[+ | +2.926 |
ourke | +2.911 |
defences | +2.875 |
iris | +2.832 |
Neg logit contributions | |
MRI | -2.718 |
NH | -2.540 |
MO | -2.495 |
MR | -2.454 |
blu | -2.411 |
Token | view |
Token ID | 1570 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
anders | +5.642 |
[+ | +4.672 |
ourke | +4.666 |
defences | +4.645 |
onent | +4.530 |
Neg logit contributions | |
MRI | -6.965 |
NH | -6.641 |
MO | -6.599 |
MR | -6.467 |
PLE | -6.287 |
Token | of |
Token ID | 286 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
anders | +2.747 |
ourke | +2.383 |
[+ | +2.374 |
defences | +2.339 |
onent | +2.305 |
Neg logit contributions | |
MRI | -2.169 |
NH | -2.040 |
MO | -2.014 |
MR | -1.973 |
PLE | -1.944 |
Token | Champions |
Token ID | 6662 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
anders | +2.602 |
ourke | +2.252 |
[+ | +2.237 |
defences | +2.199 |
onent | +2.179 |
Neg logit contributions | |
MRI | -1.925 |
NH | -1.817 |
MO | -1.794 |
MR | -1.753 |
PLE | -1.722 |
Token | Trophy |
Token ID | 25640 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
anders | +3.585 |
ourke | +3.087 |
[+ | +3.050 |
defences | +2.990 |
onent | +2.948 |
Neg logit contributions | |
MRI | -3.222 |
NH | -3.017 |
MO | -3.003 |
MR | -2.938 |
PLE | -2.862 |
Token | or |
Token ID | 393 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
anders | +0.859 |
ourke | +0.752 |
[+ | +0.743 |
defences | +0.728 |
onent | +0.728 |
Neg logit contributions | |
MRI | -0.539 |
NH | -0.510 |
MO | -0.502 |
MR | -0.490 |
PLE | -0.480 |
Token | the |
Token ID | 262 |
Feature activation | +9.88e+00 |
Pos logit contributions | |
anders | +9.135 |
[+ | +8.005 |
defences | +7.832 |
ourke | +7.817 |
onent | +7.450 |
Neg logit contributions | |
MRI | -11.762 |
MO | -10.874 |
NH | -10.799 |
MR | -10.557 |
PLE | -10.442 |
Token | World |
Token ID | 2159 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
anders | +6.410 |
[+ | +5.420 |
ourke | +5.352 |
defences | +5.304 |
onent | +5.096 |
Neg logit contributions | |
MRI | -8.362 |
NH | -7.841 |
MO | -7.820 |
MR | -7.627 |
PLE | -7.576 |
Token | Cup |
Token ID | 5454 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
anders | +1.027 |
ourke | +0.862 |
[+ | +0.855 |
defences | +0.827 |
onent | +0.824 |
Neg logit contributions | |
MRI | -1.166 |
NH | -1.112 |
MO | -1.104 |
MR | -1.082 |
PLE | -1.063 |
Token | , |
Token ID | 11 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
MRI | +0.516 |
NH | +0.491 |
MO | +0.484 |
MR | +0.470 |
PLE | +0.463 |
Neg logit contributions | |
anders | -0.908 |
ourke | -0.796 |
[+ | -0.781 |
onent | -0.770 |
defences | -0.768 |
Token | is |
Token ID | 318 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
anders | +2.347 |
ourke | +2.034 |
[+ | +2.021 |
defences | +1.980 |
onent | +1.966 |
Neg logit contributions | |
MRI | -1.706 |
NH | -1.607 |
MO | -1.589 |
MR | -1.553 |
PLE | -1.521 |
Token | is |
Token ID | 318 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
MRI | +1.345 |
NH | +1.273 |
MO | +1.257 |
MR | +1.252 |
PLE | +1.221 |
Neg logit contributions | |
anders | -1.550 |
ourke | -1.355 |
[+ | -1.321 |
defences | -1.308 |
iris | -1.292 |
Token | in |
Token ID | 287 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
MRI | +0.389 |
NH | +0.370 |
MO | +0.368 |
MR | +0.363 |
NR | +0.355 |
Neg logit contributions | |
anders | -0.463 |
ourke | -0.401 |
[+ | -0.391 |
defences | -0.383 |
onent | -0.382 |
Token | control |
Token ID | 1630 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
anders | +2.783 |
ourke | +2.416 |
[+ | +2.394 |
defences | +2.350 |
onent | +2.338 |
Neg logit contributions | |
MRI | -1.987 |
NH | -1.878 |
MO | -1.856 |
MR | -1.809 |
PLE | -1.777 |
Token | one |
Token ID | 530 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
anders | +3.303 |
ourke | +2.882 |
[+ | +2.861 |
defences | +2.799 |
onent | +2.788 |
Neg logit contributions | |
MRI | -2.201 |
NH | -2.076 |
MO | -2.050 |
MR | -1.997 |
PLE | -1.958 |
Token | way |
Token ID | 835 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
anders | +0.610 |
ourke | +0.529 |
[+ | +0.521 |
onent | +0.509 |
defences | +0.509 |
Neg logit contributions | |
MRI | -0.431 |
NH | -0.406 |
MO | -0.401 |
MR | -0.394 |
blu | -0.390 |
Token | or |
Token ID | 393 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
anders | +5.638 |
ourke | +4.944 |
[+ | +4.941 |
defences | +4.821 |
onent | +4.817 |
Neg logit contributions | |
MRI | -3.332 |
NH | -3.141 |
MO | -3.087 |
MR | -2.986 |
PLE | -2.913 |
Token | another |
Token ID | 1194 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
anders | +10.155 |
ourke | +8.843 |
[+ | +8.817 |
defences | +8.630 |
onent | +8.559 |
Neg logit contributions | |
MRI | -10.517 |
NH | -10.024 |
MO | -9.973 |
MR | -9.922 |
PLE | -9.584 |
Token | of |
Token ID | 286 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
anders | +1.658 |
ourke | +1.457 |
[+ | +1.439 |
defences | +1.416 |
onent | +1.410 |
Neg logit contributions | |
MRI | -0.962 |
NH | -0.902 |
MO | -0.892 |
MR | -0.870 |
PLE | -0.847 |
Token | his |
Token ID | 465 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
anders | +1.291 |
ourke | +1.121 |
[+ | +1.106 |
onent | +1.081 |
defences | +1.081 |
Neg logit contributions | |
MRI | -0.948 |
NH | -0.899 |
MO | -0.890 |
MR | -0.871 |
PLE | -0.855 |
Token | " |
Token ID | 366 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
MRI | +0.879 |
NH | +0.827 |
MO | +0.821 |
MR | +0.811 |
blu | +0.798 |
Neg logit contributions | |
anders | -1.326 |
ourke | -1.166 |
[+ | -1.145 |
onent | -1.121 |
iris | -1.118 |
Token | near |
Token ID | 40093 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
MRI | +3.126 |
MO | +2.952 |
NH | +2.937 |
MR | +2.935 |
PLE | +2.842 |
Neg logit contributions | |
anders | -4.807 |
[+ | -4.315 |
ourke | -4.282 |
defences | -4.129 |
onent | -4.095 |
Token | improved |
Token ID | 6596 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
anders | +3.069 |
[+ | +2.515 |
ourke | +2.491 |
onent | +2.418 |
defences | +2.402 |
Neg logit contributions | |
MRI | -4.202 |
NH | -4.015 |
MO | -3.977 |
MR | -3.919 |
PLE | -3.877 |
Token | in |
Token ID | 287 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
anders | +1.153 |
ourke | +1.012 |
[+ | +0.998 |
defences | +0.983 |
onent | +0.978 |
Neg logit contributions | |
MRI | -0.695 |
NH | -0.655 |
MO | -0.646 |
MR | -0.630 |
PLE | -0.616 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
anders | +1.577 |
ourke | +1.372 |
[+ | +1.355 |
defences | +1.331 |
iris | +1.328 |
Neg logit contributions | |
MRI | -1.118 |
NH | -1.058 |
MO | -1.047 |
MR | -1.023 |
blu | -1.005 |
Token | last |
Token ID | 938 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
MRI | +0.846 |
NH | +0.796 |
MO | +0.795 |
MR | +0.772 |
blu | +0.769 |
Neg logit contributions | |
anders | -1.562 |
ourke | -1.378 |
[+ | -1.354 |
onent | -1.343 |
defences | -1.339 |
Token | year |
Token ID | 614 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
MRI | +0.523 |
NH | +0.498 |
MO | +0.495 |
MR | +0.484 |
blu | +0.477 |
Neg logit contributions | |
anders | -0.750 |
ourke | -0.656 |
[+ | -0.641 |
onent | -0.630 |
defences | -0.630 |
Token | or |
Token ID | 393 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
anders | +0.556 |
ourke | +0.491 |
[+ | +0.481 |
defences | +0.478 |
onent | +0.475 |
Neg logit contributions | |
MRI | -0.308 |
NH | -0.289 |
MO | -0.287 |
MR | -0.278 |
PLE | -0.271 |
Token | so |
Token ID | 523 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
anders | +9.600 |
ourke | +8.279 |
[+ | +8.072 |
defences | +7.937 |
onent | +7.878 |
Neg logit contributions | |
MRI | -11.495 |
NH | -10.879 |
MO | -10.582 |
MR | -10.388 |
blu | -10.159 |
Token | . |
Token ID | 13 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
anders | +1.819 |
ourke | +1.600 |
[+ | +1.581 |
defences | +1.559 |
onent | +1.551 |
Neg logit contributions | |
MRI | -1.030 |
NH | -0.968 |
MO | -0.954 |
MR | -0.928 |
PLE | -0.906 |
Token | I |
Token ID | 314 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
MRI | +0.563 |
NH | +0.529 |
MO | +0.524 |
MR | +0.510 |
blu | +0.498 |
Neg logit contributions | |
anders | -0.985 |
ourke | -0.868 |
defences | -0.850 |
[+ | -0.843 |
iris | -0.838 |
Token | believe |
Token ID | 1975 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
anders | +2.137 |
ourke | +1.846 |
[+ | +1.826 |
defences | +1.790 |
onent | +1.782 |
Neg logit contributions | |
MRI | -1.649 |
NH | -1.564 |
MO | -1.545 |
MR | -1.512 |
PLE | -1.482 |
Token | we |
Token ID | 356 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
MRI | +0.583 |
NH | +0.551 |
MO | +0.547 |
MR | +0.532 |
blu | +0.528 |
Neg logit contributions | |
anders | -0.895 |
ourke | -0.779 |
[+ | -0.768 |
defences | -0.757 |
iris | -0.756 |
Token | . |
Token ID | 13 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
anders | +3.891 |
ourke | +3.395 |
[+ | +3.368 |
defences | +3.301 |
onent | +3.284 |
Neg logit contributions | |
MRI | -2.491 |
NH | -2.334 |
MO | -2.308 |
MR | -2.249 |
PLE | -2.200 |
Token | Naturally |
Token ID | 30413 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
anders | +2.641 |
ourke | +2.293 |
[+ | +2.281 |
defences | +2.225 |
onent | +2.221 |
Neg logit contributions | |
MRI | -1.828 |
NH | -1.723 |
MO | -1.700 |
MR | -1.662 |
PLE | -1.624 |
Token | , |
Token ID | 11 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
anders | +1.606 |
ourke | +1.403 |
[+ | +1.381 |
onent | +1.356 |
defences | +1.355 |
Neg logit contributions | |
MRI | -1.087 |
NH | -1.033 |
MO | -1.024 |
MR | -0.996 |
blu | -0.978 |
Token | having |
Token ID | 1719 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
anders | +0.671 |
ourke | +0.586 |
[+ | +0.575 |
onent | +0.567 |
defences | +0.565 |
Neg logit contributions | |
MRI | -0.465 |
NH | -0.445 |
MO | -0.440 |
MR | -0.428 |
blu | -0.424 |
Token | an |
Token ID | 281 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
anders | +4.712 |
[+ | +4.038 |
ourke | +4.031 |
defences | +3.978 |
onent | +3.900 |
Neg logit contributions | |
MRI | -3.642 |
NH | -3.409 |
MO | -3.368 |
MR | -3.297 |
PLE | -3.223 |
Token | or |
Token ID | 393 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
anders | +0.321 |
ourke | +0.277 |
[+ | +0.271 |
defences | +0.267 |
onent | +0.265 |
Neg logit contributions | |
MRI | -0.265 |
NH | -0.253 |
MO | -0.251 |
MR | -0.245 |
NR | -0.243 |
Token | chard |
Token ID | 30215 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
anders | +7.711 |
ourke | +6.759 |
onent | +6.034 |
[+ | +5.906 |
uper | +5.784 |
Neg logit contributions | |
MRI | -13.455 |
NH | -12.750 |
MR | -12.622 |
MO | -12.525 |
NR | -12.294 |
Token | setting |
Token ID | 4634 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
MRI | +0.504 |
NH | +0.487 |
MO | +0.484 |
MR | +0.468 |
NR | +0.466 |
Neg logit contributions | |
anders | -0.720 |
ourke | -0.626 |
[+ | -0.617 |
onent | -0.606 |
defences | -0.602 |
Token | is |
Token ID | 318 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
MRI | +0.185 |
NH | +0.177 |
MO | +0.175 |
MR | +0.170 |
NR | +0.169 |
Neg logit contributions | |
anders | -0.265 |
ourke | -0.231 |
[+ | -0.226 |
onent | -0.223 |
defences | -0.222 |
Token | smart |
Token ID | 4451 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
anders | +0.336 |
ourke | +0.293 |
[+ | +0.290 |
defences | +0.285 |
onent | +0.284 |
Neg logit contributions | |
MRI | -0.212 |
NH | -0.200 |
MO | -0.197 |
MR | -0.192 |
PLE | -0.188 |
Token | , |
Token ID | 11 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
MRI | +1.566 |
MO | +1.486 |
NH | +1.479 |
NR | +1.439 |
MR | +1.428 |
Neg logit contributions | |
anders | -2.539 |
ourke | -2.217 |
[+ | -2.152 |
onent | -2.124 |
iris | -2.114 |
Token | , |
Token ID | 11 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
MRI | +1.348 |
NH | +1.292 |
MO | +1.276 |
MR | +1.240 |
blu | +1.220 |
Neg logit contributions | |
anders | -2.413 |
ourke | -2.106 |
[+ | -2.066 |
onent | -2.047 |
defences | -2.029 |
Token | which |
Token ID | 543 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
MRI | +0.413 |
NH | +0.394 |
MO | +0.391 |
MR | +0.381 |
blu | +0.376 |
Neg logit contributions | |
anders | -0.603 |
ourke | -0.523 |
[+ | -0.516 |
onent | -0.508 |
defences | -0.505 |
Token | is |
Token ID | 318 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
MRI | +0.014 |
NH | +0.013 |
MO | +0.013 |
MR | +0.013 |
blu | +0.013 |
Neg logit contributions | |
anders | -0.020 |
ourke | -0.018 |
[+ | -0.017 |
onent | -0.017 |
defences | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
MRI | +0.996 |
NH | +0.950 |
MO | +0.944 |
MR | +0.920 |
blu | +0.910 |
Neg logit contributions | |
anders | -1.523 |
ourke | -1.320 |
[+ | -1.299 |
onent | -1.281 |
iris | -1.276 |
Token | bread |
Token ID | 8509 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
MRI | +2.670 |
MO | +2.561 |
NH | +2.556 |
blu | +2.551 |
NR | +2.509 |
Neg logit contributions | |
anders | -4.041 |
ourke | -3.482 |
[+ | -3.460 |
onent | -3.395 |
iris | -3.389 |
Token | and |
Token ID | 290 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
MRI | +1.270 |
NH | +1.218 |
MO | +1.210 |
MR | +1.167 |
blu | +1.144 |
Neg logit contributions | |
anders | -2.027 |
ourke | -1.773 |
[+ | -1.750 |
onent | -1.724 |
defences | -1.713 |
Token | butter |
Token ID | 9215 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
anders | +5.446 |
ourke | +3.724 |
る | +3.717 |
[+ | +3.657 |
defences | +3.648 |
Neg logit contributions | |
MRI | -15.699 |
NH | -14.895 |
LESS | -14.347 |
MR | -14.284 |
LR | -14.198 |
Token | for |
Token ID | 329 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
MRI | +0.600 |
NH | +0.574 |
MO | +0.570 |
MR | +0.553 |
blu | +0.546 |
Neg logit contributions | |
anders | -0.962 |
ourke | -0.831 |
[+ | -0.824 |
onent | -0.806 |
iris | -0.806 |
Token | these |
Token ID | 777 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
MRI | +0.802 |
MO | +0.771 |
NH | +0.767 |
blu | +0.744 |
MR | +0.744 |
Neg logit contributions | |
anders | -1.233 |
ourke | -1.077 |
[+ | -1.064 |
onent | -1.041 |
iris | -1.040 |
Token | guys |
Token ID | 3730 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
MRI | +1.866 |
MO | +1.813 |
NH | +1.789 |
blu | +1.750 |
MR | +1.734 |
Neg logit contributions | |
anders | -2.754 |
ourke | -2.376 |
[+ | -2.348 |
onent | -2.309 |
iris | -2.301 |
Token | . |
Token ID | 13 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
MRI | +1.037 |
NH | +0.986 |
MO | +0.979 |
MR | +0.948 |
NR | +0.928 |
Neg logit contributions | |
anders | -1.938 |
ourke | -1.705 |
[+ | -1.675 |
onent | -1.672 |
defences | -1.665 |
Token | . |
Token ID | 13 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
MRI | +0.692 |
NH | +0.662 |
MO | +0.646 |
MR | +0.629 |
blu | +0.615 |
Neg logit contributions | |
anders | -1.230 |
ourke | -1.080 |
[+ | -1.068 |
onent | -1.058 |
defences | -1.053 |
Token | ( |
Token ID | 357 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
anders | +2.670 |
ourke | +2.327 |
[+ | +2.306 |
defences | +2.259 |
onent | +2.252 |
Neg logit contributions | |
MRI | -1.790 |
NH | -1.689 |
MO | -1.667 |
MR | -1.627 |
PLE | -1.594 |
Token | Wa |
Token ID | 33484 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
anders | +1.836 |
ourke | +1.582 |
[+ | +1.567 |
defences | +1.534 |
onent | +1.527 |
Neg logit contributions | |
MRI | -1.483 |
NH | -1.408 |
MO | -1.392 |
MR | -1.363 |
PLE | -1.337 |
Token | ub |
Token ID | 549 |
Feature activation | +7.38e+00 |
Pos logit contributions | |
MRI | +2.081 |
NH | +1.982 |
MO | +1.940 |
MR | +1.898 |
blu | +1.853 |
Neg logit contributions | |
anders | -2.305 |
defences | -1.988 |
[+ | -1.985 |
ourke | -1.979 |
iris | -1.899 |
Token | ges |
Token ID | 3212 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
anders | +5.335 |
[+ | +4.255 |
ourke | +4.250 |
iris | +4.159 |
onent | +4.150 |
Neg logit contributions | |
MRI | -5.994 |
NH | -5.781 |
MO | -5.737 |
MR | -5.650 |
blu | -5.618 |
Token | hig |
Token ID | 25196 |
Feature activation | -1.81e+01 |
Pos logit contributions | |
MRI | +3.963 |
NH | +3.836 |
MR | +3.688 |
MO | +3.679 |
NR | +3.617 |
Neg logit contributions | |
anders | -3.280 |
defences | -2.793 |
ourke | -2.744 |
[+ | -2.702 |
onent | -2.611 |
Token | Rice |
Token ID | 13823 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
NR | +5.828 |
MRI | +5.017 |
NH | +4.765 |
Rx | +4.301 |
NR | +4.274 |
Neg logit contributions | |
anders | -19.712 |
ikuman | -17.907 |
ourke | -17.595 |
jriwal | -17.552 |
defences | -17.526 |
Token | / |
Token ID | 14 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
MRI | +1.710 |
NH | +1.578 |
MO | +1.507 |
NR | +1.468 |
MR | +1.438 |
Neg logit contributions | |
anders | -6.827 |
ourke | -6.171 |
defences | -6.102 |
berra | -6.044 |
iris | -6.039 |
Token | CBC |
Token ID | 29208 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
anders | +1.324 |
ourke | +1.162 |
[+ | +1.151 |
defences | +1.129 |
onent | +1.126 |
Neg logit contributions | |
MRI | -0.782 |
NH | -0.734 |
MO | -0.724 |
MR | -0.705 |
PLE | -0.689 |
Token | ) |
Token ID | 8 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
MRI | +0.179 |
NH | +0.169 |
MO | +0.167 |
MR | +0.163 |
PLE | +0.160 |
Neg logit contributions | |
anders | -0.259 |
ourke | -0.225 |
[+ | -0.223 |
defences | -0.219 |
onent | -0.218 |
Token |
|
Token ID | 198 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
anders | +3.439 |
ourke | +2.992 |
[+ | +2.973 |
defences | +2.904 |
onent | +2.896 |
Neg logit contributions | |
MRI | -2.327 |
NH | -2.200 |
MO | -2.166 |
MR | -2.120 |
PLE | -2.073 |
Token | . |
Token ID | 13 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
MRI | +1.030 |
NH | +0.972 |
MO | +0.959 |
MR | +0.934 |
NR | +0.910 |
Neg logit contributions | |
anders | -2.001 |
ourke | -1.770 |
[+ | -1.748 |
defences | -1.728 |
iris | -1.718 |
Token | We |
Token ID | 775 |
Feature activation | -9.22e+00 |
Pos logit contributions | |
anders | +3.188 |
ourke | +2.744 |
[+ | +2.732 |
defences | +2.659 |
onent | +2.650 |
Neg logit contributions | |
MRI | -2.469 |
NH | -2.330 |
MO | -2.301 |
MR | -2.247 |
PLE | -2.215 |
Token | need |
Token ID | 761 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
MRI | +3.139 |
MR | +2.938 |
NH | +2.888 |
NR | +2.807 |
MO | +2.778 |
Neg logit contributions | |
anders | -10.750 |
ourke | -9.592 |
onent | -9.452 |
defences | -9.445 |
jriwal | -9.283 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
MRI | +1.293 |
NH | +1.224 |
MO | +1.201 |
MR | +1.184 |
blu | +1.164 |
Neg logit contributions | |
anders | -2.169 |
ourke | -1.898 |
[+ | -1.851 |
onent | -1.841 |
defences | -1.839 |
Token | courts |
Token ID | 8028 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
anders | +1.073 |
ourke | +0.889 |
[+ | +0.873 |
onent | +0.850 |
defences | +0.847 |
Neg logit contributions | |
MRI | -1.383 |
NH | -1.330 |
MO | -1.318 |
MR | -1.297 |
blu | -1.278 |
Token | to |
Token ID | 284 |
Feature activation | -1.65e+01 |
Pos logit contributions | |
MRI | +4.707 |
MO | +4.577 |
NH | +4.516 |
NR | +4.472 |
MR | +4.422 |
Neg logit contributions | |
anders | -12.466 |
ikuman | -11.181 |
ourke | -11.024 |
jriwal | -10.898 |
ricanes | -10.810 |
Token | give |
Token ID | 1577 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
MRI | +2.254 |
NR | +2.169 |
blu | +2.104 |
MR | +1.994 |
ificate | +1.962 |
Neg logit contributions | |
anders | -20.882 |
ワン | -18.999 |
iris | -18.690 |
raviolet | -18.611 |
ikuman | -18.587 |
Token | us |
Token ID | 514 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
anders | +2.681 |
ourke | +2.383 |
[+ | +2.371 |
defences | +2.333 |
onent | +2.324 |
Neg logit contributions | |
MRI | -1.102 |
NH | -1.016 |
MO | -0.996 |
MR | -0.960 |
PLE | -0.937 |
Token | back |
Token ID | 736 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
anders | +2.063 |
ourke | +1.777 |
[+ | +1.761 |
defences | +1.731 |
onent | +1.709 |
Neg logit contributions | |
MRI | -1.614 |
NH | -1.527 |
MO | -1.509 |
MR | -1.469 |
PLE | -1.455 |
Token | our |
Token ID | 674 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
anders | +0.366 |
ourke | +0.316 |
[+ | +0.310 |
onent | +0.303 |
defences | +0.303 |
Neg logit contributions | |
MRI | -0.300 |
NH | -0.286 |
MO | -0.282 |
MR | -0.279 |
NR | -0.275 |
Token | rights |
Token ID | 2489 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
MRI | +0.399 |
NH | +0.375 |
MO | +0.372 |
MR | +0.366 |
NR | +0.359 |
Neg logit contributions | |
anders | -0.622 |
ourke | -0.549 |
[+ | -0.541 |
onent | -0.532 |
defences | -0.526 |
Token | made |
Token ID | 925 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
anders | +0.072 |
ourke | +0.063 |
[+ | +0.062 |
defences | +0.061 |
onent | +0.061 |
Neg logit contributions | |
MRI | -0.049 |
NH | -0.047 |
MO | -0.047 |
MR | -0.045 |
PLE | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
anders | +1.061 |
ourke | +0.930 |
[+ | +0.915 |
defences | +0.902 |
onent | +0.900 |
Neg logit contributions | |
MRI | -0.649 |
NH | -0.612 |
MO | -0.604 |
MR | -0.591 |
blu | -0.575 |
Token | � |
Token ID | 564 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
anders | +0.597 |
ourke | +0.526 |
defences | +0.516 |
[+ | +0.513 |
iris | +0.511 |
Neg logit contributions | |
MRI | -0.349 |
NH | -0.329 |
MO | -0.323 |
MR | -0.318 |
NR | -0.311 |
Token | � |
Token ID | 250 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
MRI | +2.750 |
NH | +2.561 |
MO | +2.523 |
PLE | +2.507 |
MR | +2.471 |
Neg logit contributions | |
anders | -5.033 |
ourke | -4.462 |
defences | -4.337 |
iris | -4.326 |
[+ | -4.268 |
Token | Mar |
Token ID | 7676 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
MRI | +0.916 |
NH | +0.862 |
MO | +0.841 |
MR | +0.836 |
PLE | +0.815 |
Neg logit contributions | |
anders | -1.604 |
ourke | -1.416 |
defences | -1.404 |
[+ | -1.396 |
iris | -1.375 |
Token | tha |
Token ID | 12898 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
MRI | +6.799 |
NH | +6.699 |
MR | +6.468 |
phys | +6.412 |
MO | +6.408 |
Neg logit contributions | |
anders | -3.221 |
る | -2.421 |
defences | -2.405 |
[+ | -2.395 |
ourke | -2.309 |
Token | … |
Token ID | 3926 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
MRI | +8.268 |
NR | +8.109 |
NH | +8.002 |
MR | +7.863 |
MO | +7.742 |
Neg logit contributions | |
anders | -12.760 |
ourke | -11.213 |
iris | -11.162 |
onent | -11.119 |
defences | -11.058 |
Token | immediately |
Token ID | 3393 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
MRI | +2.390 |
NH | +2.270 |
MO | +2.245 |
MR | +2.240 |
PLE | +2.179 |
Neg logit contributions | |
anders | -3.354 |
ourke | -2.939 |
defences | -2.884 |
[+ | -2.861 |
onent | -2.853 |
Token | recognized |
Token ID | 8018 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
MRI | +3.343 |
MO | +3.193 |
NH | +3.151 |
NR | +3.123 |
MR | +3.105 |
Neg logit contributions | |
anders | -5.200 |
ourke | -4.642 |
onent | -4.411 |
iris | -4.393 |
defences | -4.380 |
Token | that |
Token ID | 326 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
MRI | +1.810 |
NH | +1.714 |
MO | +1.698 |
MR | +1.680 |
blu | +1.658 |
Neg logit contributions | |
anders | -2.791 |
ourke | -2.440 |
iris | -2.377 |
[+ | -2.373 |
onent | -2.369 |
Token | was |
Token ID | 373 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
MRI | +2.909 |
NH | +2.739 |
MO | +2.726 |
MR | +2.714 |
blu | +2.684 |
Neg logit contributions | |
anders | -4.756 |
ourke | -4.148 |
iris | -4.101 |
onent | -4.035 |
defences | -4.008 |
Token | . |
Token ID | 13 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
MRI | +0.362 |
NH | +0.342 |
MO | +0.339 |
MR | +0.328 |
PLE | +0.318 |
Neg logit contributions | |
anders | -0.672 |
ourke | -0.596 |
[+ | -0.590 |
onent | -0.580 |
defences | -0.577 |
Token | ( |
Token ID | 357 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
anders | +0.840 |
ourke | +0.743 |
defences | +0.726 |
[+ | +0.726 |
onent | +0.718 |
Neg logit contributions | |
MRI | -0.481 |
NH | -0.448 |
MO | -0.447 |
MR | -0.431 |
NR | -0.422 |
Token | Wa |
Token ID | 33484 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
anders | +2.650 |
ourke | +2.284 |
[+ | +2.259 |
defences | +2.211 |
onent | +2.204 |
Neg logit contributions | |
MRI | -2.081 |
NH | -1.974 |
MO | -1.950 |
MR | -1.908 |
PLE | -1.873 |
Token | ub |
Token ID | 549 |
Feature activation | +9.69e+00 |
Pos logit contributions | |
MRI | +0.125 |
NH | +0.119 |
MO | +0.118 |
MR | +0.115 |
PLE | +0.113 |
Neg logit contributions | |
anders | -0.126 |
ourke | -0.106 |
[+ | -0.105 |
defences | -0.103 |
onent | -0.102 |
Token | ges |
Token ID | 3212 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
anders | +6.666 |
ourke | +5.175 |
[+ | +5.138 |
iris | +5.094 |
onent | +5.060 |
Neg logit contributions | |
MRI | -8.020 |
NH | -7.779 |
MO | -7.693 |
MR | -7.642 |
PLE | -7.575 |
Token | hig |
Token ID | 25196 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
MRI | +0.936 |
NH | +0.903 |
MO | +0.885 |
MR | +0.876 |
PLE | +0.862 |
Neg logit contributions | |
anders | -0.679 |
ourke | -0.553 |
[+ | -0.549 |
defences | -0.546 |
onent | -0.527 |
Token | Rice |
Token ID | 13823 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
NR | +5.537 |
MRI | +5.019 |
NH | +4.734 |
MR | +4.348 |
Rx | +4.295 |
Neg logit contributions | |
anders | -17.209 |
ikuman | -15.290 |
ourke | -15.239 |
defences | -15.108 |
jriwal | -15.060 |
Token | / |
Token ID | 14 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
MRI | +1.519 |
NH | +1.394 |
MO | +1.340 |
NR | +1.287 |
MR | +1.283 |
Neg logit contributions | |
anders | -5.709 |
ourke | -5.142 |
defences | -5.070 |
[+ | -5.034 |
iris | -5.032 |
Token | CBC |
Token ID | 29208 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
anders | +3.875 |
ourke | +3.390 |
[+ | +3.337 |
iris | +3.278 |
onent | +3.276 |
Neg logit contributions | |
MRI | -2.538 |
NH | -2.385 |
MO | -2.356 |
blu | -2.309 |
MR | -2.293 |
Token | ) |
Token ID | 8 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
MRI | +0.461 |
NH | +0.435 |
MO | +0.429 |
MR | +0.418 |
PLE | +0.410 |
Neg logit contributions | |
anders | -0.709 |
ourke | -0.618 |
[+ | -0.611 |
defences | -0.604 |
onent | -0.599 |
Token | Carter |
Token ID | 10831 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
anders | +0.452 |
ourke | +0.399 |
[+ | +0.391 |
defences | +0.388 |
onent | +0.387 |
Neg logit contributions | |
MRI | -0.252 |
NH | -0.234 |
MO | -0.233 |
MR | -0.226 |
PLE | -0.220 |
Token | , |
Token ID | 11 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
anders | +0.703 |
ourke | +0.618 |
[+ | +0.611 |
defences | +0.601 |
onent | +0.599 |
Neg logit contributions | |
MRI | -0.412 |
NH | -0.387 |
MO | -0.383 |
MR | -0.372 |
PLE | -0.364 |
Token | you |
Token ID | 345 |
Feature activation | -9.75e-02 |
Pos logit contributions | |
anders | +0.750 |
ourke | +0.655 |
[+ | +0.645 |
defences | +0.634 |
onent | +0.634 |
Neg logit contributions | |
MRI | -0.474 |
NH | -0.449 |
MO | -0.445 |
MR | -0.432 |
PLE | -0.426 |
Token | can |
Token ID | 460 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
MRI | +0.069 |
NH | +0.066 |
MO | +0.065 |
MR | +0.064 |
PLE | +0.063 |
Neg logit contributions | |
anders | -0.081 |
ourke | -0.070 |
[+ | -0.070 |
onent | -0.068 |
defences | -0.068 |
Token | watch |
Token ID | 2342 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
anders | +0.134 |
ourke | +0.116 |
[+ | +0.114 |
defences | +0.112 |
onent | +0.111 |
Neg logit contributions | |
MRI | -0.097 |
NH | -0.091 |
MO | -0.091 |
MR | -0.088 |
blu | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
MRI | +2.061 |
NH | +1.988 |
MO | +1.966 |
NR | +1.935 |
blu | +1.895 |
Neg logit contributions | |
anders | -3.223 |
ourke | -2.863 |
[+ | -2.732 |
iris | -2.730 |
onent | -2.700 |
Token | match |
Token ID | 2872 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
MRI | +2.109 |
NH | +2.026 |
MO | +2.013 |
NR | +1.982 |
blu | +1.954 |
Neg logit contributions | |
anders | -2.768 |
ourke | -2.418 |
[+ | -2.311 |
onent | -2.299 |
iris | -2.286 |
Token | from |
Token ID | 422 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
MRI | +7.588 |
NH | +7.527 |
NR | +7.435 |
MO | +7.340 |
MR | +7.231 |
Neg logit contributions | |
anders | -13.459 |
ourke | -12.471 |
onent | -11.561 |
defences | -11.538 |
る | -11.399 |
Token | your |
Token ID | 534 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
MRI | +1.984 |
MO | +1.854 |
NH | +1.841 |
NR | +1.825 |
blu | +1.817 |
Neg logit contributions | |
anders | -3.235 |
ourke | -2.835 |
[+ | -2.750 |
onent | -2.726 |
iris | -2.717 |
Token | couch |
Token ID | 18507 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
anders | +3.822 |
ourke | +3.331 |
[+ | +3.312 |
defences | +3.246 |
onent | +3.224 |
Neg logit contributions | |
MRI | -2.632 |
NH | -2.503 |
MO | -2.463 |
MR | -2.389 |
PLE | -2.353 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
anders | +3.071 |
ourke | +2.678 |
[+ | +2.659 |
defences | +2.603 |
onent | +2.594 |
Neg logit contributions | |
MRI | -1.990 |
NH | -1.874 |
MO | -1.848 |
MR | -1.803 |
PLE | -1.763 |
Token | as |
Token ID | 355 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
MRI | +0.870 |
NH | +0.823 |
MO | +0.820 |
MR | +0.803 |
blu | +0.801 |
Neg logit contributions | |
anders | -1.336 |
ourke | -1.171 |
[+ | -1.148 |
onent | -1.130 |
defences | -1.130 |
Token | Atomic |
Token ID | 28976 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
MRI | +1.052 |
NH | +0.995 |
MO | +0.994 |
MR | +0.975 |
blu | +0.963 |
Neg logit contributions | |
anders | -1.071 |
ourke | -0.917 |
[+ | -0.879 |
defences | -0.877 |
onent | -0.875 |
Token | < |
Token ID | 1279 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
anders | +1.453 |
ourke | +1.273 |
[+ | +1.253 |
defences | +1.236 |
onent | +1.230 |
Neg logit contributions | |
MRI | -0.944 |
NH | -0.890 |
MO | -0.879 |
MR | -0.857 |
PLE | -0.838 |
Token | T |
Token ID | 309 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
MRI | +0.157 |
NH | +0.145 |
MO | +0.143 |
MR | +0.139 |
blu | +0.135 |
Neg logit contributions | |
anders | -0.339 |
ourke | -0.300 |
[+ | -0.297 |
defences | -0.292 |
iris | -0.292 |
Token | > |
Token ID | 1875 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
MRI | +2.641 |
NH | +2.464 |
MO | +2.445 |
MR | +2.376 |
blu | +2.340 |
Neg logit contributions | |
anders | -6.764 |
ourke | -6.005 |
[+ | -5.956 |
defences | -5.924 |
berra | -5.839 |
Token | { |
Token ID | 1391 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
MRI | +1.093 |
MO | +1.026 |
NH | +1.022 |
MR | +0.992 |
NR | +0.972 |
Neg logit contributions | |
anders | -1.769 |
ourke | -1.563 |
defences | -1.514 |
[+ | -1.510 |
onent | -1.506 |
Token | pub |
Token ID | 2240 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
MRI | +4.317 |
MO | +4.044 |
MR | +3.945 |
blu | +3.901 |
NH | +3.895 |
Neg logit contributions | |
anders | -8.126 |
ourke | -7.181 |
defences | -6.982 |
onent | -6.927 |
iris | -6.921 |
Token | fn |
Token ID | 24714 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
MRI | +6.089 |
MO | +5.338 |
MR | +5.248 |
NR | +5.184 |
blu | +5.003 |
Neg logit contributions | |
anders | -16.024 |
ourke | -14.408 |
defences | -14.107 |
る | -14.009 |
iris | -13.814 |
Token | load |
Token ID | 3440 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
MRI | +1.661 |
NH | +1.570 |
MO | +1.564 |
blu | +1.548 |
MR | +1.530 |
Neg logit contributions | |
anders | -1.789 |
ourke | -1.524 |
[+ | -1.460 |
onent | -1.452 |
defences | -1.449 |
Token | < |
Token ID | 1279 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
anders | +0.219 |
ourke | +0.189 |
[+ | +0.185 |
defences | +0.183 |
onent | +0.180 |
Neg logit contributions | |
MRI | -0.199 |
NH | -0.188 |
MO | -0.187 |
MR | -0.183 |
PLE | -0.180 |
Token | ' |
Token ID | 705 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
MRI | +1.522 |
NH | +1.428 |
MO | +1.414 |
MR | +1.390 |
NR | +1.365 |
Neg logit contributions | |
anders | -2.663 |
ourke | -2.355 |
[+ | -2.297 |
iris | -2.274 |
onent | -2.250 |
Token | a |
Token ID | 64 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
MRI | +4.704 |
NH | +4.435 |
MO | +4.412 |
MR | +4.399 |
blu | +4.330 |
Neg logit contributions | |
anders | -10.516 |
ourke | -9.226 |
[+ | -9.200 |
defences | -8.961 |
jriwal | -8.931 |
Token | ( |
Token ID | 357 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
MRI | +2.661 |
NH | +2.576 |
MO | +2.531 |
MR | +2.449 |
NR | +2.426 |
Neg logit contributions | |
anders | -3.685 |
ourke | -3.197 |
iris | -3.117 |
[+ | -3.116 |
defences | -3.094 |
Token | T |
Token ID | 51 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
anders | +2.366 |
ourke | +2.104 |
[+ | +2.086 |
defences | +2.052 |
onent | +2.047 |
Neg logit contributions | |
MRI | -1.040 |
NH | -0.962 |
MO | -0.944 |
MR | -0.914 |
PLE | -0.889 |
Token | ( |
Token ID | 7 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
NH | +4.655 |
MRI | +4.550 |
MO | +4.515 |
MR | +4.327 |
NR | +4.104 |
Neg logit contributions | |
anders | -11.401 |
iris | -9.943 |
[+ | -9.930 |
ourke | -9.891 |
defences | -9.863 |
Token | t |
Token ID | 83 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
anders | +3.422 |
ourke | +3.039 |
[+ | +3.013 |
onent | +2.960 |
defences | +2.952 |
Neg logit contributions | |
MRI | -1.548 |
NH | -1.431 |
MO | -1.407 |
MR | -1.368 |
PLE | -1.329 |
Token | )- |
Token ID | 13219 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
anders | +3.542 |
ourke | +2.979 |
[+ | +2.951 |
onent | +2.908 |
defences | +2.886 |
Neg logit contributions | |
MRI | -3.431 |
NH | -3.236 |
MO | -3.229 |
MR | -3.166 |
blu | -3.116 |
Token | T |
Token ID | 309 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
MRI | +1.735 |
NH | +1.668 |
MO | +1.635 |
MR | +1.569 |
NR | +1.547 |
Neg logit contributions | |
anders | -4.480 |
ourke | -3.993 |
[+ | -3.905 |
iris | -3.895 |
defences | -3.881 |
Token | 0 |
Token ID | 657 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
NH | +5.558 |
MO | +5.314 |
MRI | +5.245 |
NR | +5.140 |
MR | +5.094 |
Neg logit contributions | |
anders | -16.105 |
ourke | -14.002 |
[+ | -13.739 |
iris | -13.702 |
defences | -13.628 |
Token | ) |
Token ID | 1267 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
MRI | +2.989 |
NH | +2.854 |
MO | +2.772 |
MR | +2.711 |
NR | +2.650 |
Neg logit contributions | |
anders | -6.190 |
ourke | -5.433 |
[+ | -5.376 |
iris | -5.340 |
defences | -5.287 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
MRI | +2.327 |
NH | +2.240 |
MO | +2.177 |
NR | +2.104 |
MR | +2.103 |
Neg logit contributions | |
anders | -4.193 |
ourke | -3.692 |
defences | -3.588 |
iris | -3.585 |
onent | -3.585 |
Token |
|
Token ID | 198 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
anders | +0.455 |
ourke | +0.401 |
[+ | +0.398 |
defences | +0.390 |
onent | +0.389 |
Neg logit contributions | |
MRI | -0.244 |
NH | -0.228 |
MO | -0.224 |
MR | -0.218 |
PLE | -0.213 |
Token | The |
Token ID | 464 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
MRI | +0.148 |
NH | +0.140 |
MO | +0.138 |
MR | +0.134 |
PLE | +0.131 |
Neg logit contributions | |
anders | -0.270 |
ourke | -0.239 |
[+ | -0.238 |
defences | -0.235 |
onent | -0.232 |
Token | . |
Token ID | 13 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
MRI | +1.379 |
NH | +1.314 |
MO | +1.299 |
MR | +1.247 |
NR | +1.228 |
Neg logit contributions | |
anders | -2.820 |
ourke | -2.525 |
[+ | -2.456 |
defences | -2.453 |
onent | -2.438 |
Token | ( |
Token ID | 357 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
anders | +4.002 |
[+ | +3.423 |
ourke | +3.403 |
onent | +3.291 |
iris | +3.291 |
Neg logit contributions | |
MRI | -3.559 |
NH | -3.388 |
MO | -3.316 |
MR | -3.286 |
blu | -3.216 |
Token | Wa |
Token ID | 33484 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
anders | +3.483 |
ourke | +2.995 |
[+ | +2.955 |
iris | +2.892 |
defences | +2.891 |
Neg logit contributions | |
MRI | -2.750 |
NH | -2.607 |
MO | -2.573 |
MR | -2.520 |
blu | -2.490 |
Token | ub |
Token ID | 549 |
Feature activation | +9.54e+00 |
Pos logit contributions | |
MRI | +1.096 |
NH | +1.045 |
MO | +1.031 |
MR | +1.009 |
PLE | +0.990 |
Neg logit contributions | |
anders | -1.157 |
ourke | -0.983 |
[+ | -0.982 |
defences | -0.972 |
iris | -0.944 |
Token | ges |
Token ID | 3212 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
anders | +6.583 |
ourke | +5.108 |
[+ | +5.052 |
iris | +5.034 |
onent | +4.997 |
Neg logit contributions | |
MRI | -7.926 |
NH | -7.674 |
MO | -7.600 |
MR | -7.548 |
blu | -7.468 |
Token | hig |
Token ID | 25196 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
MRI | +0.763 |
NH | +0.736 |
MO | +0.721 |
MR | +0.713 |
PLE | +0.704 |
Neg logit contributions | |
anders | -0.554 |
ourke | -0.452 |
[+ | -0.448 |
defences | -0.446 |
onent | -0.431 |
Token | Rice |
Token ID | 13823 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
NR | +5.468 |
MRI | +4.962 |
NH | +4.671 |
MR | +4.301 |
Rx | +4.232 |
Neg logit contributions | |
anders | -16.882 |
ikuman | -15.058 |
ourke | -14.973 |
defences | -14.873 |
jriwal | -14.840 |
Token | / |
Token ID | 14 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
MRI | +1.354 |
NH | +1.241 |
MO | +1.191 |
MR | +1.142 |
NR | +1.137 |
Neg logit contributions | |
anders | -5.024 |
ourke | -4.523 |
defences | -4.462 |
[+ | -4.435 |
iris | -4.421 |
Token | CBC |
Token ID | 29208 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
anders | +3.649 |
ourke | +3.193 |
[+ | +3.142 |
iris | +3.091 |
onent | +3.088 |
Neg logit contributions | |
MRI | -2.353 |
NH | -2.212 |
MO | -2.182 |
blu | -2.132 |
MR | -2.128 |
Token | ) |
Token ID | 8 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
anders | +0.066 |
ourke | +0.057 |
[+ | +0.057 |
defences | +0.056 |
onent | +0.055 |
Neg logit contributions | |
MRI | -0.045 |
NH | -0.042 |
MO | -0.042 |
MR | -0.041 |
PLE | -0.040 |
Token | " |
Token ID | 366 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
anders | +3.861 |
ourke | +3.368 |
[+ | +3.350 |
defences | +3.265 |
onent | +3.259 |
Neg logit contributions | |
MRI | -2.535 |
NH | -2.398 |
MO | -2.356 |
MR | -2.306 |
PLE | -2.256 |
Token | Congress |
Token ID | 3162 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
MRI | +1.622 |
NH | +1.549 |
MO | +1.535 |
MR | +1.530 |
NR | +1.524 |
Neg logit contributions | |
anders | -2.351 |
ourke | -2.059 |
[+ | -2.058 |
iris | -2.032 |
defences | -2.017 |
Token | — |
Token ID | 851 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
MRI | +1.390 |
NH | +1.327 |
MR | +1.288 |
MO | +1.285 |
NR | +1.254 |
Neg logit contributions | |
anders | -2.514 |
ourke | -2.235 |
[+ | -2.219 |
defences | -2.208 |
onent | -2.162 |
Token | standing |
Token ID | 5055 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
MRI | +3.058 |
NH | +2.983 |
MR | +2.946 |
MO | +2.921 |
NR | +2.872 |
Neg logit contributions | |
anders | -4.855 |
[+ | -4.305 |
defences | -4.282 |
ourke | -4.242 |
iris | -4.211 |
Token | up |
Token ID | 510 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
MRI | +0.662 |
NH | +0.630 |
MO | +0.622 |
MR | +0.614 |
NR | +0.612 |
Neg logit contributions | |
anders | -0.883 |
ourke | -0.764 |
[+ | -0.759 |
onent | -0.740 |
defences | -0.732 |
Token | for |
Token ID | 329 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
anders | +2.033 |
ourke | +1.757 |
[+ | +1.741 |
defences | +1.703 |
onent | +1.697 |
Neg logit contributions | |
MRI | -1.546 |
NH | -1.467 |
MO | -1.449 |
MR | -1.418 |
PLE | -1.391 |
Token | working |
Token ID | 1762 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
MRI | +2.814 |
NH | +2.755 |
NR | +2.712 |
MO | +2.705 |
MR | +2.702 |
Neg logit contributions | |
anders | -4.423 |
ourke | -3.891 |
[+ | -3.889 |
onent | -3.814 |
iris | -3.806 |
Token | people |
Token ID | 661 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
NH | +4.860 |
blu | +4.759 |
MO | +4.624 |
MRI | +4.536 |
NR | +4.405 |
Neg logit contributions | |
anders | -15.647 |
onent | -14.817 |
ourke | -14.537 |
[+ | -14.176 |
jriwal | -14.148 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
MRI | +2.407 |
NH | +2.348 |
MO | +2.270 |
MR | +2.243 |
NR | +2.200 |
Neg logit contributions | |
anders | -4.722 |
ourke | -4.134 |
[+ | -4.132 |
onent | -4.110 |
defences | -4.088 |
Token | protecting |
Token ID | 10192 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
MRI | +0.721 |
NH | +0.693 |
MO | +0.680 |
MR | +0.670 |
blu | +0.661 |
Neg logit contributions | |
anders | -1.028 |
[+ | -0.890 |
ourke | -0.888 |
onent | -0.871 |
defences | -0.866 |
Token | affordable |
Token ID | 10935 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
MRI | +2.721 |
NH | +2.649 |
NR | +2.645 |
MO | +2.614 |
blu | +2.604 |
Neg logit contributions | |
anders | -4.387 |
ourke | -3.904 |
[+ | -3.862 |
onent | -3.797 |
iris | -3.766 |
Token | health |
Token ID | 1535 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
MRI | +1.644 |
NH | +1.604 |
MO | +1.588 |
NR | +1.554 |
blu | +1.530 |
Neg logit contributions | |
anders | -3.458 |
[+ | -3.048 |
ourke | -3.047 |
onent | -2.969 |
iris | -2.933 |
Token | i |
Token ID | 1312 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
MRI | +2.749 |
MO | +2.692 |
NH | +2.682 |
blu | +2.622 |
NR | +2.544 |
Neg logit contributions | |
anders | -5.439 |
ourke | -4.851 |
defences | -4.693 |
[+ | -4.681 |
onent | -4.660 |
Token | o |
Token ID | 267 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
MRI | +1.689 |
NH | +1.621 |
MO | +1.619 |
blu | +1.562 |
MR | +1.554 |
Neg logit contributions | |
anders | -2.276 |
ourke | -1.974 |
[+ | -1.930 |
defences | -1.923 |
onent | -1.902 |
Token | Hal |
Token ID | 11023 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
MRI | +0.212 |
NH | +0.202 |
MO | +0.200 |
MR | +0.194 |
blu | +0.193 |
Neg logit contributions | |
anders | -0.283 |
ourke | -0.245 |
[+ | -0.242 |
defences | -0.238 |
onent | -0.237 |
Token | ep |
Token ID | 538 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
MRI | +0.455 |
NH | +0.422 |
MO | +0.414 |
MR | +0.396 |
PLE | +0.383 |
Neg logit contributions | |
anders | -1.242 |
ourke | -1.114 |
defences | -1.106 |
[+ | -1.097 |
onent | -1.075 |
Token | ā |
Token ID | 10235 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
MRI | +3.707 |
NH | +3.500 |
MO | +3.454 |
MR | +3.355 |
blu | +3.338 |
Neg logit contributions | |
anders | -4.928 |
defences | -4.309 |
ourke | -4.252 |
[+ | -4.175 |
る | -4.096 |
Token | k |
Token ID | 74 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
anders | +0.696 |
ourke | +0.606 |
[+ | +0.600 |
defences | +0.590 |
onent | +0.588 |
Neg logit contributions | |
MRI | -0.467 |
NH | -0.442 |
MO | -0.437 |
MR | -0.426 |
PLE | -0.416 |
Token | ī |
Token ID | 18962 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
MRI | +6.327 |
NH | +5.755 |
MO | +5.645 |
MR | +5.435 |
ë | +5.399 |
Neg logit contributions | |
anders | -14.284 |
defences | -13.225 |
ourke | -12.951 |
ワン | -12.756 |
[+ | -12.463 |
Token | l |
Token ID | 300 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
MRI | +1.458 |
NH | +1.403 |
MO | +1.393 |
blu | +1.342 |
MR | +1.329 |
Neg logit contributions | |
anders | -2.714 |
ourke | -2.390 |
[+ | -2.344 |
defences | -2.332 |
onent | -2.312 |
Token | ā |
Token ID | 10235 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
MRI | +0.478 |
NH | +0.456 |
MO | +0.453 |
MR | +0.441 |
blu | +0.434 |
Neg logit contributions | |
anders | -0.541 |
ourke | -0.464 |
[+ | -0.456 |
defences | -0.454 |
onent | -0.444 |
Token | , |
Token ID | 11 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
MRI | +2.496 |
NH | +2.364 |
MO | +2.350 |
MR | +2.220 |
blu | +2.173 |
Neg logit contributions | |
anders | -5.894 |
ourke | -5.143 |
defences | -5.138 |
[+ | -5.107 |
onent | -5.049 |
Token | w |
Token ID | 266 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
MRI | +2.645 |
NH | +2.600 |
MO | +2.586 |
blu | +2.517 |
MR | +2.466 |
Neg logit contributions | |
anders | -4.390 |
ourke | -3.847 |
defences | -3.776 |
[+ | -3.741 |
onent | -3.715 |
Token | to |
Token ID | 284 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
anders | +0.852 |
ourke | +0.740 |
[+ | +0.733 |
defences | +0.718 |
onent | +0.714 |
Neg logit contributions | |
MRI | -0.615 |
NH | -0.581 |
MO | -0.574 |
MR | -0.560 |
PLE | -0.550 |
Token | funding |
Token ID | 4918 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
anders | +2.058 |
ourke | +1.771 |
[+ | +1.755 |
defences | +1.731 |
onent | +1.707 |
Neg logit contributions | |
MRI | -1.620 |
NH | -1.528 |
MO | -1.512 |
MR | -1.476 |
PLE | -1.454 |
Token | , |
Token ID | 11 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
anders | +3.532 |
ourke | +3.084 |
[+ | +3.072 |
defences | +3.023 |
onent | +2.990 |
Neg logit contributions | |
MRI | -2.213 |
NH | -2.069 |
MO | -2.044 |
MR | -1.982 |
PLE | -1.961 |
Token | requiring |
Token ID | 10616 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
anders | +2.339 |
ourke | +2.032 |
[+ | +2.012 |
defences | +1.973 |
onent | +1.965 |
Neg logit contributions | |
MRI | -1.652 |
NH | -1.561 |
MO | -1.541 |
MR | -1.505 |
PLE | -1.476 |
Token | F |
Token ID | 376 |
Feature activation | -7.60e+00 |
Pos logit contributions | |
anders | +1.225 |
ourke | +1.062 |
[+ | +1.052 |
onent | +1.026 |
defences | +1.024 |
Neg logit contributions | |
MRI | -0.882 |
NH | -0.838 |
MO | -0.828 |
MR | -0.809 |
NR | -0.794 |
Token | annie |
Token ID | 42883 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
MO | +1.996 |
NH | +1.927 |
MRI | +1.918 |
MR | +1.892 |
PLE | +1.512 |
Neg logit contributions | |
anders | -9.294 |
[+ | -8.723 |
defences | -8.542 |
ourke | -8.531 |
る | -8.421 |
Token | Mae |
Token ID | 34673 |
Feature activation | -7.46e+00 |
Pos logit contributions | |
MRI | +4.917 |
MO | +4.884 |
MR | +4.640 |
NH | +4.626 |
NR | +4.480 |
Neg logit contributions | |
anders | -15.710 |
ourke | -14.567 |
iris | -14.426 |
onent | -14.400 |
jriwal | -13.935 |
Token | and |
Token ID | 290 |
Feature activation | -7.72e+00 |
Pos logit contributions | |
MRI | +3.606 |
NH | +3.572 |
MO | +3.569 |
NR | +3.504 |
MR | +3.452 |
Neg logit contributions | |
anders | -7.530 |
ourke | -6.583 |
iris | -6.497 |
onent | -6.449 |
[+ | -6.424 |
Token | Freddie |
Token ID | 31658 |
Feature activation | -9.71e+00 |
Pos logit contributions | |
MRI | +1.554 |
NH | +1.461 |
MO | +1.456 |
NR | +1.439 |
MR | +1.373 |
Neg logit contributions | |
anders | -9.988 |
ourke | -9.080 |
[+ | -9.032 |
iris | -8.908 |
defences | -8.829 |
Token | Mac |
Token ID | 4100 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
MRI | +3.956 |
NH | +3.622 |
MR | +3.543 |
MO | +3.538 |
NR | +3.474 |
Neg logit contributions | |
anders | -10.840 |
ourke | -9.729 |
onent | -9.694 |
iris | -9.651 |
[+ | -9.448 |
Token | to |
Token ID | 284 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
MRI | +3.062 |
MO | +2.991 |
NH | +2.980 |
NR | +2.885 |
MR | +2.843 |
Neg logit contributions | |
anders | -5.811 |
ourke | -5.033 |
[+ | -4.954 |
onent | -4.916 |
iris | -4.911 |
Token | think |
Token ID | 892 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
MRI | +1.510 |
NH | +1.423 |
MO | +1.417 |
blu | +1.387 |
NR | +1.364 |
Neg logit contributions | |
anders | -2.206 |
[+ | -1.926 |
ourke | -1.923 |
defences | -1.903 |
iris | -1.872 |
Token | reduces |
Token ID | 12850 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
MRI | +4.329 |
MR | +4.041 |
MO | +4.040 |
NH | +4.038 |
blu | +4.014 |
Neg logit contributions | |
anders | -3.524 |
ourke | -3.034 |
ワン | -2.760 |
iris | -2.759 |
[+ | -2.756 |
Token | immersion |
Token ID | 36375 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
anders | +1.319 |
ourke | +1.084 |
[+ | +1.080 |
defences | +1.052 |
onent | +1.037 |
Neg logit contributions | |
MRI | -1.685 |
NH | -1.621 |
MO | -1.598 |
MR | -1.572 |
PLE | -1.570 |
Token | more |
Token ID | 517 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
MRI | +0.207 |
NH | +0.195 |
MO | +0.193 |
MR | +0.188 |
blu | +0.186 |
Neg logit contributions | |
anders | -0.334 |
ourke | -0.295 |
[+ | -0.291 |
iris | -0.286 |
onent | -0.285 |
Token | on |
Token ID | 319 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
MRI | +0.356 |
NH | +0.337 |
MO | +0.334 |
MR | +0.327 |
blu | +0.321 |
Neg logit contributions | |
anders | -0.479 |
ourke | -0.415 |
[+ | -0.406 |
defences | -0.403 |
onent | -0.399 |
Token | H |
Token ID | 367 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
MRI | +1.351 |
NH | +1.273 |
MO | +1.238 |
MR | +1.200 |
NR | +1.192 |
Neg logit contributions | |
anders | -3.490 |
ourke | -3.137 |
[+ | -3.076 |
defences | -3.043 |
onent | -3.043 |
Token | MD |
Token ID | 12740 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
MO | +5.369 |
MRI | +5.116 |
MR | +5.009 |
NH | +4.692 |
RC | +4.022 |
Neg logit contributions | |
anders | -15.913 |
ikuman | -15.012 |
berra | -14.879 |
intendent | -14.854 |
Archdemon | -14.741 |
Token | s |
Token ID | 82 |
Feature activation | +7.09e+00 |
Pos logit contributions | |
MRI | +2.655 |
MO | +2.534 |
NH | +2.502 |
MR | +2.448 |
blu | +2.397 |
Neg logit contributions | |
anders | -3.660 |
ourke | -3.233 |
[+ | -3.152 |
iris | -3.109 |
defences | -3.101 |
Token | but |
Token ID | 475 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
anders | +6.311 |
ourke | +5.425 |
[+ | +5.422 |
onent | +5.356 |
defences | +5.304 |
Neg logit contributions | |
MRI | -4.563 |
NH | -4.376 |
MO | -4.268 |
MR | -4.202 |
PLE | -4.090 |
Token | it |
Token ID | 340 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
MRI | +2.066 |
NH | +1.950 |
MO | +1.933 |
MR | +1.892 |
blu | +1.886 |
Neg logit contributions | |
anders | -3.982 |
ourke | -3.469 |
[+ | -3.370 |
onent | -3.368 |
iris | -3.365 |
Token | can |
Token ID | 460 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
MRI | +3.727 |
MO | +3.554 |
NH | +3.512 |
blu | +3.506 |
NR | +3.454 |
Neg logit contributions | |
anders | -5.530 |
ourke | -4.681 |
onent | -4.637 |
defences | -4.554 |
[+ | -4.550 |
Token | on |
Token ID | 319 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
MRI | +1.356 |
NH | +1.303 |
MO | +1.284 |
MR | +1.263 |
PLE | +1.229 |
Neg logit contributions | |
anders | -1.984 |
ourke | -1.728 |
[+ | -1.708 |
defences | -1.698 |
onent | -1.673 |
Token | Women |
Token ID | 6926 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
MRI | +2.956 |
MO | +2.860 |
NH | +2.812 |
NR | +2.794 |
blu | +2.761 |
Neg logit contributions | |
anders | -4.744 |
ourke | -4.181 |
[+ | -4.132 |
defences | -4.127 |
onent | -4.112 |
Token | in |
Token ID | 287 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
anders | +1.576 |
ourke | +1.380 |
[+ | +1.366 |
defences | +1.340 |
onent | +1.337 |
Neg logit contributions | |
MRI | -0.989 |
NH | -0.935 |
MO | -0.922 |
MR | -0.899 |
PLE | -0.879 |
Token | politics |
Token ID | 4819 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
MRI | +1.241 |
NH | +1.201 |
MO | +1.178 |
NR | +1.157 |
MR | +1.148 |
Neg logit contributions | |
anders | -1.986 |
ourke | -1.753 |
[+ | -1.740 |
iris | -1.710 |
onent | -1.685 |
Token | . |
Token ID | 13 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
MRI | +1.139 |
NH | +1.108 |
MO | +1.084 |
MR | +1.052 |
NR | +1.048 |
Neg logit contributions | |
anders | -2.133 |
ourke | -1.903 |
[+ | -1.859 |
onent | -1.835 |
iris | -1.835 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
MRI | +1.253 |
NH | +1.204 |
MO | +1.190 |
NR | +1.154 |
MR | +1.139 |
Neg logit contributions | |
anders | -2.242 |
ourke | -1.985 |
defences | -1.950 |
onent | -1.915 |
[+ | -1.911 |
Token | Caption |
Token ID | 11260 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
NH | +4.552 |
NR | +4.450 |
MRI | +4.441 |
MO | +4.062 |
MR | +4.050 |
Neg logit contributions | |
anders | -16.240 |
raviolet | -15.017 |
berra | -14.896 |
defences | -14.814 |
jriwal | -14.729 |
Token | 7 |
Token ID | 767 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
MRI | +4.193 |
NH | +4.058 |
NR | +4.047 |
MO | +3.993 |
MR | +3.811 |
Neg logit contributions | |
anders | -13.375 |
defences | -12.370 |
iris | -12.165 |
ikuman | -12.159 |
jriwal | -12.142 |
Token | of |
Token ID | 286 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
anders | +0.028 |
ourke | +0.024 |
[+ | +0.024 |
defences | +0.024 |
onent | +0.024 |
Neg logit contributions | |
MRI | -0.019 |
NH | -0.018 |
MO | -0.018 |
MR | -0.017 |
PLE | -0.017 |
Token | 15 |
Token ID | 1315 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
MRI | +0.761 |
NH | +0.710 |
MO | +0.699 |
MR | +0.678 |
NR | +0.659 |
Neg logit contributions | |
anders | -1.654 |
ourke | -1.460 |
[+ | -1.440 |
defences | -1.433 |
onent | -1.424 |
Token | Photos |
Token ID | 9434 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
MRI | +1.926 |
NH | +1.810 |
MO | +1.774 |
NR | +1.727 |
MR | +1.719 |
Neg logit contributions | |
anders | -3.583 |
ourke | -3.150 |
defences | -3.122 |
iris | -3.090 |
onent | -3.074 |
Token | arer |
Token ID | 11258 |
Feature activation | -6.91e+00 |
Pos logit contributions | |
MRI | +3.257 |
NH | +3.021 |
MR | +3.020 |
MO | +2.960 |
NR | +2.886 |
Neg logit contributions | |
anders | -5.444 |
[+ | -4.908 |
defences | -4.844 |
ourke | -4.838 |
る | -4.707 |
Token | Ver |
Token ID | 4643 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
MRI | +4.346 |
NR | +4.130 |
MR | +4.079 |
blu | +4.079 |
NH | +4.061 |
Neg logit contributions | |
anders | -5.840 |
ourke | -5.107 |
[+ | -4.996 |
iris | -4.957 |
onent | -4.932 |
Token | h |
Token ID | 71 |
Feature activation | -6.32e+00 |
Pos logit contributions | |
anders | +1.068 |
ourke | +0.940 |
[+ | +0.935 |
defences | +0.920 |
onent | +0.915 |
Neg logit contributions | |
MRI | -0.625 |
NH | -0.592 |
MO | -0.580 |
MR | -0.566 |
blu | -0.552 |
Token | ä |
Token ID | 11033 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
MRI | +3.461 |
NH | +3.223 |
MO | +3.147 |
MR | +3.113 |
ë | +2.969 |
Neg logit contributions | |
anders | -5.862 |
defences | -5.376 |
[+ | -5.349 |
ourke | -5.267 |
onent | -5.204 |
Token | lt |
Token ID | 2528 |
Feature activation | -6.46e+00 |
Pos logit contributions | |
MRI | +1.404 |
NH | +1.333 |
MO | +1.320 |
MR | +1.293 |
PLE | +1.280 |
Neg logit contributions | |
anders | -1.641 |
[+ | -1.422 |
ourke | -1.417 |
defences | -1.401 |
iris | -1.367 |
Token | n |
Token ID | 77 |
Feature activation | -1.45e+01 |
Pos logit contributions | |
MRI | +2.379 |
NH | +2.316 |
NR | +2.181 |
MO | +2.145 |
MR | +2.044 |
Neg logit contributions | |
anders | -7.294 |
ourke | -6.514 |
defences | -6.513 |
[+ | -6.508 |
onent | -6.387 |
Token | isse |
Token ID | 20782 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
MRI | +2.953 |
ë | +2.047 |
isse | +1.852 |
NH | +1.841 |
ificate | +1.791 |
Neg logit contributions | |
anders | -17.010 |
defences | -16.159 |
Archdemon | -15.750 |
ikuman | -15.721 |
barr | -15.680 |
Token | " |
Token ID | 1 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
MRI | +2.696 |
NH | +2.569 |
MO | +2.553 |
NR | +2.498 |
blu | +2.485 |
Neg logit contributions | |
anders | -4.526 |
ourke | -3.964 |
[+ | -3.932 |
onent | -3.836 |
iris | -3.814 |
Token | because |
Token ID | 780 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
MRI | +0.700 |
NH | +0.671 |
MO | +0.657 |
MR | +0.646 |
NR | +0.640 |
Neg logit contributions | |
anders | -1.012 |
ourke | -0.883 |
[+ | -0.863 |
onent | -0.860 |
iris | -0.853 |
Token | of |
Token ID | 286 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
anders | +2.476 |
ourke | +2.150 |
[+ | +2.128 |
defences | +2.084 |
onent | +2.078 |
Neg logit contributions | |
MRI | -1.772 |
NH | -1.677 |
MO | -1.656 |
MR | -1.618 |
PLE | -1.586 |
Token | refugees |
Token ID | 8015 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
MRI | +0.747 |
NH | +0.712 |
MO | +0.700 |
MR | +0.694 |
NR | +0.692 |
Neg logit contributions | |
anders | -1.143 |
ourke | -1.005 |
[+ | -0.987 |
onent | -0.981 |
iris | -0.967 |
Token | January |
Token ID | 3269 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
MRI | +0.932 |
NH | +0.878 |
MO | +0.872 |
NR | +0.851 |
MR | +0.850 |
Neg logit contributions | |
anders | -1.474 |
ourke | -1.293 |
[+ | -1.277 |
onent | -1.248 |
defences | -1.247 |
Token | 20 |
Token ID | 1160 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
MRI | +1.071 |
NH | +0.999 |
MO | +0.986 |
MR | +0.953 |
NR | +0.930 |
Neg logit contributions | |
anders | -2.320 |
ourke | -2.065 |
[+ | -2.032 |
defences | -2.009 |
onent | -1.999 |
Token | , |
Token ID | 11 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
anders | +2.675 |
ourke | +2.344 |
[+ | +2.323 |
onent | +2.266 |
defences | +2.255 |
Neg logit contributions | |
MRI | -1.745 |
NH | -1.646 |
MO | -1.624 |
MR | -1.581 |
PLE | -1.567 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
anders | +2.793 |
ourke | +2.425 |
[+ | +2.401 |
defences | +2.351 |
onent | +2.346 |
Neg logit contributions | |
MRI | -2.011 |
NH | -1.893 |
MO | -1.865 |
MR | -1.824 |
PLE | -1.794 |
Token | . |
Token ID | 13 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
anders | +3.955 |
ourke | +3.471 |
[+ | +3.414 |
onent | +3.333 |
defences | +3.313 |
Neg logit contributions | |
MRI | -2.623 |
NH | -2.435 |
MO | -2.392 |
MR | -2.356 |
blu | -2.315 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.44e+01 |
Pos logit contributions | |
MRI | +1.746 |
NH | +1.678 |
MO | +1.645 |
NR | +1.619 |
MR | +1.574 |
Neg logit contributions | |
anders | -3.279 |
ourke | -2.915 |
defences | -2.866 |
onent | -2.812 |
jriwal | -2.804 |
Token | Caption |
Token ID | 11260 |
Feature activation | -8.94e+00 |
Pos logit contributions | |
NH | +4.440 |
MRI | +4.410 |
NR | +4.346 |
MO | +3.986 |
MR | +3.954 |
Neg logit contributions | |
anders | -16.089 |
raviolet | -14.839 |
berra | -14.704 |
defences | -14.641 |
jriwal | -14.553 |
Token | 8 |
Token ID | 807 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
MRI | +3.137 |
MO | +2.923 |
NR | +2.812 |
NH | +2.712 |
MR | +2.658 |
Neg logit contributions | |
anders | -10.531 |
defences | -9.410 |
berra | -9.405 |
ourke | -9.272 |
jriwal | -9.220 |
Token | of |
Token ID | 286 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
anders | +1.403 |
ourke | +1.219 |
[+ | +1.211 |
onent | +1.178 |
defences | +1.177 |
Neg logit contributions | |
MRI | -1.029 |
NH | -0.974 |
MO | -0.960 |
MR | -0.940 |
PLE | -0.922 |
Token | 15 |
Token ID | 1315 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
MRI | +1.184 |
NH | +1.106 |
MO | +1.089 |
MR | +1.054 |
NR | +1.033 |
Neg logit contributions | |
anders | -2.741 |
ourke | -2.416 |
defences | -2.383 |
[+ | -2.376 |
onent | -2.364 |
Token | Photos |
Token ID | 9434 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
MRI | +2.758 |
NH | +2.595 |
MO | +2.525 |
NR | +2.498 |
MR | +2.439 |
Neg logit contributions | |
anders | -5.535 |
defences | -4.868 |
ourke | -4.865 |
iris | -4.817 |
berra | -4.784 |
Token | Leslie |
Token ID | 26909 |
Feature activation | +9.87e-02 |
Pos logit contributions | |
MRI | +0.114 |
NH | +0.108 |
MO | +0.107 |
MR | +0.104 |
NR | +0.102 |
Neg logit contributions | |
anders | -0.163 |
ourke | -0.142 |
[+ | -0.139 |
defences | -0.138 |
onent | -0.137 |
Token | in |
Token ID | 287 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
anders | +0.091 |
ourke | +0.079 |
[+ | +0.078 |
onent | +0.077 |
defences | +0.077 |
Neg logit contributions | |
MRI | -0.061 |
NH | -0.058 |
MO | -0.058 |
MR | -0.056 |
NR | -0.055 |
Token | a |
Token ID | 257 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
MRI | +0.393 |
NH | +0.376 |
MO | +0.370 |
MR | +0.361 |
NR | +0.359 |
Neg logit contributions | |
anders | -0.589 |
ourke | -0.511 |
[+ | -0.505 |
onent | -0.496 |
iris | -0.494 |
Token | race |
Token ID | 3234 |
Feature activation | -6.89e+00 |
Pos logit contributions | |
MRI | +1.106 |
NH | +1.052 |
MO | +1.047 |
blu | +1.014 |
MR | +1.014 |
Neg logit contributions | |
anders | -1.708 |
ourke | -1.471 |
[+ | -1.455 |
onent | -1.434 |
iris | -1.428 |
Token | of |
Token ID | 286 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
MRI | +3.901 |
NH | +3.817 |
MO | +3.699 |
NR | +3.668 |
MR | +3.618 |
Neg logit contributions | |
anders | -6.487 |
ourke | -5.586 |
iris | -5.452 |
onent | -5.418 |
[+ | -5.409 |
Token | remote |
Token ID | 6569 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
anders | +0.432 |
ourke | +0.375 |
[+ | +0.372 |
onent | +0.364 |
iris | +0.362 |
Neg logit contributions | |
MRI | -0.292 |
NH | -0.278 |
MO | -0.274 |
MR | -0.268 |
blu | -0.263 |
Token | control |
Token ID | 1630 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
MRI | +5.397 |
MO | +5.101 |
NR | +5.010 |
MR | +4.991 |
blu | +4.962 |
Neg logit contributions | |
anders | -14.478 |
ourke | -12.908 |
iris | -12.870 |
onent | -12.663 |
[+ | -12.649 |
Token | cars |
Token ID | 5006 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
MRI | +3.284 |
MO | +3.108 |
NH | +3.104 |
blu | +3.023 |
MR | +3.015 |
Neg logit contributions | |
anders | -5.527 |
ourke | -4.849 |
onent | -4.750 |
[+ | -4.741 |
iris | -4.722 |
Token | 1993 |
Token ID | 9656 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
MRI | +0.227 |
NH | +0.217 |
MO | +0.214 |
MR | +0.208 |
NR | +0.204 |
Neg logit contributions | |
anders | -0.346 |
ourke | -0.302 |
[+ | -0.296 |
onent | -0.293 |
defences | -0.293 |
Token | : |
Token ID | 25 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
anders | +2.170 |
ourke | +1.877 |
[+ | +1.869 |
defences | +1.825 |
onent | +1.824 |
Neg logit contributions | |
MRI | -1.584 |
NH | -1.493 |
MO | -1.472 |
MR | -1.447 |
PLE | -1.418 |
Token | Father |
Token ID | 9190 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
anders | +0.838 |
ourke | +0.731 |
[+ | +0.718 |
defences | +0.707 |
onent | +0.703 |
Neg logit contributions | |
MRI | -0.591 |
NH | -0.560 |
MO | -0.554 |
MR | -0.541 |
NR | -0.532 |
Token | could |
Token ID | 714 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
MRI | +0.545 |
NH | +0.514 |
MO | +0.512 |
MR | +0.497 |
blu | +0.488 |
Neg logit contributions | |
anders | -0.870 |
ourke | -0.762 |
[+ | -0.751 |
defences | -0.737 |
onent | -0.736 |
Token | shoot |
Token ID | 2686 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
anders | +0.068 |
ourke | +0.059 |
[+ | +0.058 |
defences | +0.057 |
onent | +0.057 |
Neg logit contributions | |
MRI | -0.046 |
NH | -0.043 |
MO | -0.043 |
MR | -0.042 |
blu | -0.041 |
Token | with |
Token ID | 351 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
MRI | +2.555 |
MO | +2.431 |
NH | +2.429 |
blu | +2.385 |
MR | +2.376 |
Neg logit contributions | |
anders | -4.147 |
ourke | -3.648 |
[+ | -3.530 |
onent | -3.483 |
iris | -3.469 |
Token | that |
Token ID | 326 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
anders | +3.186 |
ourke | +2.766 |
[+ | +2.751 |
defences | +2.693 |
onent | +2.680 |
Neg logit contributions | |
MRI | -2.289 |
NH | -2.161 |
MO | -2.126 |
MR | -2.075 |
PLE | -2.041 |
Token | ," |
Token ID | 553 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
MRI | +0.906 |
NH | +0.862 |
MO | +0.857 |
MR | +0.833 |
blu | +0.831 |
Neg logit contributions | |
anders | -1.459 |
ourke | -1.267 |
[+ | -1.242 |
defences | -1.228 |
onent | -1.221 |
Token | Retro |
Token ID | 29884 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
anders | +3.088 |
ourke | +2.706 |
[+ | +2.694 |
defences | +2.639 |
onent | +2.621 |
Neg logit contributions | |
MRI | -1.865 |
NH | -1.756 |
MO | -1.717 |
MR | -1.678 |
PLE | -1.640 |
Token | Camera |
Token ID | 20432 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
MRI | +5.002 |
MO | +4.574 |
NH | +4.546 |
PLE | +4.331 |
NR | +4.264 |
Neg logit contributions | |
anders | -15.170 |
berra | -13.467 |
defences | -13.338 |
iris | -13.288 |
ourke | -13.240 |
Token | should |
Token ID | 815 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
MRI | +0.628 |
MO | +0.596 |
NH | +0.593 |
MR | +0.578 |
blu | +0.575 |
Neg logit contributions | |
anders | -0.801 |
ourke | -0.693 |
[+ | -0.682 |
onent | -0.667 |
defences | -0.665 |
Token | be |
Token ID | 307 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
anders | +2.252 |
ourke | +1.969 |
[+ | +1.955 |
defences | +1.918 |
onent | +1.912 |
Neg logit contributions | |
MRI | -1.406 |
NH | -1.327 |
MO | -1.307 |
MR | -1.275 |
PLE | -1.247 |
Token | your |
Token ID | 534 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
anders | +1.320 |
ourke | +1.145 |
[+ | +1.130 |
onent | +1.107 |
defences | +1.106 |
Neg logit contributions | |
MRI | -0.934 |
NH | -0.883 |
MO | -0.877 |
MR | -0.853 |
blu | -0.840 |
Token | next |
Token ID | 1306 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
anders | +4.975 |
ourke | +4.350 |
[+ | +4.317 |
defences | +4.235 |
onent | +4.189 |
Neg logit contributions | |
MRI | -3.770 |
NH | -3.604 |
MO | -3.538 |
MR | -3.457 |
PLE | -3.406 |
Token | February |
Token ID | 3945 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
MRI | +1.487 |
NH | +1.407 |
MO | +1.390 |
MR | +1.345 |
NR | +1.337 |
Neg logit contributions | |
anders | -2.599 |
ourke | -2.285 |
onent | -2.227 |
[+ | -2.222 |
defences | -2.211 |
Token | 11 |
Token ID | 1367 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
MRI | +0.146 |
NH | +0.137 |
MO | +0.135 |
MR | +0.131 |
NR | +0.127 |
Neg logit contributions | |
anders | -0.297 |
ourke | -0.263 |
[+ | -0.260 |
defences | -0.256 |
onent | -0.255 |
Token | , |
Token ID | 11 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
anders | +2.241 |
ourke | +1.965 |
[+ | +1.947 |
defences | +1.911 |
onent | +1.905 |
Neg logit contributions | |
MRI | -1.345 |
NH | -1.264 |
MO | -1.246 |
MR | -1.214 |
PLE | -1.187 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
anders | +3.269 |
ourke | +2.826 |
[+ | +2.811 |
defences | +2.730 |
onent | +2.720 |
Neg logit contributions | |
MRI | -2.559 |
NH | -2.420 |
MO | -2.382 |
MR | -2.333 |
PLE | -2.302 |
Token | . |
Token ID | 13 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
anders | +5.232 |
ourke | +4.617 |
[+ | +4.592 |
defences | +4.440 |
onent | +4.437 |
Neg logit contributions | |
MRI | -3.320 |
NH | -3.113 |
MO | -3.046 |
MR | -2.991 |
blu | -2.906 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
anders | +4.974 |
ourke | +4.382 |
[+ | +4.377 |
onent | +4.245 |
defences | +4.238 |
Neg logit contributions | |
MRI | -2.940 |
NH | -2.750 |
MO | -2.684 |
MR | -2.627 |
PLE | -2.561 |
Token | / |
Token ID | 14 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
MRI | +3.297 |
MO | +3.203 |
NH | +3.144 |
PLE | +3.091 |
NR | +2.998 |
Neg logit contributions | |
anders | -16.904 |
jriwal | -15.794 |
ikuman | -15.763 |
berra | -15.572 |
raviolet | -15.566 |
Token | Cl |
Token ID | 2601 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
MRI | +0.375 |
NH | +0.355 |
MO | +0.352 |
MR | +0.345 |
PLE | +0.335 |
Neg logit contributions | |
anders | -0.582 |
ourke | -0.507 |
[+ | -0.502 |
defences | -0.500 |
onent | -0.493 |
Token | od |
Token ID | 375 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
anders | +1.513 |
[+ | +1.344 |
ourke | +1.337 |
defences | +1.317 |
onent | +1.302 |
Neg logit contributions | |
MRI | -0.741 |
NH | -0.689 |
MO | -0.682 |
MR | -0.660 |
PLE | -0.639 |
Token | agh |
Token ID | 10471 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
anders | +0.691 |
ourke | +0.571 |
[+ | +0.562 |
defences | +0.546 |
onent | +0.544 |
Neg logit contributions | |
MRI | -0.881 |
NH | -0.846 |
MO | -0.838 |
MR | -0.824 |
PLE | -0.812 |
Token | Kil |
Token ID | 19902 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
MRI | +0.778 |
NH | +0.737 |
MO | +0.731 |
MR | +0.713 |
NR | +0.704 |
Neg logit contributions | |
anders | -0.990 |
ourke | -0.854 |
[+ | -0.849 |
defences | -0.831 |
onent | -0.825 |
Token | been |
Token ID | 587 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
anders | +4.700 |
[+ | +4.009 |
ourke | +3.966 |
defences | +3.930 |
onent | +3.908 |
Neg logit contributions | |
MRI | -3.870 |
NH | -3.686 |
MO | -3.617 |
MR | -3.550 |
PLE | -3.512 |
Token | acquired |
Token ID | 9477 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
anders | +1.364 |
ourke | +1.196 |
[+ | +1.181 |
defences | +1.159 |
onent | +1.157 |
Neg logit contributions | |
MRI | -0.841 |
NH | -0.793 |
MO | -0.783 |
MR | -0.762 |
blu | -0.746 |
Token | ," |
Token ID | 553 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
anders | +2.063 |
ourke | +1.797 |
[+ | +1.780 |
defences | +1.745 |
onent | +1.739 |
Neg logit contributions | |
MRI | -1.392 |
NH | -1.313 |
MO | -1.297 |
MR | -1.266 |
PLE | -1.240 |
Token | said |
Token ID | 531 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
anders | +1.374 |
ourke | +1.189 |
[+ | +1.170 |
iris | +1.143 |
onent | +1.142 |
Neg logit contributions | |
MRI | -1.115 |
NH | -1.066 |
MO | -1.052 |
MR | -1.027 |
blu | -1.013 |
Token | Des |
Token ID | 2935 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
anders | +3.059 |
ourke | +2.626 |
[+ | +2.599 |
defences | +2.544 |
onent | +2.533 |
Neg logit contributions | |
MRI | -2.538 |
NH | -2.409 |
MO | -2.383 |
MR | -2.333 |
PLE | -2.293 |
Token | j |
Token ID | 73 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
MRI | +2.489 |
NH | +2.381 |
MO | +2.348 |
MR | +2.303 |
PLE | +2.256 |
Neg logit contributions | |
anders | -2.412 |
ourke | -2.058 |
[+ | -2.050 |
defences | -2.013 |
onent | -1.975 |
Token | ard |
Token ID | 446 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
MRI | +3.917 |
MO | +3.170 |
NH | +3.065 |
mark | +3.054 |
MR | +2.987 |
Neg logit contributions | |
anders | -15.456 |
defences | -14.897 |
ikuman | -14.831 |
ワン | -14.743 |
る | -14.355 |
Token | ins |
Token ID | 1040 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
MRI | +3.149 |
NH | +3.005 |
MO | +2.950 |
MR | +2.871 |
NR | +2.835 |
Neg logit contributions | |
anders | -2.710 |
ourke | -2.370 |
defences | -2.342 |
[+ | -2.308 |
onent | -2.237 |
Token | , |
Token ID | 11 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
anders | +2.627 |
ourke | +2.303 |
[+ | +2.274 |
onent | +2.233 |
defences | +2.227 |
Neg logit contributions | |
MRI | -1.659 |
NH | -1.557 |
MO | -1.528 |
MR | -1.500 |
PLE | -1.468 |
Token | who |
Token ID | 508 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
anders | +4.287 |
[+ | +3.697 |
ourke | +3.685 |
defences | +3.596 |
onent | +3.586 |
Neg logit contributions | |
MRI | -3.758 |
NH | -3.543 |
MO | -3.524 |
MR | -3.449 |
PLE | -3.420 |
Token | spent |
Token ID | 3377 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
anders | +3.188 |
ourke | +2.748 |
[+ | +2.729 |
defences | +2.674 |
onent | +2.662 |
Neg logit contributions | |
MRI | -2.394 |
NH | -2.262 |
MO | -2.235 |
MR | -2.188 |
PLE | -2.149 |
Token | have |
Token ID | 423 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
MRI | +0.604 |
NH | +0.576 |
MO | +0.571 |
MR | +0.556 |
blu | +0.555 |
Neg logit contributions | |
anders | -0.909 |
ourke | -0.796 |
[+ | -0.779 |
defences | -0.767 |
iris | -0.762 |
Token | a |
Token ID | 257 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
MRI | +2.373 |
blu | +2.321 |
MO | +2.260 |
NH | +2.238 |
NR | +2.216 |
Neg logit contributions | |
anders | -4.191 |
ourke | -3.728 |
[+ | -3.601 |
onent | -3.581 |
iris | -3.572 |
Token | messy |
Token ID | 24097 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
MRI | +2.820 |
blu | +2.775 |
MO | +2.766 |
NH | +2.702 |
MR | +2.657 |
Neg logit contributions | |
anders | -4.163 |
ourke | -3.563 |
[+ | -3.540 |
iris | -3.476 |
onent | -3.471 |
Token | mother |
Token ID | 2802 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
MO | +4.074 |
MRI | +4.071 |
blu | +3.984 |
NH | +3.959 |
NR | +3.927 |
Neg logit contributions | |
anders | -5.812 |
ourke | -5.118 |
[+ | -4.991 |
iris | -4.909 |
onent | -4.837 |
Token | / |
Token ID | 14 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
MRI | +2.859 |
MO | +2.803 |
NH | +2.712 |
MR | +2.623 |
PLE | +2.602 |
Neg logit contributions | |
anders | -5.440 |
ourke | -4.820 |
iris | -4.664 |
defences | -4.655 |
[+ | -4.643 |
Token | daughter |
Token ID | 29642 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
MRI | +0.774 |
MO | +0.735 |
NH | +0.733 |
MR | +0.706 |
PLE | +0.690 |
Neg logit contributions | |
anders | -1.478 |
ourke | -1.325 |
[+ | -1.310 |
defences | -1.306 |
onent | -1.281 |
Token | thing |
Token ID | 1517 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
blu | +7.616 |
MO | +7.533 |
MRI | +7.199 |
NR | +7.097 |
shepherd | +7.022 |
Neg logit contributions | |
anders | -12.350 |
iris | -10.654 |
ourke | -10.567 |
onent | -10.423 |
ricanes | -10.356 |
Token | going |
Token ID | 1016 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
MRI | +0.285 |
NH | +0.273 |
MO | +0.273 |
MR | +0.263 |
blu | +0.258 |
Neg logit contributions | |
anders | -0.422 |
ourke | -0.367 |
[+ | -0.363 |
defences | -0.357 |
onent | -0.357 |
Token | on |
Token ID | 319 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
anders | +3.263 |
ourke | +2.799 |
[+ | +2.782 |
defences | +2.725 |
iris | +2.704 |
Neg logit contributions | |
MRI | -2.556 |
NH | -2.418 |
MO | -2.390 |
MR | -2.340 |
PLE | -2.294 |
Token | , |
Token ID | 11 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
MRI | +3.084 |
MO | +2.969 |
NH | +2.943 |
MR | +2.871 |
NR | +2.829 |
Neg logit contributions | |
anders | -6.299 |
ourke | -5.612 |
onent | -5.424 |
[+ | -5.397 |
defences | -5.383 |
Token | but |
Token ID | 475 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
MRI | +3.215 |
MO | +3.178 |
NH | +3.116 |
blu | +3.074 |
NR | +3.070 |
Neg logit contributions | |
anders | -6.793 |
ourke | -6.067 |
onent | -5.955 |
iris | -5.917 |
[+ | -5.901 |
Token | , |
Token ID | 11 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
anders | +1.933 |
ourke | +1.698 |
[+ | +1.679 |
defences | +1.648 |
onent | +1.645 |
Neg logit contributions | |
MRI | -1.158 |
NH | -1.088 |
MO | -1.073 |
MR | -1.046 |
PLE | -1.023 |
Token | but |
Token ID | 475 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
anders | +3.389 |
ourke | +2.953 |
[+ | +2.935 |
defences | +2.885 |
onent | +2.859 |
Neg logit contributions | |
MRI | -2.203 |
NH | -2.073 |
MO | -2.048 |
MR | -1.995 |
PLE | -1.946 |
Token | occasionally |
Token ID | 10491 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
anders | +2.095 |
ourke | +1.823 |
[+ | +1.805 |
defences | +1.770 |
onent | +1.763 |
Neg logit contributions | |
MRI | -1.440 |
NH | -1.360 |
MO | -1.343 |
MR | -1.311 |
PLE | -1.285 |
Token | , |
Token ID | 11 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
anders | +0.423 |
ourke | +0.372 |
[+ | +0.366 |
onent | +0.359 |
iris | +0.358 |
Neg logit contributions | |
MRI | -0.263 |
NH | -0.248 |
MO | -0.244 |
MR | -0.238 |
NR | -0.234 |
Token | Dungeons |
Token ID | 25461 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
anders | +2.227 |
ourke | +1.937 |
[+ | +1.919 |
defences | +1.881 |
onent | +1.874 |
Neg logit contributions | |
MRI | -1.542 |
NH | -1.457 |
MO | -1.439 |
MR | -1.405 |
PLE | -1.376 |
Token | and |
Token ID | 290 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
anders | +3.464 |
ourke | +3.006 |
[+ | +2.976 |
defences | +2.936 |
onent | +2.918 |
Neg logit contributions | |
MRI | -2.137 |
NH | -2.001 |
MO | -1.973 |
MR | -1.917 |
PLE | -1.904 |
Token | Dragons |
Token ID | 19075 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
anders | +6.179 |
[+ | +4.593 |
defences | +4.495 |
onent | +4.482 |
ourke | +4.470 |
Neg logit contributions | |
MRI | -11.285 |
NH | -11.049 |
blu | -10.711 |
PLE | -10.600 |
MO | -10.564 |
Token | players |
Token ID | 1938 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
MRI | +0.941 |
NH | +0.889 |
MO | +0.886 |
MR | +0.866 |
NR | +0.857 |
Neg logit contributions | |
anders | -1.116 |
ourke | -0.966 |
[+ | -0.948 |
iris | -0.932 |
onent | -0.926 |
Token | do |
Token ID | 466 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
anders | +1.336 |
ourke | +1.160 |
[+ | +1.148 |
defences | +1.125 |
onent | +1.121 |
Neg logit contributions | |
MRI | -0.956 |
NH | -0.904 |
MO | -0.893 |
MR | -0.872 |
PLE | -0.855 |
Token | not |
Token ID | 407 |
Feature activation | +8.08e+00 |
Pos logit contributions | |
anders | +4.487 |
[+ | +3.849 |
ourke | +3.829 |
defences | +3.779 |
onent | +3.743 |
Neg logit contributions | |
MRI | -3.515 |
NH | -3.321 |
MO | -3.292 |
MR | -3.203 |
PLE | -3.156 |
Token | take |
Token ID | 1011 |
Feature activation | +6.44e+00 |
Pos logit contributions | |
anders | +6.799 |
[+ | +5.918 |
defences | +5.790 |
ourke | +5.776 |
onent | +5.773 |
Neg logit contributions | |
MRI | -5.350 |
NH | -5.084 |
MO | -5.006 |
MR | -4.920 |
PLE | -4.799 |
Token | z |
Token ID | 89 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
anders | +1.696 |
ourke | +1.481 |
[+ | +1.465 |
defences | +1.441 |
onent | +1.435 |
Neg logit contributions | |
MRI | -1.114 |
NH | -1.048 |
MO | -1.036 |
MR | -1.012 |
PLE | -0.988 |
Token | us |
Token ID | 385 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
MRI | +0.918 |
NH | +0.868 |
MO | +0.864 |
MR | +0.842 |
blu | +0.820 |
Neg logit contributions | |
anders | -1.389 |
ourke | -1.221 |
[+ | -1.207 |
defences | -1.201 |
onent | -1.185 |
Token | on |
Token ID | 319 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
anders | +0.233 |
ourke | +0.202 |
[+ | +0.197 |
defences | +0.196 |
onent | +0.196 |
Neg logit contributions | |
MRI | -0.175 |
NH | -0.168 |
MO | -0.166 |
MR | -0.162 |
PLE | -0.158 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
anders | +1.442 |
ourke | +1.225 |
[+ | +1.207 |
defences | +1.184 |
onent | +1.178 |
Neg logit contributions | |
MRI | -1.367 |
NH | -1.307 |
MO | -1.294 |
MR | -1.267 |
blu | -1.244 |
Token | @ |
Token ID | 2488 |
Feature activation | +8.11e+00 |
Pos logit contributions | |
anders | +1.346 |
ourke | +1.157 |
[+ | +1.143 |
defences | +1.121 |
onent | +1.120 |
Neg logit contributions | |
MRI | -1.137 |
NH | -1.086 |
MO | -1.071 |
MR | -1.049 |
PLE | -1.030 |
Token | dan |
Token ID | 25604 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
anders | +6.220 |
ourke | +5.107 |
[+ | +5.005 |
onent | +4.899 |
iris | +4.865 |
Neg logit contributions | |
MRI | -6.149 |
NH | -5.774 |
MO | -5.761 |
NR | -5.703 |
blu | -5.697 |
Token | han |
Token ID | 7637 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
anders | +8.253 |
iris | +6.474 |
ourke | +6.469 |
[+ | +6.463 |
onent | +6.247 |
Neg logit contributions | |
MRI | -8.341 |
NR | -8.166 |
MO | -8.082 |
Skydragon | -8.009 |
MR | -7.910 |
Token | z |
Token ID | 89 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
anders | +10.915 |
ourke | +9.009 |
onent | +8.802 |
[+ | +8.678 |
iris | +8.559 |
Neg logit contributions | |
MRI | -9.762 |
MO | -9.586 |
NR | -9.468 |
Phant | -9.377 |
NH | -9.345 |
Token | us |
Token ID | 385 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
anders | +4.465 |
ourke | +3.795 |
[+ | +3.768 |
iris | +3.664 |
onent | +3.659 |
Neg logit contributions | |
MRI | -3.518 |
MO | -3.363 |
NH | -3.341 |
MR | -3.260 |
PLE | -3.256 |
Token | and |
Token ID | 290 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
anders | +5.331 |
ourke | +4.647 |
[+ | +4.632 |
onent | +4.489 |
defences | +4.481 |
Neg logit contributions | |
MRI | -3.249 |
NH | -3.024 |
MO | -2.994 |
MR | -2.918 |
PLE | -2.865 |
Token | check |
Token ID | 2198 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
anders | +0.597 |
ourke | +0.516 |
[+ | +0.507 |
defences | +0.503 |
onent | +0.498 |
Neg logit contributions | |
MRI | -0.429 |
NH | -0.410 |
MO | -0.403 |
MR | -0.395 |
blu | -0.388 |
Token | CBS |
Token ID | 11133 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
MRI | +5.190 |
NR | +5.164 |
MO | +5.044 |
NH | +4.998 |
MR | +4.955 |
Neg logit contributions | |
anders | -8.878 |
jriwal | -7.790 |
ourke | -7.711 |
berra | -7.639 |
defences | -7.613 |
Token | Amy |
Token ID | 14235 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
MRI | +2.970 |
MO | +2.851 |
NH | +2.847 |
MR | +2.803 |
NR | +2.767 |
Neg logit contributions | |
anders | -4.347 |
ourke | -3.725 |
defences | -3.701 |
jriwal | -3.650 |
iris | -3.642 |
Token | Poe |
Token ID | 34815 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
anders | +0.422 |
ourke | +0.358 |
[+ | +0.354 |
defences | +0.348 |
onent | +0.347 |
Neg logit contributions | |
MRI | -0.393 |
NH | -0.377 |
MO | -0.372 |
MR | -0.366 |
NR | -0.359 |
Token | hler |
Token ID | 49737 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
anders | +2.015 |
ourke | +1.567 |
[+ | +1.525 |
defences | +1.473 |
onent | +1.469 |
Neg logit contributions | |
MRI | -3.769 |
NH | -3.628 |
MO | -3.605 |
MR | -3.546 |
PLE | -3.531 |
Token | Parks |
Token ID | 20604 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
MRI | +1.871 |
NH | +1.778 |
MO | +1.766 |
NR | +1.738 |
MR | +1.735 |
Neg logit contributions | |
anders | -2.926 |
ourke | -2.554 |
defences | -2.498 |
iris | -2.469 |
onent | -2.462 |
Token | and |
Token ID | 290 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
anders | +4.019 |
ourke | +3.464 |
[+ | +3.457 |
defences | +3.371 |
iris | +3.352 |
Neg logit contributions | |
MRI | -2.734 |
NH | -2.524 |
MO | -2.489 |
MR | -2.425 |
PLE | -2.413 |
Token | Recreation |
Token ID | 34285 |
Feature activation | -9.96e+00 |
Pos logit contributions | |
anders | +6.589 |
ourke | +5.496 |
onent | +5.114 |
iar | +4.951 |
る | +4.917 |
Neg logit contributions | |
MRI | -9.927 |
NH | -9.480 |
MO | -9.306 |
LESS | -9.124 |
blu | -8.979 |
Token | NBC |
Token ID | 9716 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
NR | +5.350 |
MRI | +5.327 |
MO | +5.177 |
NH | +5.115 |
blu | +5.044 |
Neg logit contributions | |
anders | -9.368 |
jriwal | -8.197 |
defences | -8.156 |
ourke | -8.126 |
berra | -8.124 |
Token |
|
Token ID | 198 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
MRI | +1.631 |
NH | +1.562 |
MO | +1.556 |
MR | +1.526 |
NR | +1.509 |
Neg logit contributions | |
anders | -2.446 |
ourke | -2.107 |
defences | -2.071 |
[+ | -2.058 |
iris | -2.051 |
Token |
|
Token ID | 198 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
anders | +0.233 |
ourke | +0.206 |
[+ | +0.204 |
defences | +0.200 |
onent | +0.200 |
Neg logit contributions | |
MRI | -0.125 |
NH | -0.117 |
MO | -0.115 |
MR | -0.112 |
PLE | -0.109 |
Token | Out |
Token ID | 7975 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
MRI | +1.064 |
NH | +1.019 |
MO | +1.011 |
MR | +0.974 |
PLE | +0.960 |
Neg logit contributions | |
anders | -1.668 |
[+ | -1.457 |
defences | -1.456 |
ourke | -1.454 |
onent | -1.419 |
Token | and |
Token ID | 290 |
Feature activation | +8.03e+00 |
Pos logit contributions | |
anders | +0.594 |
ourke | +0.521 |
[+ | +0.512 |
onent | +0.506 |
defences | +0.504 |
Neg logit contributions | |
MRI | -0.369 |
NH | -0.350 |
MO | -0.345 |
MR | -0.338 |
blu | -0.329 |
Token | I |
Token ID | 314 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
anders | +6.786 |
[+ | +5.862 |
defences | +5.779 |
ourke | +5.776 |
iris | +5.630 |
Neg logit contributions | |
MRI | -5.447 |
NH | -5.103 |
MO | -5.024 |
MR | -4.851 |
PLE | -4.768 |
Token | am |
Token ID | 716 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
anders | +4.003 |
[+ | +3.454 |
ourke | +3.451 |
defences | +3.375 |
iris | +3.339 |
Neg logit contributions | |
MRI | -3.004 |
NH | -2.840 |
MO | -2.793 |
MR | -2.732 |
PLE | -2.680 |
Token | going |
Token ID | 1016 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
anders | +3.098 |
ourke | +2.673 |
[+ | +2.652 |
defences | +2.599 |
onent | +2.583 |
Neg logit contributions | |
MRI | -2.379 |
NH | -2.253 |
MO | -2.222 |
MR | -2.172 |
PLE | -2.130 |
Token | to |
Token ID | 284 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
anders | +2.228 |
ourke | +1.940 |
[+ | +1.923 |
defences | +1.885 |
onent | +1.878 |
Neg logit contributions | |
MRI | -1.508 |
NH | -1.423 |
MO | -1.404 |
MR | -1.372 |
PLE | -1.343 |
Token | do |
Token ID | 466 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
anders | +1.879 |
ourke | +1.636 |
[+ | +1.626 |
defences | +1.594 |
onent | +1.585 |
Neg logit contributions | |
MRI | -1.250 |
NH | -1.178 |
MO | -1.161 |
MR | -1.134 |
PLE | -1.110 |
Token | this |
Token ID | 428 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
anders | +9.944 |
[+ | +8.727 |
defences | +8.391 |
ourke | +8.242 |
iris | +8.107 |
Neg logit contributions | |
MRI | -8.969 |
NH | -8.473 |
MO | -8.410 |
MR | -8.082 |
PLE | -8.066 |
Token | . |
Token ID | 13 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
MRI | +2.189 |
NH | +2.056 |
MO | +2.034 |
blu | +2.015 |
MR | +2.010 |
Neg logit contributions | |
anders | -3.563 |
ourke | -3.127 |
onent | -3.034 |
[+ | -2.996 |
iris | -2.982 |
Token | You |
Token ID | 921 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
MRI | +0.120 |
NH | +0.114 |
MO | +0.112 |
MR | +0.110 |
NR | +0.108 |
Neg logit contributions | |
anders | -0.192 |
ourke | -0.169 |
defences | -0.164 |
[+ | -0.163 |
onent | -0.163 |
Token | are |
Token ID | 389 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
MRI | +0.993 |
NH | +0.933 |
MO | +0.926 |
MR | +0.906 |
blu | +0.891 |
Neg logit contributions | |
anders | -1.693 |
ourke | -1.497 |
[+ | -1.474 |
onent | -1.444 |
defences | -1.436 |
Token | going |
Token ID | 1016 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
anders | +0.053 |
ourke | +0.046 |
[+ | +0.046 |
onent | +0.045 |
defences | +0.045 |
Neg logit contributions | |
MRI | -0.038 |
NH | -0.036 |
MO | -0.035 |
MR | -0.035 |
blu | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
anders | +4.702 |
[+ | +4.062 |
ourke | +4.048 |
defences | +3.942 |
onent | +3.933 |
Neg logit contributions | |
MRI | -3.437 |
NH | -3.233 |
MO | -3.204 |
MR | -3.124 |
PLE | -3.066 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
anders | +2.185 |
[+ | +1.915 |
ourke | +1.909 |
onent | +1.856 |
defences | +1.844 |
Neg logit contributions | |
MRI | -1.304 |
NH | -1.215 |
MO | -1.196 |
MR | -1.168 |
blu | -1.148 |
Token | On |
Token ID | 2202 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
anders | +4.108 |
ourke | +3.542 |
[+ | +3.511 |
onent | +3.435 |
defences | +3.434 |
Neg logit contributions | |
MRI | -2.855 |
NH | -2.685 |
MO | -2.660 |
MR | -2.593 |
blu | -2.586 |
Token | 6 |
Token ID | 718 |
Feature activation | +8.40e+00 |
Pos logit contributions | |
MRI | +0.729 |
NH | +0.682 |
MO | +0.674 |
MR | +0.651 |
NR | +0.645 |
Neg logit contributions | |
anders | -1.573 |
ourke | -1.402 |
[+ | -1.373 |
onent | -1.355 |
defences | -1.353 |
Token | October |
Token ID | 3267 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
anders | +6.511 |
[+ | +5.465 |
defences | +5.399 |
ourke | +5.349 |
onent | +5.296 |
Neg logit contributions | |
MRI | -6.173 |
NH | -5.883 |
MO | -5.751 |
MR | -5.684 |
PLE | -5.651 |
Token | 1941 |
Token ID | 23234 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
anders | +6.873 |
defences | +5.719 |
[+ | +5.704 |
ourke | +5.486 |
onent | +5.417 |
Neg logit contributions | |
MRI | -8.331 |
MO | -7.946 |
NH | -7.824 |
PLE | -7.674 |
MR | -7.663 |
Token | Zh |
Token ID | 10511 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
anders | +8.488 |
[+ | +7.218 |
defences | +7.100 |
ourke | +6.985 |
onent | +6.802 |
Neg logit contributions | |
MRI | -8.106 |
MO | -7.627 |
NH | -7.582 |
MR | -7.379 |
PLE | -7.290 |
Token | uk |
Token ID | 2724 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
anders | +3.423 |
ourke | +2.926 |
[+ | +2.877 |
onent | +2.833 |
iris | +2.812 |
Neg logit contributions | |
MRI | -2.744 |
NH | -2.596 |
MO | -2.567 |
MR | -2.519 |
PLE | -2.484 |
Token | ov |
Token ID | 709 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
anders | +0.963 |
ourke | +0.805 |
[+ | +0.795 |
defences | +0.775 |
onent | +0.771 |
Neg logit contributions | |
MRI | -1.086 |
NH | -1.040 |
MO | -1.029 |
MR | -1.011 |
PLE | -0.995 |
Token | was |
Token ID | 373 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
anders | +3.118 |
ourke | +2.698 |
[+ | +2.676 |
defences | +2.621 |
onent | +2.609 |
Neg logit contributions | |
MRI | -2.290 |
NH | -2.167 |
MO | -2.138 |
MR | -2.090 |
PLE | -2.052 |
Token | appointed |
Token ID | 9899 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
anders | +0.104 |
ourke | +0.091 |
[+ | +0.089 |
defences | +0.087 |
onent | +0.087 |
Neg logit contributions | |
MRI | -0.073 |
NH | -0.069 |
MO | -0.069 |
MR | -0.067 |
NR | -0.066 |
Token | contingent |
Token ID | 25477 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
MRI | +0.261 |
NH | +0.248 |
MO | +0.244 |
MR | +0.239 |
blu | +0.235 |
Neg logit contributions | |
anders | -0.385 |
ourke | -0.335 |
[+ | -0.327 |
defences | -0.322 |
iris | -0.322 |
Token | on |
Token ID | 319 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
anders | +1.826 |
ourke | +1.586 |
[+ | +1.558 |
onent | +1.530 |
defences | +1.528 |
Neg logit contributions | |
MRI | -1.303 |
NH | -1.237 |
MO | -1.217 |
MR | -1.195 |
PLE | -1.168 |
Token | revenues |
Token ID | 13089 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
anders | +3.032 |
ourke | +2.636 |
[+ | +2.612 |
defences | +2.557 |
onent | +2.547 |
Neg logit contributions | |
MRI | -2.177 |
NH | -2.057 |
MO | -2.031 |
MR | -1.983 |
PLE | -1.945 |
Token | or |
Token ID | 393 |
Feature activation | +6.25e+00 |
Pos logit contributions | |
anders | +2.827 |
ourke | +2.478 |
[+ | +2.461 |
defences | +2.412 |
onent | +2.404 |
Neg logit contributions | |
MRI | -1.689 |
NH | -1.585 |
MO | -1.565 |
MR | -1.521 |
PLE | -1.491 |
Token | earnings |
Token ID | 12042 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
anders | +5.261 |
ourke | +4.616 |
[+ | +4.578 |
defences | +4.522 |
onent | +4.453 |
Neg logit contributions | |
MRI | -4.238 |
NH | -4.013 |
MO | -3.952 |
MR | -3.830 |
PLE | -3.810 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
anders | +0.131 |
ourke | +0.116 |
[+ | +0.113 |
defences | +0.112 |
onent | +0.112 |
Neg logit contributions | |
MRI | -0.074 |
NH | -0.070 |
MO | -0.069 |
MR | -0.068 |
NR | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
anders | +1.827 |
ourke | +1.599 |
[+ | +1.574 |
defences | +1.562 |
onent | +1.545 |
Neg logit contributions | |
MRI | -1.110 |
NH | -1.046 |
MO | -1.032 |
MR | -1.007 |
NR | -0.988 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
anders | +1.370 |
ourke | +1.204 |
[+ | +1.200 |
onent | +1.172 |
defences | +1.167 |
Neg logit contributions | |
MRI | -0.761 |
NH | -0.712 |
MO | -0.701 |
MR | -0.682 |
PLE | -0.668 |
Token | However |
Token ID | 4864 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
anders | +2.113 |
ourke | +1.847 |
[+ | +1.832 |
defences | +1.801 |
onent | +1.790 |
Neg logit contributions | |
MRI | -1.334 |
NH | -1.258 |
MO | -1.240 |
MR | -1.210 |
PLE | -1.184 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
anders | +1.812 |
ourke | +1.593 |
[+ | +1.575 |
defences | +1.545 |
onent | +1.542 |
Neg logit contributions | |
MRI | -1.105 |
NH | -1.036 |
MO | -1.022 |
MR | -0.995 |
PLE | -0.973 |
Token | a |
Token ID | 257 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
anders | +1.241 |
ourke | +1.069 |
[+ | +1.059 |
defences | +1.038 |
iris | +1.036 |
Neg logit contributions | |
MRI | -0.887 |
NH | -0.845 |
MO | -0.831 |
MR | -0.815 |
NR | -0.804 |
Token | ownership |
Token ID | 9238 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
MRI | +1.344 |
NH | +1.237 |
MO | +1.215 |
NR | +1.178 |
blu | +1.173 |
Neg logit contributions | |
anders | -3.548 |
ourke | -3.197 |
[+ | -3.106 |
onent | -3.097 |
iris | -3.086 |
Token | ," |
Token ID | 553 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
anders | +3.133 |
ourke | +2.701 |
[+ | +2.692 |
defences | +2.636 |
onent | +2.607 |
Neg logit contributions | |
MRI | -2.371 |
NH | -2.237 |
MO | -2.213 |
MR | -2.156 |
PLE | -2.116 |
Token | one |
Token ID | 530 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
anders | +0.188 |
ourke | +0.162 |
[+ | +0.158 |
onent | +0.155 |
defences | +0.155 |
Neg logit contributions | |
MRI | -0.155 |
NH | -0.147 |
MO | -0.145 |
MR | -0.142 |
NR | -0.141 |
Token | NBA |
Token ID | 7403 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
anders | +2.260 |
ourke | +1.920 |
[+ | +1.895 |
defences | +1.850 |
onent | +1.840 |
Neg logit contributions | |
MRI | -2.158 |
NH | -2.059 |
MO | -2.037 |
MR | -1.997 |
PLE | -1.964 |
Token | general |
Token ID | 2276 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
anders | +1.805 |
ourke | +1.539 |
[+ | +1.519 |
defences | +1.483 |
onent | +1.473 |
Neg logit contributions | |
MRI | -1.648 |
NH | -1.571 |
MO | -1.559 |
MR | -1.525 |
PLE | -1.498 |
Token | manager |
Token ID | 4706 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
anders | +0.979 |
ourke | +0.826 |
[+ | +0.816 |
defences | +0.795 |
onent | +0.790 |
Neg logit contributions | |
MRI | -1.014 |
NH | -0.969 |
MO | -0.961 |
MR | -0.940 |
PLE | -0.925 |
Token | said |
Token ID | 531 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
anders | +2.375 |
ourke | +2.057 |
[+ | +2.042 |
defences | +2.000 |
onent | +1.990 |
Neg logit contributions | |
MRI | -1.754 |
NH | -1.659 |
MO | -1.633 |
MR | -1.600 |
PLE | -1.570 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
anders | +1.208 |
ourke | +1.058 |
[+ | +1.046 |
defences | +1.027 |
onent | +1.026 |
Neg logit contributions | |
MRI | -0.732 |
NH | -0.690 |
MO | -0.680 |
MR | -0.664 |
PLE | -0.649 |
Token | "… |
Token ID | 29368 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
anders | +1.288 |
ourke | +1.117 |
[+ | +1.095 |
defences | +1.085 |
onent | +1.074 |
Neg logit contributions | |
MRI | -0.969 |
NH | -0.917 |
MO | -0.906 |
MR | -0.887 |
PLE | -0.870 |
Token | Maybe |
Token ID | 13300 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
MRI | +2.809 |
NH | +2.668 |
MO | +2.618 |
MR | +2.586 |
PLE | +2.536 |
Neg logit contributions | |
anders | -4.607 |
ourke | -4.158 |
defences | -4.016 |
onent | -3.965 |
iris | -3.956 |
Token | just |
Token ID | 655 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
anders | +0.205 |
ourke | +0.179 |
[+ | +0.175 |
onent | +0.173 |
defences | +0.172 |
Neg logit contributions | |
MRI | -0.141 |
NH | -0.133 |
MO | -0.132 |
MR | -0.129 |
blu | -0.126 |
Token | world |
Token ID | 995 |
Feature activation | -8.26e+00 |
Pos logit contributions | |
MRI | +2.355 |
blu | +2.269 |
MO | +2.252 |
NH | +2.242 |
NR | +2.227 |
Neg logit contributions | |
anders | -3.525 |
ourke | -3.090 |
[+ | -3.034 |
onent | -2.999 |
iris | -2.989 |
Token | . |
Token ID | 13 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
MRI | +4.090 |
blu | +3.941 |
NH | +3.846 |
NR | +3.827 |
MR | +3.791 |
Neg logit contributions | |
anders | -8.042 |
ourke | -7.206 |
onent | -6.938 |
[+ | -6.893 |
ricanes | -6.798 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
MRI | +0.444 |
NH | +0.418 |
MO | +0.414 |
MR | +0.406 |
NR | +0.402 |
Neg logit contributions | |
anders | -0.814 |
ourke | -0.724 |
defences | -0.712 |
onent | -0.699 |
iris | -0.698 |
Token | It |
Token ID | 1026 |
Feature activation | +6.16e+00 |
Pos logit contributions | |
MRI | +0.613 |
NH | +0.580 |
MO | +0.575 |
MR | +0.560 |
PLE | +0.550 |
Neg logit contributions | |
anders | -0.970 |
ourke | -0.854 |
[+ | -0.845 |
defences | -0.840 |
onent | -0.828 |
Token | is |
Token ID | 318 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
anders | +5.173 |
ourke | +4.432 |
[+ | +4.415 |
defences | +4.289 |
iris | +4.273 |
Neg logit contributions | |
MRI | -4.313 |
NH | -4.092 |
MO | -4.021 |
MR | -3.952 |
PLE | -3.885 |
Token | impossible |
Token ID | 5340 |
Feature activation | +8.73e+00 |
Pos logit contributions | |
anders | +3.333 |
[+ | +2.899 |
ourke | +2.897 |
defences | +2.830 |
onent | +2.805 |
Neg logit contributions | |
MRI | -2.373 |
NH | -2.238 |
MO | -2.199 |
MR | -2.145 |
PLE | -2.108 |
Token | to |
Token ID | 284 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
anders | +6.935 |
[+ | +6.021 |
ourke | +5.924 |
defences | +5.792 |
onent | +5.755 |
Neg logit contributions | |
MRI | -6.281 |
NH | -5.762 |
MO | -5.679 |
MR | -5.661 |
blu | -5.554 |
Token | identify |
Token ID | 5911 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
anders | +4.045 |
[+ | +3.523 |
ourke | +3.476 |
defences | +3.422 |
onent | +3.416 |
Neg logit contributions | |
MRI | -2.962 |
NH | -2.798 |
MO | -2.740 |
MR | -2.704 |
PLE | -2.636 |
Token | what |
Token ID | 644 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
anders | +0.785 |
ourke | +0.685 |
[+ | +0.673 |
onent | +0.663 |
defences | +0.659 |
Neg logit contributions | |
MRI | -0.542 |
NH | -0.514 |
MO | -0.508 |
MR | -0.496 |
blu | -0.488 |
Token | made |
Token ID | 925 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
MRI | +0.628 |
NH | +0.597 |
MO | +0.592 |
MR | +0.579 |
blu | +0.573 |
Neg logit contributions | |
anders | -0.880 |
ourke | -0.764 |
[+ | -0.751 |
onent | -0.740 |
iris | -0.738 |
Token | F |
Token ID | 376 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
MRI | +1.612 |
NH | +1.538 |
MO | +1.518 |
MR | +1.496 |
NR | +1.494 |
Neg logit contributions | |
anders | -2.294 |
ourke | -2.003 |
[+ | -1.951 |
iris | -1.926 |
onent | -1.923 |
Token | 's |
Token ID | 338 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
anders | +2.734 |
ourke | +2.369 |
[+ | +2.342 |
defences | +2.296 |
onent | +2.290 |
Neg logit contributions | |
MRI | -2.052 |
NH | -1.945 |
MO | -1.921 |
MR | -1.877 |
PLE | -1.842 |
Token | some |
Token ID | 617 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
anders | +3.599 |
ourke | +3.116 |
[+ | +3.094 |
defences | +3.033 |
onent | +3.006 |
Neg logit contributions | |
MRI | -2.751 |
NH | -2.609 |
MO | -2.574 |
MR | -2.518 |
PLE | -2.473 |
Token | last |
Token ID | 938 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
MRI | +2.335 |
NH | +2.222 |
MO | +2.197 |
NR | +2.153 |
blu | +2.146 |
Neg logit contributions | |
anders | -3.457 |
ourke | -2.994 |
[+ | -2.936 |
onent | -2.880 |
defences | -2.864 |
Token | - |
Token ID | 12 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
MRI | +0.400 |
NH | +0.375 |
MO | +0.373 |
MR | +0.362 |
blu | +0.358 |
Neg logit contributions | |
anders | -0.694 |
ourke | -0.612 |
[+ | -0.606 |
onent | -0.594 |
iris | -0.588 |
Token | minute |
Token ID | 11374 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
MRI | +2.185 |
MO | +2.054 |
NH | +2.045 |
MR | +1.984 |
PLE | +1.915 |
Neg logit contributions | |
anders | -4.092 |
ourke | -3.653 |
[+ | -3.598 |
onent | -3.558 |
defences | -3.541 |
Token | marketing |
Token ID | 7124 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
MRI | +1.797 |
MO | +1.705 |
NH | +1.704 |
blu | +1.681 |
NR | +1.672 |
Neg logit contributions | |
anders | -2.234 |
ourke | -1.901 |
[+ | -1.869 |
iris | -1.842 |
onent | -1.842 |
Token | for |
Token ID | 329 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
anders | +1.170 |
ourke | +1.004 |
[+ | +0.992 |
defences | +0.970 |
onent | +0.967 |
Neg logit contributions | |
MRI | -0.986 |
NH | -0.938 |
MO | -0.928 |
MR | -0.908 |
PLE | -0.892 |
Token | The |
Token ID | 383 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
anders | +0.633 |
ourke | +0.550 |
[+ | +0.545 |
onent | +0.534 |
defences | +0.533 |
Neg logit contributions | |
MRI | -0.423 |
NH | -0.401 |
MO | -0.397 |
MR | -0.387 |
NR | -0.381 |
Token | Pur |
Token ID | 9330 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
anders | +3.650 |
ourke | +3.144 |
[+ | +3.126 |
defences | +3.032 |
onent | +3.026 |
Neg logit contributions | |
MRI | -2.997 |
NH | -2.837 |
MO | -2.789 |
MR | -2.729 |
PLE | -2.695 |
Token | ge |
Token ID | 469 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
anders | +1.921 |
ourke | +1.633 |
[+ | +1.614 |
defences | +1.576 |
onent | +1.569 |
Neg logit contributions | |
MRI | -1.804 |
NH | -1.720 |
MO | -1.700 |
MR | -1.667 |
PLE | -1.638 |
Token | : |
Token ID | 25 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
MRI | +0.855 |
NH | +0.816 |
MO | +0.810 |
MR | +0.787 |
blu | +0.775 |
Neg logit contributions | |
anders | -1.378 |
ourke | -1.216 |
[+ | -1.199 |
defences | -1.182 |
iris | -1.178 |
Token | p |
Token ID | 79 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
anders | +1.387 |
ourke | +1.224 |
[+ | +1.213 |
onent | +1.187 |
defences | +1.184 |
Neg logit contributions | |
MRI | -0.755 |
NH | -0.710 |
MO | -0.696 |
MR | -0.678 |
PLE | -0.661 |
Token | ra |
Token ID | 430 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
MRI | +1.042 |
NH | +0.937 |
MO | +0.921 |
MR | +0.901 |
NR | +0.868 |
Neg logit contributions | |
anders | -2.398 |
[+ | -2.133 |
ourke | -2.130 |
defences | -2.110 |
る | -2.071 |
Token | e |
Token ID | 68 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
anders | +1.799 |
ourke | +1.564 |
[+ | +1.548 |
onent | +1.517 |
defences | +1.513 |
Neg logit contributions | |
MRI | -1.226 |
NH | -1.162 |
MO | -1.144 |
MR | -1.117 |
PLE | -1.097 |
Token | multiplied |
Token ID | 33096 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
anders | +0.873 |
ourke | +0.762 |
[+ | +0.747 |
onent | +0.732 |
iris | +0.729 |
Neg logit contributions | |
MRI | -0.641 |
NH | -0.609 |
MO | -0.602 |
MR | -0.590 |
blu | -0.577 |
Token | in |
Token ID | 287 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
anders | +3.314 |
ourke | +2.868 |
[+ | +2.859 |
defences | +2.797 |
onent | +2.781 |
Neg logit contributions | |
MRI | -2.431 |
NH | -2.289 |
MO | -2.265 |
MR | -2.212 |
PLE | -2.173 |
Token | mac |
Token ID | 8352 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
anders | +1.643 |
ourke | +1.432 |
[+ | +1.413 |
defences | +1.382 |
onent | +1.381 |
Neg logit contributions | |
MRI | -1.170 |
NH | -1.111 |
MO | -1.097 |
MR | -1.073 |
blu | -1.051 |
Token | roph |
Token ID | 10051 |
Feature activation | +6.41e+00 |
Pos logit contributions | |
anders | +2.677 |
ourke | +2.191 |
[+ | +2.171 |
onent | +2.100 |
defences | +2.099 |
Neg logit contributions | |
MRI | -3.496 |
NH | -3.352 |
MO | -3.322 |
MR | -3.267 |
PLE | -3.225 |
Token | ages |
Token ID | 1095 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
anders | +3.627 |
ourke | +2.895 |
[+ | +2.807 |
onent | +2.756 |
iris | +2.726 |
Neg logit contributions | |
MRI | -6.213 |
NH | -6.009 |
MO | -5.927 |
MR | -5.837 |
blu | -5.813 |
Token | at |
Token ID | 379 |
Feature activation | -8.79e-03 |
Pos logit contributions | |
anders | +3.587 |
ourke | +3.122 |
[+ | +3.113 |
defences | +3.046 |
onent | +3.025 |
Neg logit contributions | |
MRI | -2.377 |
NH | -2.231 |
MO | -2.205 |
MR | -2.152 |
PLE | -2.115 |
Token | the |
Token ID | 262 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
MRI | +0.005 |
NH | +0.005 |
MO | +0.005 |
MR | +0.005 |
NR | +0.005 |
Neg logit contributions | |
anders | -0.008 |
ourke | -0.007 |
[+ | -0.007 |
onent | -0.007 |
defences | -0.007 |
Token | site |
Token ID | 2524 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
anders | +2.123 |
ourke | +1.830 |
[+ | +1.806 |
defences | +1.766 |
onent | +1.764 |
Neg logit contributions | |
MRI | -1.692 |
NH | -1.609 |
MO | -1.590 |
MR | -1.556 |
blu | -1.526 |
Token | simple |
Token ID | 2829 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
MRI | +0.455 |
NH | +0.435 |
MO | +0.431 |
MR | +0.423 |
blu | +0.418 |
Neg logit contributions | |
anders | -0.490 |
ourke | -0.414 |
[+ | -0.411 |
defences | -0.403 |
onent | -0.400 |
Token | passing |
Token ID | 6427 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
anders | +4.374 |
ourke | +3.812 |
[+ | +3.794 |
defences | +3.701 |
onent | +3.675 |
Neg logit contributions | |
MRI | -3.433 |
NH | -3.239 |
MO | -3.199 |
MR | -3.117 |
PLE | -3.075 |
Token | mention |
Token ID | 3068 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
MRI | +0.159 |
NH | +0.151 |
MO | +0.148 |
MR | +0.145 |
blu | +0.143 |
Neg logit contributions | |
anders | -0.237 |
ourke | -0.205 |
[+ | -0.202 |
defences | -0.199 |
iris | -0.198 |
Token | of |
Token ID | 286 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
anders | +4.610 |
ourke | +4.002 |
[+ | +3.975 |
defences | +3.876 |
onent | +3.847 |
Neg logit contributions | |
MRI | -3.437 |
NH | -3.224 |
MO | -3.201 |
MR | -3.123 |
PLE | -3.057 |
Token | the |
Token ID | 262 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
anders | +1.221 |
ourke | +1.057 |
[+ | +1.047 |
onent | +1.025 |
defences | +1.025 |
Neg logit contributions | |
MRI | -0.895 |
NH | -0.851 |
MO | -0.842 |
MR | -0.823 |
blu | -0.808 |
Token | intervention |
Token ID | 9572 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
MRI | +0.556 |
NH | +0.534 |
MO | +0.529 |
MR | +0.518 |
blu | +0.515 |
Neg logit contributions | |
anders | -0.743 |
ourke | -0.645 |
[+ | -0.636 |
onent | -0.626 |
defences | -0.623 |
Token | of |
Token ID | 286 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
anders | +0.341 |
ourke | +0.289 |
[+ | +0.286 |
onent | +0.279 |
defences | +0.278 |
Neg logit contributions | |
MRI | -0.336 |
NH | -0.322 |
MO | -0.320 |
MR | -0.313 |
blu | -0.308 |
Token | the |
Token ID | 262 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
MRI | +1.107 |
NH | +1.059 |
MO | +1.057 |
MR | +1.035 |
NR | +1.024 |
Neg logit contributions | |
anders | -1.566 |
ourke | -1.358 |
[+ | -1.347 |
onent | -1.327 |
iris | -1.317 |
Token | FBI |
Token ID | 5349 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
MRI | +0.699 |
NH | +0.671 |
MO | +0.669 |
MR | +0.653 |
NR | +0.651 |
Neg logit contributions | |
anders | -0.945 |
ourke | -0.827 |
[+ | -0.815 |
onent | -0.800 |
defences | -0.793 |
Token | down |
Token ID | 866 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
MRI | +0.068 |
NH | +0.065 |
MO | +0.064 |
MR | +0.063 |
blu | +0.062 |
Neg logit contributions | |
anders | -0.100 |
ourke | -0.087 |
[+ | -0.085 |
onent | -0.084 |
defences | -0.084 |
Token | plays |
Token ID | 26024 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
anders | +3.493 |
ourke | +3.023 |
[+ | +2.987 |
defences | +2.932 |
onent | +2.909 |
Neg logit contributions | |
MRI | -2.522 |
NH | -2.387 |
MO | -2.352 |
MR | -2.301 |
PLE | -2.265 |
Token | were |
Token ID | 547 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
anders | +0.350 |
ourke | +0.307 |
[+ | +0.302 |
onent | +0.296 |
defences | +0.296 |
Neg logit contributions | |
MRI | -0.234 |
NH | -0.221 |
MO | -0.219 |
MR | -0.213 |
blu | -0.209 |
Token | some |
Token ID | 617 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
MRI | +1.719 |
NH | +1.653 |
MO | +1.651 |
NR | +1.590 |
blu | +1.587 |
Neg logit contributions | |
anders | -2.486 |
ourke | -2.185 |
[+ | -2.131 |
iris | -2.104 |
onent | -2.099 |
Token | of |
Token ID | 286 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
MRI | +3.459 |
NH | +3.336 |
MO | +3.293 |
MR | +3.204 |
NR | +3.191 |
Neg logit contributions | |
anders | -5.921 |
ourke | -5.236 |
[+ | -5.143 |
onent | -4.977 |
iris | -4.976 |
Token | the |
Token ID | 262 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
MRI | +1.907 |
NH | +1.847 |
MO | +1.806 |
NR | +1.794 |
MR | +1.774 |
Neg logit contributions | |
anders | -3.246 |
ourke | -2.848 |
[+ | -2.809 |
iris | -2.766 |
onent | -2.766 |
Token | local |
Token ID | 1957 |
Feature activation | -5.61e+00 |
Pos logit contributions | |
MRI | +0.644 |
NH | +0.619 |
MO | +0.611 |
blu | +0.599 |
NR | +0.597 |
Neg logit contributions | |
anders | -0.889 |
ourke | -0.777 |
[+ | -0.762 |
onent | -0.751 |
iris | -0.746 |
Token | wildlife |
Token ID | 15599 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
MRI | +3.581 |
MO | +3.494 |
NH | +3.491 |
NR | +3.479 |
blu | +3.460 |
Neg logit contributions | |
anders | -4.746 |
ourke | -4.193 |
[+ | -4.067 |
onent | -4.041 |
iris | -4.023 |
Token | that |
Token ID | 326 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
MRI | +1.763 |
NH | +1.703 |
MO | +1.686 |
NR | +1.655 |
blu | +1.631 |
Neg logit contributions | |
anders | -2.594 |
ourke | -2.285 |
onent | -2.219 |
[+ | -2.217 |
iris | -2.200 |
Token | might |
Token ID | 1244 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
MRI | +0.166 |
NH | +0.158 |
MO | +0.156 |
MR | +0.152 |
NR | +0.149 |
Neg logit contributions | |
anders | -0.247 |
ourke | -0.216 |
[+ | -0.213 |
onent | -0.209 |
defences | -0.208 |
Token | be |
Token ID | 307 |
Feature activation | -5.74e+00 |
Pos logit contributions | |
MRI | +1.012 |
NH | +0.961 |
MO | +0.946 |
MR | +0.918 |
NR | +0.912 |
Neg logit contributions | |
anders | -1.875 |
ourke | -1.662 |
[+ | -1.623 |
onent | -1.593 |
iris | -1.589 |
Token | impacted |
Token ID | 20755 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
MRI | +3.477 |
NH | +3.392 |
MO | +3.365 |
NR | +3.297 |
blu | +3.255 |
Neg logit contributions | |
anders | -5.121 |
ourke | -4.508 |
[+ | -4.371 |
onent | -4.354 |
iris | -4.336 |
Token | ? |
Token ID | 30 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
anders | +0.140 |
ourke | +0.122 |
[+ | +0.120 |
defences | +0.118 |
onent | +0.118 |
Neg logit contributions | |
MRI | -0.099 |
NH | -0.094 |
MO | -0.092 |
MR | -0.090 |
NR | -0.089 |
Token | activists |
Token ID | 7941 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
anders | +1.609 |
ourke | +1.377 |
[+ | +1.361 |
defences | +1.334 |
onent | +1.327 |
Neg logit contributions | |
MRI | -1.384 |
NH | -1.313 |
MO | -1.298 |
MR | -1.271 |
PLE | -1.251 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
anders | +4.587 |
ourke | +3.990 |
[+ | +3.953 |
defences | +3.866 |
onent | +3.845 |
Neg logit contributions | |
MRI | -3.095 |
NH | -2.901 |
MO | -2.854 |
MR | -2.787 |
PLE | -2.747 |
Token | the |
Token ID | 262 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
MRI | +0.728 |
NH | +0.697 |
MO | +0.694 |
MR | +0.678 |
NR | +0.677 |
Neg logit contributions | |
anders | -1.037 |
ourke | -0.906 |
[+ | -0.903 |
iris | -0.875 |
onent | -0.875 |
Token | Koch |
Token ID | 17009 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
MRI | +1.005 |
MO | +0.963 |
NH | +0.961 |
NR | +0.945 |
MR | +0.938 |
Neg logit contributions | |
anders | -1.868 |
ourke | -1.670 |
[+ | -1.668 |
iris | -1.615 |
onent | -1.614 |
Token | Brothers |
Token ID | 16055 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
MRI | +0.128 |
NH | +0.121 |
MO | +0.121 |
MR | +0.118 |
PLE | +0.115 |
Neg logit contributions | |
anders | -0.189 |
ourke | -0.166 |
[+ | -0.164 |
defences | -0.161 |
onent | -0.160 |
Token | — |
Token ID | 851 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
anders | +1.656 |
ourke | +1.450 |
[+ | +1.437 |
defences | +1.410 |
onent | +1.407 |
Neg logit contributions | |
MRI | -1.041 |
NH | -0.983 |
MO | -0.973 |
MR | -0.948 |
PLE | -0.925 |
Token | those |
Token ID | 883 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
MRI | +0.946 |
NH | +0.910 |
MO | +0.903 |
MR | +0.884 |
NR | +0.870 |
Neg logit contributions | |
anders | -1.416 |
ourke | -1.241 |
[+ | -1.237 |
onent | -1.206 |
iris | -1.205 |
Token | uber |
Token ID | 48110 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
MRI | +2.535 |
MO | +2.470 |
NH | +2.453 |
NR | +2.434 |
blu | +2.422 |
Neg logit contributions | |
anders | -3.545 |
ourke | -3.103 |
[+ | -3.102 |
onent | -3.019 |
iris | -2.984 |
Token | - |
Token ID | 12 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
MRI | +1.985 |
MO | +1.936 |
NH | +1.906 |
MR | +1.851 |
NR | +1.808 |
Neg logit contributions | |
anders | -3.967 |
ourke | -3.585 |
[+ | -3.564 |
onent | -3.466 |
defences | -3.461 |
Token | wealth |
Token ID | 14298 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
MRI | +2.730 |
MO | +2.669 |
NH | +2.634 |
MR | +2.589 |
PLE | +2.477 |
Neg logit contributions | |
anders | -4.163 |
[+ | -3.773 |
ourke | -3.743 |
defences | -3.675 |
onent | -3.602 |
Token | y |
Token ID | 88 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
anders | +0.701 |
ourke | +0.585 |
[+ | +0.577 |
defences | +0.561 |
onent | +0.559 |
Neg logit contributions | |
MRI | -0.825 |
NH | -0.791 |
MO | -0.784 |
MR | -0.770 |
PLE | -0.757 |
Token | ppy |
Token ID | 14097 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
anders | +1.649 |
ourke | +1.415 |
[+ | +1.399 |
defences | +1.368 |
onent | +1.363 |
Neg logit contributions | |
MRI | -1.408 |
NH | -1.340 |
MO | -1.325 |
MR | -1.298 |
PLE | -1.274 |
Token | Har |
Token ID | 2113 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
MRI | +1.185 |
NH | +1.125 |
MO | +1.114 |
MR | +1.088 |
PLE | +1.069 |
Neg logit contributions | |
anders | -1.514 |
ourke | -1.315 |
[+ | -1.295 |
defences | -1.268 |
onent | -1.262 |
Token | low |
Token ID | 9319 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
MRI | +1.997 |
NH | +1.796 |
MO | +1.706 |
phys | +1.690 |
blu | +1.657 |
Neg logit contributions | |
anders | -4.962 |
defences | -4.493 |
[+ | -4.461 |
onent | -4.391 |
ourke | -4.386 |
Token | , |
Token ID | 11 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
MRI | +0.708 |
NH | +0.677 |
MO | +0.666 |
MR | +0.649 |
NR | +0.640 |
Neg logit contributions | |
anders | -1.117 |
ourke | -0.981 |
[+ | -0.964 |
defences | -0.962 |
onent | -0.959 |
Token | Brian |
Token ID | 8403 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
anders | +3.109 |
ourke | +2.702 |
[+ | +2.671 |
defences | +2.609 |
onent | +2.600 |
Neg logit contributions | |
MRI | -2.304 |
NH | -2.168 |
MO | -2.148 |
MR | -2.093 |
PLE | -2.063 |
Token | Todd |
Token ID | 14377 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
MRI | +1.043 |
NH | +0.989 |
MO | +0.963 |
MR | +0.949 |
NR | +0.938 |
Neg logit contributions | |
anders | -1.838 |
ourke | -1.634 |
[+ | -1.618 |
defences | -1.591 |
onent | -1.582 |
Token | , |
Token ID | 11 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
MRI | +2.236 |
NH | +2.145 |
MO | +2.092 |
NR | +2.050 |
MR | +2.001 |
Neg logit contributions | |
anders | -4.353 |
ourke | -3.816 |
defences | -3.786 |
onent | -3.777 |
[+ | -3.777 |
Token | Jason |
Token ID | 8982 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
anders | +3.610 |
ourke | +3.133 |
[+ | +3.102 |
defences | +3.034 |
onent | +3.014 |
Neg logit contributions | |
MRI | -2.610 |
NH | -2.451 |
MO | -2.425 |
MR | -2.360 |
PLE | -2.328 |
Token | Carroll |
Token ID | 21298 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
MRI | +3.120 |
NH | +2.942 |
MR | +2.925 |
NR | +2.898 |
MO | +2.898 |
Neg logit contributions | |
anders | -4.458 |
ourke | -3.852 |
[+ | -3.838 |
onent | -3.825 |
iris | -3.801 |
Token | , |
Token ID | 11 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
anders | +4.381 |
ourke | +3.829 |
[+ | +3.791 |
iris | +3.691 |
defences | +3.674 |
Neg logit contributions | |
MRI | -2.858 |
NH | -2.653 |
MO | -2.609 |
MR | -2.569 |
PLE | -2.517 |
Token | Pete |
Token ID | 17542 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
anders | +3.379 |
ourke | +2.930 |
[+ | +2.903 |
defences | +2.840 |
onent | +2.822 |
Neg logit contributions | |
MRI | -2.433 |
NH | -2.288 |
MO | -2.262 |
MR | -2.204 |
PLE | -2.171 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
MRI | +1.009 |
NH | +0.977 |
MO | +0.960 |
MR | +0.932 |
blu | +0.930 |
Neg logit contributions | |
anders | -1.758 |
ourke | -1.532 |
[+ | -1.509 |
onent | -1.489 |
iris | -1.480 |
Token | We |
Token ID | 775 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
MRI | +1.035 |
NH | +0.983 |
MO | +0.972 |
MR | +0.946 |
NR | +0.930 |
Neg logit contributions | |
anders | -1.727 |
ourke | -1.522 |
defences | -1.482 |
onent | -1.466 |
iris | -1.463 |
Token | came |
Token ID | 1625 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
anders | +0.048 |
ourke | +0.042 |
[+ | +0.042 |
defences | +0.041 |
onent | +0.041 |
Neg logit contributions | |
MRI | -0.029 |
NH | -0.028 |
MO | -0.027 |
MR | -0.027 |
blu | -0.026 |
Token | away |
Token ID | 1497 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
MRI | +0.391 |
NH | +0.377 |
MO | +0.372 |
MR | +0.362 |
blu | +0.358 |
Neg logit contributions | |
anders | -0.531 |
ourke | -0.464 |
[+ | -0.455 |
onent | -0.446 |
defences | -0.444 |
Token | thinking |
Token ID | 3612 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
MRI | +1.473 |
NH | +1.405 |
MO | +1.367 |
MR | +1.359 |
NR | +1.347 |
Neg logit contributions | |
anders | -2.645 |
ourke | -2.382 |
[+ | -2.298 |
onent | -2.279 |
iris | -2.243 |
Token | we |
Token ID | 356 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
anders | +0.102 |
ourke | +0.089 |
[+ | +0.087 |
onent | +0.086 |
iris | +0.086 |
Neg logit contributions | |
MRI | -0.066 |
NH | -0.063 |
MO | -0.062 |
MR | -0.060 |
NR | -0.059 |
Token | could |
Token ID | 714 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
MRI | +1.114 |
MO | +1.041 |
NH | +1.040 |
MR | +1.014 |
blu | +0.996 |
Neg logit contributions | |
anders | -2.049 |
ourke | -1.808 |
[+ | -1.780 |
onent | -1.742 |
defences | -1.737 |
Token | have |
Token ID | 423 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
MRI | +0.447 |
NH | +0.423 |
MO | +0.420 |
MR | +0.409 |
blu | +0.404 |
Neg logit contributions | |
anders | -0.674 |
ourke | -0.587 |
[+ | -0.574 |
iris | -0.563 |
defences | -0.562 |
Token | got |
Token ID | 1392 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
anders | +1.291 |
ourke | +1.123 |
[+ | +1.111 |
defences | +1.088 |
onent | +1.085 |
Neg logit contributions | |
MRI | -0.893 |
NH | -0.844 |
MO | -0.834 |
MR | -0.814 |
PLE | -0.797 |
Token | a |
Token ID | 257 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
anders | +2.974 |
ourke | +2.580 |
[+ | +2.562 |
defences | +2.523 |
onent | +2.497 |
Neg logit contributions | |
MRI | -2.136 |
NH | -2.002 |
MO | -1.983 |
MR | -1.935 |
PLE | -1.905 |
Token | draw |
Token ID | 3197 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
anders | +0.844 |
ourke | +0.723 |
[+ | +0.716 |
onent | +0.700 |
defences | +0.700 |
Neg logit contributions | |
MRI | -0.673 |
NH | -0.642 |
MO | -0.635 |
MR | -0.620 |
blu | -0.613 |
Token | in |
Token ID | 287 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
MRI | +0.827 |
NH | +0.784 |
MO | +0.778 |
MR | +0.759 |
blu | +0.750 |
Neg logit contributions | |
anders | -1.321 |
ourke | -1.154 |
[+ | -1.127 |
onent | -1.113 |
iris | -1.110 |
Token | pretty |
Token ID | 2495 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
MRI | +1.706 |
NH | +1.663 |
MO | +1.652 |
blu | +1.615 |
NR | +1.613 |
Neg logit contributions | |
anders | -3.005 |
[+ | -2.672 |
ourke | -2.658 |
iris | -2.628 |
onent | -2.555 |
Token | short |
Token ID | 1790 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
anders | +0.529 |
ourke | +0.456 |
[+ | +0.449 |
iris | +0.438 |
defences | +0.436 |
Neg logit contributions | |
MRI | -0.447 |
NH | -0.425 |
MO | -0.421 |
MR | -0.413 |
blu | -0.409 |
Token | order |
Token ID | 1502 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
MRI | +1.996 |
NH | +1.882 |
MO | +1.863 |
blu | +1.828 |
MR | +1.822 |
Neg logit contributions | |
anders | -3.785 |
ourke | -3.339 |
[+ | -3.255 |
iris | -3.239 |
onent | -3.200 |
Token | . |
Token ID | 13 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
MRI | +1.517 |
NH | +1.461 |
MO | +1.426 |
MR | +1.392 |
PLE | +1.351 |
Neg logit contributions | |
anders | -3.153 |
ourke | -2.806 |
onent | -2.712 |
defences | -2.700 |
[+ | -2.699 |
Token | (" |
Token ID | 5855 |
Feature activation | -9.46e+00 |
Pos logit contributions | |
MRI | +0.047 |
NH | +0.045 |
MO | +0.045 |
MR | +0.044 |
PLE | +0.043 |
Neg logit contributions | |
anders | -0.073 |
ourke | -0.064 |
defences | -0.062 |
[+ | -0.062 |
onent | -0.061 |
Token | Power |
Token ID | 13434 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
MRI | +5.210 |
MO | +5.060 |
NH | +5.005 |
MR | +4.942 |
PLE | +4.826 |
Neg logit contributions | |
anders | -8.912 |
ourke | -7.900 |
defences | -7.748 |
[+ | -7.632 |
ricanes | -7.603 |
Token | tends |
Token ID | 12444 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
anders | +2.124 |
ourke | +1.851 |
[+ | +1.833 |
defences | +1.797 |
onent | +1.791 |
Neg logit contributions | |
MRI | -1.424 |
NH | -1.345 |
MO | -1.328 |
MR | -1.296 |
PLE | -1.269 |
Token | to |
Token ID | 284 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
MRI | +1.411 |
NH | +1.354 |
MO | +1.335 |
MR | +1.307 |
blu | +1.281 |
Neg logit contributions | |
anders | -2.281 |
ourke | -1.993 |
[+ | -1.956 |
onent | -1.924 |
iris | -1.922 |
Token | corrupt |
Token ID | 10622 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
MRI | +0.591 |
NH | +0.562 |
MO | +0.559 |
MR | +0.544 |
blu | +0.542 |
Neg logit contributions | |
anders | -0.851 |
ourke | -0.742 |
[+ | -0.726 |
onent | -0.713 |
iris | -0.713 |
Token | ; |
Token ID | 26 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
MRI | +0.957 |
NH | +0.902 |
MO | +0.901 |
MR | +0.884 |
blu | +0.867 |
Neg logit contributions | |
anders | -1.492 |
ourke | -1.301 |
[+ | -1.280 |
iris | -1.252 |
onent | -1.251 |
Token | X |
Token ID | 55 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
MRI | +1.791 |
NH | +1.710 |
MO | +1.702 |
MR | +1.671 |
PLE | +1.593 |
Neg logit contributions | |
anders | -2.395 |
[+ | -2.075 |
ourke | -2.060 |
defences | -2.027 |
onent | -2.001 |
Token | iv |
Token ID | 452 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
anders | +2.838 |
ourke | +2.361 |
[+ | +2.334 |
defences | +2.269 |
onent | +2.250 |
Neg logit contributions | |
MRI | -3.207 |
NH | -3.063 |
MO | -3.016 |
MR | -2.954 |
PLE | -2.932 |
Token | , |
Token ID | 11 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
anders | +3.442 |
ourke | +3.010 |
[+ | +2.993 |
defences | +2.931 |
onent | +2.918 |
Neg logit contributions | |
MRI | -2.112 |
NH | -1.985 |
MO | -1.953 |
MR | -1.907 |
PLE | -1.863 |
Token | before |
Token ID | 878 |
Feature activation | -6.41e+00 |
Pos logit contributions | |
MRI | +0.168 |
NH | +0.159 |
MO | +0.157 |
MR | +0.154 |
blu | +0.150 |
Neg logit contributions | |
anders | -0.255 |
ourke | -0.222 |
[+ | -0.219 |
onent | -0.216 |
defences | -0.216 |
Token | sending |
Token ID | 7216 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
MRI | +3.900 |
MO | +3.750 |
NH | +3.737 |
blu | +3.690 |
NR | +3.674 |
Neg logit contributions | |
anders | -5.795 |
ourke | -5.045 |
[+ | -4.908 |
onent | -4.883 |
iris | -4.848 |
Token | it |
Token ID | 340 |
Feature activation | -9.42e+00 |
Pos logit contributions | |
MRI | +2.291 |
NH | +2.165 |
MO | +2.132 |
MR | +2.077 |
blu | +2.074 |
Neg logit contributions | |
anders | -4.103 |
ourke | -3.601 |
onent | -3.522 |
[+ | -3.521 |
iris | -3.489 |
Token | to |
Token ID | 284 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
MRI | +4.590 |
NH | +4.445 |
MO | +4.426 |
blu | +4.336 |
NR | +4.209 |
Neg logit contributions | |
anders | -9.192 |
ourke | -8.056 |
onent | -7.879 |
iris | -7.862 |
ワン | -7.859 |
Token | a |
Token ID | 257 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
MRI | +2.221 |
NH | +2.103 |
MO | +2.080 |
NR | +2.045 |
MR | +2.034 |
Neg logit contributions | |
anders | -3.438 |
ourke | -3.010 |
[+ | -2.935 |
onent | -2.909 |
defences | -2.877 |
Token | peer |
Token ID | 12720 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
anders | +1.253 |
ourke | +1.081 |
[+ | +1.071 |
defences | +1.048 |
onent | +1.045 |
Neg logit contributions | |
MRI | -0.959 |
NH | -0.910 |
MO | -0.899 |
MR | -0.880 |
blu | -0.863 |
Token | review |
Token ID | 2423 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
MRI | +1.729 |
MO | +1.589 |
NH | +1.581 |
MR | +1.548 |
NR | +1.511 |
Neg logit contributions | |
anders | -3.414 |
ourke | -3.027 |
[+ | -2.904 |
iris | -2.896 |
onent | -2.886 |
Token | journal |
Token ID | 3989 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
MRI | +0.821 |
NH | +0.779 |
MO | +0.764 |
MR | +0.752 |
blu | +0.739 |
Neg logit contributions | |
anders | -1.149 |
ourke | -0.992 |
[+ | -0.971 |
iris | -0.965 |
defences | -0.952 |
Token | U |
Token ID | 471 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
MRI | +2.322 |
MO | +2.226 |
NH | +2.209 |
MR | +2.135 |
NR | +2.090 |
Neg logit contributions | |
anders | -4.749 |
ourke | -4.161 |
[+ | -4.105 |
defences | -4.074 |
onent | -4.069 |
Token | PP |
Token ID | 10246 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
anders | +4.430 |
ourke | +3.952 |
[+ | +3.921 |
onent | +3.829 |
defences | +3.823 |
Neg logit contributions | |
MRI | -2.086 |
NH | -1.908 |
MO | -1.874 |
blu | -1.815 |
MR | -1.794 |
Token | LE |
Token ID | 2538 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
MRI | +0.366 |
NH | +0.342 |
MO | +0.335 |
MR | +0.324 |
PLE | +0.315 |
Neg logit contributions | |
anders | -0.946 |
ourke | -0.844 |
[+ | -0.834 |
defences | -0.828 |
iris | -0.820 |
Token | MENT |
Token ID | 10979 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
MRI | +1.632 |
MO | +1.553 |
NH | +1.551 |
MR | +1.518 |
PLE | +1.473 |
Neg logit contributions | |
anders | -3.085 |
ourke | -2.703 |
[+ | -2.659 |
defences | -2.643 |
onent | -2.641 |
Token | UM |
Token ID | 5883 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
MRI | +1.883 |
NH | +1.792 |
MO | +1.784 |
MR | +1.740 |
PLE | +1.681 |
Neg logit contributions | |
anders | -3.745 |
ourke | -3.299 |
defences | -3.250 |
[+ | -3.239 |
onent | -3.219 |
Token | T |
Token ID | 309 |
Feature activation | -9.26e+00 |
Pos logit contributions | |
MRI | +3.012 |
MO | +2.907 |
NH | +2.882 |
MR | +2.812 |
PLE | +2.751 |
Neg logit contributions | |
anders | -6.154 |
ourke | -5.452 |
defences | -5.293 |
berra | -5.291 |
jriwal | -5.282 |
Token | ER |
Token ID | 13793 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
MRI | +4.283 |
MO | +4.180 |
NH | +4.114 |
MR | +4.091 |
NR | +3.988 |
Neg logit contributions | |
anders | -9.582 |
ourke | -8.326 |
defences | -8.249 |
berra | -8.191 |
jriwal | -8.185 |
Token | TI |
Token ID | 25621 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
MRI | +1.769 |
NH | +1.668 |
MO | +1.635 |
MR | +1.585 |
PLE | +1.557 |
Neg logit contributions | |
anders | -4.305 |
ourke | -3.789 |
[+ | -3.778 |
defences | -3.755 |
iris | -3.729 |
Token | � |
Token ID | 127 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
MRI | +3.050 |
MO | +2.976 |
NH | +2.932 |
MR | +2.875 |
PLE | +2.806 |
Neg logit contributions | |
anders | -6.119 |
ourke | -5.379 |
defences | -5.324 |
berra | -5.280 |
jriwal | -5.251 |
Token | � |
Token ID | 228 |
Feature activation | -5.53e+00 |
Pos logit contributions | |
MRI | +2.403 |
NH | +2.319 |
MO | +2.303 |
MR | +2.266 |
PLE | +2.203 |
Neg logit contributions | |
anders | -3.530 |
ourke | -3.037 |
[+ | -2.975 |
defences | -2.964 |
onent | -2.959 |
Token | P |
Token ID | 350 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
MRI | +2.553 |
NH | +2.469 |
MO | +2.457 |
MR | +2.403 |
PLE | +2.340 |
Neg logit contributions | |
anders | -5.954 |
ourke | -5.225 |
defences | -5.172 |
onent | -5.133 |
berra | -5.124 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
anders | +0.924 |
ourke | +0.812 |
[+ | +0.799 |
onent | +0.785 |
iris | +0.785 |
Neg logit contributions | |
MRI | -0.529 |
NH | -0.499 |
MO | -0.489 |
MR | -0.480 |
PLE | -0.466 |
Token |
|
Token ID | 198 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
MRI | +1.084 |
NH | +1.023 |
MO | +0.989 |
MR | +0.980 |
NR | +0.960 |
Neg logit contributions | |
anders | -2.280 |
ourke | -2.002 |
defences | -1.981 |
iris | -1.969 |
[+ | -1.957 |
Token |
|
Token ID | 198 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
MRI | +0.195 |
NH | +0.182 |
MO | +0.179 |
MR | +0.174 |
PLE | +0.170 |
Neg logit contributions | |
anders | -0.380 |
ourke | -0.336 |
[+ | -0.333 |
defences | -0.328 |
onent | -0.326 |
Token | At |
Token ID | 2953 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
anders | +0.564 |
ourke | +0.495 |
[+ | +0.492 |
defences | +0.485 |
onent | +0.481 |
Neg logit contributions | |
MRI | -0.343 |
NH | -0.324 |
MO | -0.318 |
MR | -0.312 |
PLE | -0.304 |
Token | this |
Token ID | 428 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
MRI | +1.961 |
NH | +1.885 |
MO | +1.858 |
MR | +1.829 |
NR | +1.813 |
Neg logit contributions | |
anders | -3.143 |
ourke | -2.755 |
[+ | -2.700 |
iris | -2.670 |
onent | -2.667 |
Token | pre |
Token ID | 662 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
MRI | +1.709 |
MO | +1.619 |
NH | +1.600 |
MR | +1.565 |
blu | +1.530 |
Neg logit contributions | |
anders | -3.292 |
ourke | -2.901 |
[+ | -2.866 |
onent | -2.833 |
iris | -2.817 |
Token | - |
Token ID | 12 |
Feature activation | -9.37e+00 |
Pos logit contributions | |
MRI | +5.642 |
MO | +5.264 |
NH | +5.117 |
PLE | +5.088 |
MR | +5.053 |
Neg logit contributions | |
anders | -9.697 |
ourke | -8.777 |
[+ | -8.458 |
iris | -8.185 |
る | -8.178 |
Token | trial |
Token ID | 45994 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
MRI | +5.888 |
NH | +5.577 |
MO | +5.511 |
MR | +5.367 |
PLE | +5.286 |
Neg logit contributions | |
anders | -8.195 |
ourke | -7.287 |
[+ | -7.115 |
ategories | -6.976 |
onent | -6.937 |
Token | hearing |
Token ID | 4854 |
Feature activation | -6.22e+00 |
Pos logit contributions | |
MRI | +4.446 |
NH | +4.251 |
MO | +4.237 |
MR | +4.187 |
blu | +4.166 |
Neg logit contributions | |
anders | -4.560 |
ourke | -3.851 |
[+ | -3.630 |
iris | -3.621 |
onent | -3.563 |
Token | on |
Token ID | 319 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
MRI | +3.947 |
NH | +3.848 |
MR | +3.795 |
NR | +3.757 |
MO | +3.711 |
Neg logit contributions | |
anders | -5.460 |
ourke | -4.643 |
iris | -4.516 |
[+ | -4.501 |
onent | -4.460 |
Token | Thursday |
Token ID | 3635 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
MRI | +2.536 |
NH | +2.415 |
MR | +2.365 |
NR | +2.356 |
MO | +2.356 |
Neg logit contributions | |
anders | -4.722 |
ourke | -4.166 |
[+ | -4.077 |
iris | -4.035 |
onent | -4.022 |
Token | ( |
Token ID | 7 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
MRI | +1.903 |
NH | +1.777 |
MO | +1.753 |
MR | +1.696 |
PLE | +1.636 |
Neg logit contributions | |
anders | -3.910 |
ourke | -3.463 |
defences | -3.449 |
[+ | -3.415 |
iris | -3.375 |
Token | 193 |
Token ID | 24943 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
MRI | +1.110 |
NH | +1.067 |
MO | +1.055 |
MR | +1.034 |
NR | +1.008 |
Neg logit contributions | |
anders | -1.267 |
ourke | -1.096 |
defences | -1.070 |
[+ | -1.068 |
onent | -1.051 |
Token | s |
Token ID | 82 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
MRI | +0.708 |
NH | +0.673 |
MO | +0.668 |
MR | +0.654 |
NR | +0.640 |
Neg logit contributions | |
anders | -0.844 |
ourke | -0.731 |
[+ | -0.715 |
defences | -0.706 |
onent | -0.699 |
Token | )} |
Token ID | 38165 |
Feature activation | -9.96e+00 |
Pos logit contributions | |
anders | +0.879 |
ourke | +0.774 |
[+ | +0.769 |
defences | +0.753 |
onent | +0.753 |
Neg logit contributions | |
MRI | -0.473 |
NH | -0.442 |
MO | -0.435 |
MR | -0.424 |
PLE | -0.413 |
Token | 23 |
Token ID | 2242 |
Feature activation | -8.23e+00 |
Pos logit contributions | |
MRI | +3.052 |
NR | +2.924 |
NH | +2.757 |
MO | +2.737 |
blu | +2.702 |
Neg logit contributions | |
anders | -11.494 |
ourke | -10.663 |
defences | -10.339 |
intendent | -10.183 |
jriwal | -10.144 |
Token | . |
Token ID | 13 |
Feature activation | -8.77e+00 |
Pos logit contributions | |
MRI | +3.431 |
MO | +3.266 |
NH | +3.218 |
MR | +3.153 |
NR | +3.112 |
Neg logit contributions | |
anders | -8.980 |
ourke | -8.200 |
defences | -8.069 |
berra | -7.980 |
jriwal | -7.923 |
Token | R |
Token ID | 371 |
Feature activation | -7.12e+00 |
Pos logit contributions | |
NR | +3.876 |
Rx | +3.759 |
MRI | +3.736 |
NH | +3.735 |
blu | +3.712 |
Neg logit contributions | |
anders | -9.204 |
ourke | -8.364 |
ricanes | -7.903 |
iris | -7.888 |
ワン | -7.847 |
Token | f |
Token ID | 69 |
Feature activation | -9.31e+00 |
Pos logit contributions | |
MRI | +4.003 |
NH | +3.946 |
MO | +3.939 |
MR | +3.826 |
NR | +3.619 |
Neg logit contributions | |
anders | -6.524 |
defences | -5.750 |
ourke | -5.705 |
ricanes | -5.524 |
[+ | -5.510 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
MRI | +5.411 |
MO | +5.309 |
NH | +5.261 |
MR | +5.127 |
NR | +4.836 |
Neg logit contributions | |
anders | -8.368 |
defences | -7.235 |
ourke | -7.232 |
raviolet | -7.113 |
ricanes | -7.054 |
Token | { |
Token ID | 1391 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
Rx | +4.469 |
NR | +4.462 |
MRI | +4.441 |
MR | +4.433 |
MO | +4.403 |
Neg logit contributions | |
anders | -11.187 |
ourke | -10.174 |
ricanes | -9.735 |
berra | -9.696 |
iris | -9.662 |
Token | ( |
Token ID | 7 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
MRI | +2.065 |
NH | +1.921 |
MO | +1.901 |
MR | +1.841 |
PLE | +1.767 |
Neg logit contributions | |
anders | -4.316 |
ourke | -3.826 |
defences | -3.813 |
[+ | -3.766 |
iris | -3.726 |