Token | with |
Token ID | 351 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ubs | +0.066 |
ales | +0.062 |
ooth | +0.061 |
gif | +0.058 |
Chains | +0.057 |
Neg logit contributions | |
attent | -0.071 |
Rik | -0.065 |
� | -0.063 |
Crash | -0.063 |
Deng | -0.063 |
Token | # |
Token ID | 1303 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
attent | +0.010 |
Rik | +0.009 |
� | +0.009 |
Crash | +0.009 |
Leader | +0.009 |
Neg logit contributions | |
ubs | -0.008 |
ales | -0.008 |
ooth | -0.007 |
gif | -0.007 |
Chains | -0.007 |
Token | Ask |
Token ID | 25214 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
ubs | +0.025 |
ales | +0.023 |
ooth | +0.023 |
gif | +0.021 |
Chains | +0.021 |
Neg logit contributions | |
attent | -0.029 |
Rik | -0.027 |
� | -0.026 |
Crash | -0.026 |
Deng | -0.026 |
Token | The |
Token ID | 464 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
attent | +0.057 |
Rik | +0.051 |
� | +0.050 |
Crash | +0.050 |
Deng | +0.050 |
Neg logit contributions | |
ubs | -0.050 |
ales | -0.047 |
ooth | -0.046 |
gif | -0.043 |
Chains | -0.043 |
Token | D |
Token ID | 35 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ubs | +0.013 |
ales | +0.013 |
ooth | +0.012 |
gif | +0.012 |
Chains | +0.012 |
Neg logit contributions | |
attent | -0.015 |
Rik | -0.014 |
� | -0.014 |
Crash | -0.014 |
Deng | -0.013 |
Token | ubs |
Token ID | 23161 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
ubs | +0.000 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
Chains | -0.001 |
Neg logit contributions | |
attent | -0.026 |
Rik | -0.025 |
abled | -0.025 |
Crash | -0.025 |
� | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -1.89e-03 |
Pos logit contributions | |
ubs | +0.372 |
ales | +0.349 |
ooth | +0.345 |
gif | +0.324 |
Chains | +0.321 |
Neg logit contributions | |
attent | -0.413 |
Rik | -0.374 |
� | -0.367 |
Crash | -0.366 |
Deng | -0.364 |
Token | then |
Token ID | 788 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
attent | +0.001 |
Rik | +0.001 |
� | +0.001 |
Leader | +0.001 |
Deng | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
uncture | -0.001 |
Token | tune |
Token ID | 14009 |
Feature activation | -5.49e-03 |
Pos logit contributions | |
ubs | +0.041 |
ales | +0.039 |
ooth | +0.038 |
gif | +0.036 |
Chains | +0.036 |
Neg logit contributions | |
attent | -0.046 |
Rik | -0.042 |
� | -0.041 |
Crash | -0.041 |
Leader | -0.041 |
Token | in |
Token ID | 287 |
Feature activation | +7.68e-03 |
Pos logit contributions | |
attent | +0.004 |
Rik | +0.004 |
� | +0.004 |
Crash | +0.004 |
Leader | +0.004 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.003 |
Chains | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -7.53e-03 |
Pos logit contributions | |
ubs | +0.006 |
ales | +0.005 |
ooth | +0.005 |
gif | +0.005 |
Chains | +0.005 |
Neg logit contributions | |
attent | -0.006 |
Rik | -0.005 |
� | -0.005 |
Crash | -0.005 |
Leader | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
attent | +0.035 |
Rik | +0.031 |
� | +0.030 |
Crash | +0.030 |
Deng | +0.030 |
Neg logit contributions | |
ubs | -0.034 |
ales | -0.032 |
ooth | -0.032 |
gif | -0.030 |
Chains | -0.029 |
Token | word |
Token ID | 1573 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
attent | +0.010 |
Rik | +0.010 |
� | +0.009 |
Crash | +0.009 |
Deng | +0.009 |
Neg logit contributions | |
ubs | -0.008 |
ales | -0.007 |
ooth | -0.007 |
gif | -0.006 |
Chains | -0.006 |
Token | � |
Token ID | 564 |
Feature activation | -6.98e-03 |
Pos logit contributions | |
attent | +0.011 |
Rik | +0.010 |
� | +0.010 |
Crash | +0.010 |
Deng | +0.010 |
Neg logit contributions | |
ubs | -0.011 |
ales | -0.011 |
ooth | -0.011 |
gif | -0.010 |
Chains | -0.010 |
Token | � |
Token ID | 250 |
Feature activation | +9.50e-03 |
Pos logit contributions | |
attent | +0.005 |
Rik | +0.004 |
� | +0.004 |
Crash | +0.004 |
Deng | +0.004 |
Neg logit contributions | |
ubs | -0.005 |
ales | -0.005 |
ooth | -0.005 |
gif | -0.005 |
Chains | -0.005 |
Token | C |
Token ID | 34 |
Feature activation | +5.94e-03 |
Pos logit contributions | |
ubs | +0.007 |
ales | +0.006 |
ooth | +0.006 |
gif | +0.006 |
Chains | +0.006 |
Neg logit contributions | |
attent | -0.007 |
Rik | -0.007 |
� | -0.006 |
Crash | -0.006 |
Deng | -0.006 |
Token | ubs |
Token ID | 23161 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.000 |
ooth | +0.000 |
gif | +0.000 |
ale | -0.000 |
Neg logit contributions | |
attent | -0.008 |
Rik | -0.008 |
� | -0.008 |
Crash | -0.008 |
Deng | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | -1.85e-03 |
Pos logit contributions | |
ubs | +0.375 |
ales | +0.352 |
ooth | +0.346 |
gif | +0.326 |
Chains | +0.322 |
Neg logit contributions | |
attent | -0.411 |
Rik | -0.372 |
� | -0.363 |
Crash | -0.362 |
abled | -0.361 |
Token | � |
Token ID | 251 |
Feature activation | -1.75e-03 |
Pos logit contributions | |
attent | +0.001 |
Rik | +0.001 |
� | +0.001 |
Crash | +0.001 |
Deng | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
Chains | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
attent | +0.001 |
Rik | +0.001 |
� | +0.001 |
Crash | +0.001 |
Deng | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
Chains | -0.001 |
Token | come |
Token ID | 1282 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
attent | +0.012 |
Rik | +0.011 |
� | +0.011 |
Crash | +0.011 |
Leader | +0.011 |
Neg logit contributions | |
ubs | -0.011 |
ales | -0.011 |
ooth | -0.011 |
gif | -0.010 |
Chains | -0.010 |
Token | up |
Token ID | 510 |
Feature activation | +2.16e-03 |
Pos logit contributions | |
attent | +0.090 |
Rik | +0.082 |
� | +0.080 |
Crash | +0.080 |
Deng | +0.079 |
Neg logit contributions | |
ubs | -0.083 |
ales | -0.078 |
ooth | -0.077 |
gif | -0.072 |
Chains | -0.072 |
Token | with |
Token ID | 351 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ubs | +0.006 |
ales | +0.005 |
ooth | +0.005 |
gif | +0.005 |
Chains | +0.005 |
Neg logit contributions | |
attent | -0.006 |
Rik | -0.005 |
� | -0.005 |
Crash | -0.005 |
abled | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +3.37e-03 |
Pos logit contributions | |
attent | +0.012 |
Rik | +0.010 |
� | +0.010 |
Crash | +0.010 |
Deng | +0.010 |
Neg logit contributions | |
ubs | -0.011 |
ales | -0.010 |
ooth | -0.010 |
gif | -0.009 |
Chains | -0.009 |
Token | Cly |
Token ID | 29133 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.002 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.003 |
Rik | -0.002 |
� | -0.002 |
Crash | -0.002 |
Deng | -0.002 |
Token | des |
Token ID | 8906 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
ubs | +0.120 |
ales | +0.113 |
ooth | +0.111 |
gif | +0.104 |
Chains | +0.103 |
Neg logit contributions | |
attent | -0.130 |
Rik | -0.118 |
� | -0.115 |
Crash | -0.115 |
Leader | -0.114 |
Token | d |
Token ID | 67 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
ubs | +0.015 |
ales | +0.014 |
ooth | +0.014 |
gif | +0.013 |
Chains | +0.013 |
Neg logit contributions | |
attent | -0.014 |
Rik | -0.013 |
� | -0.012 |
Crash | -0.012 |
Leader | -0.012 |
Token | ales |
Token ID | 2040 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
attent | +0.044 |
Rik | +0.041 |
� | +0.041 |
Crash | +0.041 |
abled | +0.041 |
Neg logit contributions | |
ubs | -0.002 |
ooth | -0.000 |
ales | -0.000 |
gif | +0.001 |
Chains | +0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e-03 |
Pos logit contributions | |
ubs | +0.385 |
ales | +0.363 |
ooth | +0.358 |
gif | +0.339 |
Chains | +0.335 |
Neg logit contributions | |
attent | -0.398 |
Rik | -0.360 |
� | -0.353 |
Crash | -0.352 |
Deng | -0.350 |
Token | He |
Token ID | 679 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.002 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
� | -0.002 |
Crash | -0.002 |
abled | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
attent | +0.047 |
Rik | +0.043 |
� | +0.042 |
Crash | +0.042 |
Leader | +0.042 |
Neg logit contributions | |
ubs | -0.044 |
ales | -0.041 |
ooth | -0.041 |
gif | -0.038 |
Chains | -0.038 |
Token | " |
Token ID | 366 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
ubs | +0.015 |
ales | +0.014 |
ooth | +0.014 |
gif | +0.013 |
Chains | +0.013 |
Neg logit contributions | |
attent | -0.016 |
Rik | -0.015 |
� | -0.015 |
Crash | -0.015 |
Deng | -0.014 |
Token | m |
Token ID | 76 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
attent | +0.021 |
Rik | +0.019 |
� | +0.018 |
Deng | +0.018 |
Crash | +0.018 |
Neg logit contributions | |
ubs | -0.021 |
ales | -0.020 |
ooth | -0.019 |
gif | -0.018 |
ale | -0.018 |
Token | hashtag |
Token ID | 23950 |
Feature activation | -6.62e-03 |
Pos logit contributions | |
attent | +0.007 |
Rik | +0.006 |
� | +0.006 |
Crash | +0.006 |
Deng | +0.006 |
Neg logit contributions | |
ubs | -0.006 |
ales | -0.006 |
ooth | -0.006 |
gif | -0.005 |
Chains | -0.005 |
Token | # |
Token ID | 1303 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
attent | +0.005 |
Rik | +0.005 |
� | +0.004 |
Leader | +0.004 |
Crash | +0.004 |
Neg logit contributions | |
ubs | -0.005 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.004 |
Chains | -0.004 |
Token | Ask |
Token ID | 25214 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
ubs | +0.023 |
ales | +0.021 |
ooth | +0.021 |
gif | +0.020 |
Chains | +0.020 |
Neg logit contributions | |
attent | -0.025 |
Rik | -0.023 |
� | -0.022 |
Crash | -0.022 |
Deng | -0.022 |
Token | The |
Token ID | 464 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
attent | +0.063 |
Rik | +0.057 |
� | +0.056 |
Crash | +0.056 |
Deng | +0.055 |
Neg logit contributions | |
ubs | -0.064 |
ales | -0.060 |
ooth | -0.059 |
gif | -0.056 |
Chains | -0.056 |
Token | D |
Token ID | 35 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
ubs | +0.018 |
ales | +0.017 |
ooth | +0.016 |
gif | +0.016 |
Chains | +0.015 |
Neg logit contributions | |
attent | -0.017 |
Rik | -0.015 |
� | -0.015 |
Crash | -0.015 |
Leader | -0.015 |
Token | ubs |
Token ID | 23161 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
ubs | +0.009 |
ales | +0.009 |
ooth | +0.009 |
gif | +0.008 |
Chains | +0.008 |
Neg logit contributions | |
attent | -0.009 |
Rik | -0.009 |
� | -0.008 |
Crash | -0.008 |
Deng | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -9.55e-03 |
Pos logit contributions | |
ubs | +0.388 |
ales | +0.366 |
ooth | +0.362 |
gif | +0.341 |
Chains | +0.338 |
Neg logit contributions | |
attent | -0.394 |
Rik | -0.355 |
� | -0.349 |
Crash | -0.348 |
Leader | -0.346 |
Token | and |
Token ID | 290 |
Feature activation | +1.12e-03 |
Pos logit contributions | |
attent | +0.007 |
Rik | +0.007 |
� | +0.006 |
Leader | +0.006 |
Deng | +0.006 |
Neg logit contributions | |
ubs | -0.007 |
ales | -0.006 |
ooth | -0.006 |
gif | -0.006 |
Chains | -0.006 |
Token | be |
Token ID | 307 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
uncture | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
Leader | -0.001 |
� | -0.001 |
Deng | -0.001 |
Token | on |
Token ID | 319 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
ubs | +0.018 |
ales | +0.017 |
ooth | +0.017 |
gif | +0.016 |
Chains | +0.015 |
Neg logit contributions | |
attent | -0.017 |
Rik | -0.015 |
� | -0.015 |
Leader | -0.015 |
Crash | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ubs | +0.016 |
ales | +0.015 |
ooth | +0.015 |
gif | +0.014 |
Chains | +0.014 |
Neg logit contributions | |
attent | -0.016 |
Rik | -0.015 |
� | -0.014 |
Crash | -0.014 |
Deng | -0.014 |
Token | we |
Token ID | 732 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
ubs | +0.028 |
ales | +0.026 |
ooth | +0.026 |
gif | +0.024 |
Chains | +0.024 |
Neg logit contributions | |
attent | -0.039 |
Rik | -0.036 |
� | -0.035 |
Crash | -0.035 |
abled | -0.035 |
Token | iser |
Token ID | 5847 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
ubs | +0.061 |
ales | +0.058 |
ooth | +0.057 |
gif | +0.054 |
Chains | +0.054 |
Neg logit contributions | |
attent | -0.059 |
Rik | -0.053 |
� | -0.052 |
Crash | -0.052 |
Leader | -0.051 |
Token | Cly |
Token ID | 29133 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
attent | +0.010 |
Rik | +0.009 |
� | +0.009 |
Crash | +0.009 |
Deng | +0.009 |
Neg logit contributions | |
ubs | -0.007 |
ales | -0.007 |
ooth | -0.007 |
gif | -0.006 |
Chains | -0.006 |
Token | des |
Token ID | 8906 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
ubs | +0.121 |
ales | +0.114 |
ooth | +0.112 |
gif | +0.106 |
Chains | +0.105 |
Neg logit contributions | |
attent | -0.129 |
Rik | -0.117 |
� | -0.114 |
Crash | -0.114 |
Deng | -0.113 |
Token | d |
Token ID | 67 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
ubs | +0.012 |
ales | +0.012 |
ooth | +0.011 |
gif | +0.011 |
Chains | +0.011 |
Neg logit contributions | |
attent | -0.012 |
Rik | -0.011 |
� | -0.010 |
Crash | -0.010 |
Leader | -0.010 |
Token | ales |
Token ID | 2040 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
attent | +0.039 |
Rik | +0.036 |
abled | +0.036 |
� | +0.036 |
Leader | +0.036 |
Neg logit contributions | |
ubs | -0.002 |
ooth | -0.000 |
ales | -0.000 |
gif | +0.000 |
Chains | +0.001 |
Token | paid |
Token ID | 3432 |
Feature activation | +6.82e-02 |
Pos logit contributions | |
ubs | +0.369 |
ales | +0.347 |
ooth | +0.342 |
gif | +0.322 |
Chains | +0.319 |
Neg logit contributions | |
attent | -0.408 |
Rik | -0.370 |
� | -0.363 |
Crash | -0.362 |
Deng | -0.360 |
Token | a |
Token ID | 257 |
Feature activation | +4.55e-03 |
Pos logit contributions | |
ubs | +0.047 |
ales | +0.044 |
ooth | +0.043 |
gif | +0.041 |
Chains | +0.040 |
Neg logit contributions | |
attent | -0.054 |
Rik | -0.049 |
� | -0.048 |
Crash | -0.048 |
Deng | -0.048 |
Token | visit |
Token ID | 3187 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
ubs | +0.003 |
ales | +0.003 |
ooth | +0.003 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.003 |
Rik | -0.003 |
� | -0.003 |
Crash | -0.003 |
Deng | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.09e-03 |
Pos logit contributions | |
attent | +0.032 |
Rik | +0.029 |
� | +0.029 |
Crash | +0.029 |
Deng | +0.028 |
Neg logit contributions | |
ubs | -0.031 |
ales | -0.029 |
ooth | -0.029 |
gif | -0.027 |
Chains | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +7.04e-03 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.002 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
� | -0.002 |
Crash | -0.002 |
Deng | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -2.34e-04 |
Pos logit contributions | |
attent | +0.040 |
Rik | +0.036 |
� | +0.035 |
Crash | +0.035 |
Deng | +0.035 |
Neg logit contributions | |
ubs | -0.039 |
ales | -0.037 |
ooth | -0.036 |
gif | -0.034 |
Chains | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -4.07e-03 |
Pos logit contributions | |
attent | +0.000 |
Rik | +0.000 |
� | +0.000 |
Crash | +0.000 |
abled | +0.000 |
Neg logit contributions | |
ubs | -0.000 |
ales | -0.000 |
ooth | -0.000 |
gif | -0.000 |
Chains | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -4.57e-03 |
Pos logit contributions | |
attent | +0.003 |
Rik | +0.003 |
� | +0.003 |
Crash | +0.003 |
Deng | +0.003 |
Neg logit contributions | |
ubs | -0.003 |
ales | -0.003 |
ooth | -0.003 |
gif | -0.003 |
Chains | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
attent | +0.003 |
Rik | +0.003 |
Deng | +0.003 |
� | +0.003 |
Leader | +0.003 |
Neg logit contributions | |
ubs | -0.003 |
ales | -0.003 |
ooth | -0.003 |
gif | -0.003 |
ale | -0.003 |
Token | Be |
Token ID | 1355 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
ubs | +0.015 |
ales | +0.014 |
ooth | +0.014 |
gif | +0.013 |
Chains | +0.013 |
Neg logit contributions | |
attent | -0.015 |
Rik | -0.013 |
� | -0.013 |
Crash | -0.013 |
Deng | -0.013 |
Token | ales |
Token ID | 2040 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
ubs | +0.023 |
ales | +0.019 |
ooth | +0.018 |
gif | +0.014 |
ale | +0.014 |
Neg logit contributions | |
attent | -0.125 |
Rik | -0.117 |
� | -0.116 |
Crash | -0.116 |
Deng | -0.115 |
Token | bought |
Token ID | 5839 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ubs | +0.372 |
ales | +0.351 |
ooth | +0.344 |
gif | +0.324 |
ale | +0.321 |
Neg logit contributions | |
attent | -0.402 |
Rik | -0.364 |
� | -0.358 |
Crash | -0.358 |
Deng | -0.355 |
Token | a |
Token ID | 257 |
Feature activation | +5.90e-03 |
Pos logit contributions | |
attent | +0.144 |
Rik | +0.130 |
� | +0.127 |
Crash | +0.127 |
Deng | +0.126 |
Neg logit contributions | |
ubs | -0.142 |
ales | -0.133 |
ooth | -0.132 |
gif | -0.124 |
Chains | -0.123 |
Token | nearly |
Token ID | 3016 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
ubs | +0.005 |
ales | +0.004 |
ooth | +0.004 |
gif | +0.004 |
Chains | +0.004 |
Neg logit contributions | |
attent | -0.004 |
Rik | -0.004 |
� | -0.004 |
Crash | -0.004 |
Deng | -0.004 |
Token | 200 |
Token ID | 939 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
attent | +0.039 |
Rik | +0.035 |
� | +0.034 |
Crash | +0.034 |
Deng | +0.034 |
Neg logit contributions | |
ubs | -0.038 |
ales | -0.036 |
ooth | -0.036 |
gif | -0.034 |
Chains | -0.033 |
Token | - |
Token ID | 12 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
attent | +0.079 |
Rik | +0.071 |
� | +0.070 |
Crash | +0.070 |
Deng | +0.069 |
Neg logit contributions | |
ubs | -0.078 |
ales | -0.073 |
ooth | -0.072 |
gif | -0.068 |
Chains | -0.068 |
Token | we |
Token ID | 732 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
ubs | +0.008 |
ales | +0.008 |
ooth | +0.008 |
gif | +0.007 |
Chains | +0.007 |
Neg logit contributions | |
attent | -0.009 |
Rik | -0.009 |
� | -0.008 |
Crash | -0.008 |
Deng | -0.008 |
Token | iser |
Token ID | 5847 |
Feature activation | -1.87e-03 |
Pos logit contributions | |
ubs | +0.057 |
ales | +0.054 |
ooth | +0.053 |
gif | +0.050 |
Chains | +0.050 |
Neg logit contributions | |
attent | -0.057 |
Rik | -0.052 |
� | -0.051 |
Crash | -0.050 |
Deng | -0.050 |
Token | Cly |
Token ID | 29133 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
attent | +0.001 |
Rik | +0.001 |
� | +0.001 |
Crash | +0.001 |
Deng | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
Chains | -0.001 |
Token | des |
Token ID | 8906 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
ubs | +0.124 |
ales | +0.117 |
ooth | +0.116 |
gif | +0.110 |
Chains | +0.108 |
Neg logit contributions | |
attent | -0.122 |
Rik | -0.110 |
abled | -0.107 |
Crash | -0.107 |
� | -0.107 |
Token | d |
Token ID | 67 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
ubs | +0.017 |
ales | +0.016 |
ooth | +0.016 |
gif | +0.015 |
Chains | +0.015 |
Neg logit contributions | |
attent | -0.014 |
Rik | -0.012 |
� | -0.012 |
Crash | -0.012 |
Deng | -0.012 |
Token | ales |
Token ID | 2040 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
attent | +0.034 |
Rik | +0.033 |
Leader | +0.033 |
Deng | +0.033 |
abled | +0.032 |
Neg logit contributions | |
ubs | -0.002 |
ooth | -0.001 |
uncture | -0.001 |
ammy | -0.001 |
gif | -0.000 |
Token | make |
Token ID | 787 |
Feature activation | +9.23e-02 |
Pos logit contributions | |
ubs | +0.371 |
ales | +0.349 |
ooth | +0.343 |
gif | +0.325 |
Chains | +0.322 |
Neg logit contributions | |
attent | -0.401 |
Rik | -0.362 |
� | -0.356 |
Crash | -0.355 |
Deng | -0.353 |
Token | deliveries |
Token ID | 31167 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
ubs | +0.066 |
ales | +0.062 |
ooth | +0.061 |
gif | +0.058 |
Chains | +0.057 |
Neg logit contributions | |
attent | -0.071 |
Rik | -0.064 |
� | -0.063 |
Crash | -0.062 |
Deng | -0.062 |
Token | in |
Token ID | 287 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
ubs | +0.038 |
ales | +0.036 |
ooth | +0.035 |
gif | +0.033 |
Chains | +0.033 |
Neg logit contributions | |
attent | -0.040 |
Rik | -0.037 |
� | -0.036 |
Crash | -0.036 |
Deng | -0.035 |
Token | Arlington |
Token ID | 30379 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
ubs | +0.015 |
ales | +0.014 |
ooth | +0.014 |
gif | +0.014 |
Chains | +0.013 |
Neg logit contributions | |
attent | -0.016 |
Rik | -0.015 |
� | -0.014 |
Crash | -0.014 |
Deng | -0.014 |
Token | Heights |
Token ID | 20365 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
attent | +0.036 |
Rik | +0.032 |
� | +0.032 |
Crash | +0.032 |
Leader | +0.032 |
Neg logit contributions | |
ubs | -0.035 |
ales | -0.033 |
ooth | -0.033 |
gif | -0.031 |
Chains | -0.031 |
Token | bad |
Token ID | 2089 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ubs | +0.006 |
ales | +0.005 |
ooth | +0.005 |
gif | +0.005 |
Chains | +0.005 |
Neg logit contributions | |
attent | -0.006 |
Rik | -0.005 |
� | -0.005 |
Crash | -0.005 |
Leader | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +4.33e-03 |
Pos logit contributions | |
ubs | +0.079 |
ales | +0.075 |
ooth | +0.074 |
gif | +0.069 |
Chains | +0.069 |
Neg logit contributions | |
attent | -0.081 |
Rik | -0.073 |
� | -0.071 |
Crash | -0.071 |
Leader | -0.071 |
Token | but |
Token ID | 475 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
ubs | +0.003 |
ales | +0.003 |
ooth | +0.003 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.003 |
Rik | -0.003 |
� | -0.003 |
Crash | -0.003 |
Deng | -0.003 |
Token | he |
Token ID | 339 |
Feature activation | -2.92e-04 |
Pos logit contributions | |
attent | +0.029 |
Rik | +0.026 |
� | +0.025 |
Crash | +0.025 |
Deng | +0.025 |
Neg logit contributions | |
ubs | -0.028 |
ales | -0.026 |
ooth | -0.026 |
gif | -0.024 |
Chains | -0.024 |
Token | p |
Token ID | 279 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
attent | +0.000 |
Rik | +0.000 |
� | +0.000 |
Crash | +0.000 |
Deng | +0.000 |
Neg logit contributions | |
ubs | -0.000 |
ales | -0.000 |
ooth | -0.000 |
gif | -0.000 |
Chains | -0.000 |
Token | ales |
Token ID | 2040 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
attent | +0.107 |
Rik | +0.096 |
� | +0.094 |
Crash | +0.093 |
abled | +0.093 |
Neg logit contributions | |
ubs | -0.116 |
ales | -0.109 |
ooth | -0.108 |
gif | -0.103 |
Chains | -0.102 |
Token | in |
Token ID | 287 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
ubs | +0.355 |
ales | +0.331 |
ooth | +0.325 |
gif | +0.311 |
ale | +0.302 |
Neg logit contributions | |
attent | -0.414 |
Rik | -0.375 |
� | -0.369 |
Crash | -0.368 |
abled | -0.367 |
Token | com |
Token ID | 401 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ubs | +0.012 |
ales | +0.011 |
ooth | +0.011 |
gif | +0.011 |
Chains | +0.010 |
Neg logit contributions | |
attent | -0.012 |
Rik | -0.011 |
Crash | -0.011 |
� | -0.010 |
abled | -0.010 |
Token | |
Token ID | 3907 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
attent | +0.090 |
Rik | +0.081 |
� | +0.080 |
Crash | +0.080 |
Deng | +0.079 |
Neg logit contributions | |
ubs | -0.094 |
ales | -0.089 |
ooth | -0.088 |
gif | -0.084 |
ale | -0.082 |
Token | par |
Token ID | 1845 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
attent | +0.013 |
Rik | +0.011 |
� | +0.011 |
Crash | +0.011 |
abled | +0.011 |
Neg logit contributions | |
ubs | -0.013 |
ales | -0.012 |
ooth | -0.012 |
gif | -0.011 |
Chains | -0.011 |
Token | |
Token ID | 3907 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
attent | +0.056 |
Rik | +0.050 |
� | +0.049 |
Crash | +0.049 |
Deng | +0.048 |
Neg logit contributions | |
ubs | -0.060 |
ales | -0.056 |
ooth | -0.056 |
gif | -0.053 |
Chains | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
attent | +0.003 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
abled | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.002 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
� | -0.002 |
Crash | -0.002 |
Deng | -0.002 |
Token | Cly |
Token ID | 29133 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ubs | +0.019 |
ales | +0.018 |
ooth | +0.017 |
gif | +0.016 |
Chains | +0.016 |
Neg logit contributions | |
attent | -0.024 |
Rik | -0.022 |
� | -0.021 |
Crash | -0.021 |
Deng | -0.021 |
Token | des |
Token ID | 8906 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ubs | +0.117 |
ales | +0.110 |
ooth | +0.108 |
gif | +0.102 |
Chains | +0.101 |
Neg logit contributions | |
attent | -0.126 |
Rik | -0.114 |
� | -0.112 |
Crash | -0.111 |
Leader | -0.110 |
Token | d |
Token ID | 67 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
ubs | +0.009 |
ales | +0.009 |
ooth | +0.008 |
gif | +0.008 |
Chains | +0.008 |
Neg logit contributions | |
attent | -0.009 |
Rik | -0.008 |
� | -0.008 |
Crash | -0.007 |
Leader | -0.007 |
Token | ales |
Token ID | 2040 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
attent | +0.059 |
Rik | +0.056 |
abled | +0.055 |
� | +0.055 |
Crash | +0.055 |
Neg logit contributions | |
ubs | -0.002 |
ooth | -0.000 |
ales | -0.000 |
gif | +0.001 |
Chains | +0.002 |
Token | , |
Token ID | 11 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
ubs | +0.366 |
ales | +0.345 |
ooth | +0.339 |
gif | +0.320 |
Chains | +0.317 |
Neg logit contributions | |
attent | -0.401 |
Rik | -0.364 |
� | -0.357 |
Crash | -0.356 |
Deng | -0.354 |
Token | which |
Token ID | 543 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
attent | +0.001 |
Rik | +0.001 |
� | +0.001 |
Crash | +0.001 |
abled | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
Chains | -0.001 |
Token | will |
Token ID | 481 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
ubs | +0.012 |
ales | +0.011 |
ooth | +0.011 |
gif | +0.010 |
Chains | +0.010 |
Neg logit contributions | |
attent | -0.012 |
Rik | -0.011 |
� | -0.011 |
Crash | -0.011 |
abled | -0.011 |
Token | visit |
Token ID | 3187 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
ubs | +0.040 |
ales | +0.038 |
ooth | +0.037 |
gif | +0.035 |
Chains | +0.035 |
Neg logit contributions | |
attent | -0.046 |
Rik | -0.041 |
� | -0.041 |
Crash | -0.041 |
Deng | -0.040 |
Token | Antioch |
Token ID | 46590 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
attent | +0.036 |
Rik | +0.033 |
� | +0.032 |
Crash | +0.032 |
Deng | +0.032 |
Neg logit contributions | |
ubs | -0.037 |
ales | -0.035 |
ooth | -0.035 |
gif | -0.033 |
Chains | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -6.62e-03 |
Pos logit contributions | |
attent | +0.077 |
Rik | +0.069 |
� | +0.068 |
Crash | +0.068 |
Deng | +0.067 |
Neg logit contributions | |
ubs | -0.072 |
ales | -0.067 |
ooth | -0.067 |
gif | -0.063 |
Chains | -0.062 |
Token | 13 |
Token ID | 1511 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
attent | +0.005 |
Rik | +0.004 |
� | +0.004 |
Crash | +0.004 |
abled | +0.004 |
Neg logit contributions | |
ubs | -0.005 |
ales | -0.005 |
ooth | -0.005 |
gif | -0.005 |
Chains | -0.005 |
Token | th |
Token ID | 400 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
attent | +0.032 |
Rik | +0.029 |
� | +0.028 |
Crash | +0.028 |
Leader | +0.028 |
Neg logit contributions | |
ubs | -0.031 |
ales | -0.029 |
ooth | -0.029 |
gif | -0.027 |
Chains | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +8.20e-03 |
Pos logit contributions | |
ubs | +0.017 |
ales | +0.016 |
ooth | +0.016 |
gif | +0.015 |
Chains | +0.015 |
Neg logit contributions | |
attent | -0.018 |
Rik | -0.016 |
� | -0.016 |
Crash | -0.016 |
Deng | -0.016 |
Token | Texas |
Token ID | 3936 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ubs | +0.006 |
ales | +0.006 |
ooth | +0.006 |
gif | +0.006 |
Chains | +0.006 |
Neg logit contributions | |
attent | -0.006 |
Rik | -0.005 |
� | -0.005 |
Crash | -0.005 |
Deng | -0.005 |
Token | Chains |
Token ID | 34950 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
ubs | +0.023 |
ales | +0.016 |
ooth | +0.016 |
gif | +0.010 |
uncture | +0.009 |
Neg logit contributions | |
attent | -0.188 |
Rik | -0.178 |
Crash | -0.176 |
Leader | -0.176 |
� | -0.176 |
Token | aw |
Token ID | 707 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ubs | +0.300 |
ooth | +0.279 |
ales | +0.278 |
uncture | +0.256 |
gif | +0.254 |
Neg logit contributions | |
attent | -0.457 |
Rik | -0.423 |
Leader | -0.417 |
abled | -0.415 |
Deng | -0.414 |
Token | Massacre |
Token ID | 40602 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
ubs | +0.144 |
ales | +0.135 |
ooth | +0.134 |
gif | +0.128 |
uncture | +0.127 |
Neg logit contributions | |
attent | -0.100 |
Rik | -0.088 |
Crash | -0.086 |
Leader | -0.086 |
� | -0.085 |
Token | have |
Token ID | 423 |
Feature activation | -8.74e-04 |
Pos logit contributions | |
attent | +0.049 |
Rik | +0.045 |
� | +0.044 |
Crash | +0.044 |
Leader | +0.043 |
Neg logit contributions | |
ubs | -0.047 |
ales | -0.045 |
ooth | -0.044 |
gif | -0.041 |
Chains | -0.041 |
Token | been |
Token ID | 587 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
attent | +0.001 |
Rik | +0.001 |
� | +0.001 |
Crash | +0.001 |
Deng | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
Chains | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +5.56e-04 |
Pos logit contributions | |
ubs | +0.020 |
ales | +0.019 |
ooth | +0.019 |
gif | +0.017 |
Chains | +0.017 |
Neg logit contributions | |
attent | -0.022 |
Rik | -0.020 |
� | -0.019 |
Crash | -0.019 |
Leader | -0.019 |
Token | artists |
Token ID | 7912 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
ubs | +0.027 |
ales | +0.025 |
ooth | +0.025 |
gif | +0.024 |
Chains | +0.024 |
Neg logit contributions | |
attent | -0.027 |
Rik | -0.024 |
� | -0.024 |
Crash | -0.023 |
Deng | -0.023 |
Token | Veronica |
Token ID | 44498 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
attent | +0.035 |
Rik | +0.031 |
� | +0.031 |
Crash | +0.031 |
abled | +0.031 |
Neg logit contributions | |
ubs | -0.034 |
ales | -0.032 |
ooth | -0.031 |
gif | -0.030 |
Chains | -0.029 |
Token | de |
Token ID | 390 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ubs | +0.029 |
ales | +0.028 |
ooth | +0.027 |
gif | +0.026 |
Chains | +0.026 |
Neg logit contributions | |
attent | -0.030 |
Rik | -0.027 |
� | -0.026 |
Crash | -0.026 |
abled | -0.026 |
Token | N |
Token ID | 399 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
attent | +0.116 |
Rik | +0.105 |
� | +0.102 |
Crash | +0.102 |
Deng | +0.101 |
Neg logit contributions | |
ubs | -0.125 |
ales | -0.117 |
ooth | -0.116 |
gif | -0.110 |
Chains | -0.109 |
Token | og |
Token ID | 519 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
attent | +0.057 |
Rik | +0.051 |
� | +0.050 |
Crash | +0.050 |
abled | +0.049 |
Neg logit contributions | |
ubs | -0.057 |
ales | -0.054 |
ooth | -0.053 |
gif | -0.050 |
Chains | -0.050 |
Token | ales |
Token ID | 2040 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
attent | +0.084 |
Rik | +0.077 |
� | +0.075 |
Crash | +0.075 |
Deng | +0.075 |
Neg logit contributions | |
ubs | -0.067 |
ales | -0.062 |
ooth | -0.062 |
gif | -0.058 |
Chains | -0.058 |
Token | Lep |
Token ID | 42957 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
ubs | +0.363 |
ales | +0.342 |
ooth | +0.336 |
gif | +0.318 |
Chains | +0.314 |
Neg logit contributions | |
attent | -0.402 |
Rik | -0.363 |
� | -0.356 |
Crash | -0.356 |
abled | -0.353 |
Token | re |
Token ID | 260 |
Feature activation | -6.08e-03 |
Pos logit contributions | |
attent | +0.016 |
Rik | +0.015 |
� | +0.014 |
Crash | +0.014 |
abled | +0.014 |
Neg logit contributions | |
ubs | -0.015 |
ales | -0.014 |
ooth | -0.014 |
gif | -0.013 |
Chains | -0.013 |
Token | - |
Token ID | 12 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
attent | +0.005 |
Rik | +0.005 |
� | +0.004 |
Crash | +0.004 |
Deng | +0.004 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.004 |
Chains | -0.003 |
Token | v |
Token ID | 85 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
attent | +0.015 |
Rik | +0.013 |
� | +0.013 |
Crash | +0.013 |
Deng | +0.013 |
Neg logit contributions | |
ubs | -0.014 |
ales | -0.013 |
ooth | -0.013 |
gif | -0.012 |
Chains | -0.012 |
Token | ost |
Token ID | 455 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
attent | +0.170 |
Rik | +0.154 |
� | +0.150 |
Crash | +0.150 |
abled | +0.150 |
Neg logit contributions | |
ubs | -0.151 |
ales | -0.140 |
ooth | -0.139 |
gif | -0.132 |
Chains | -0.130 |
Token | mine |
Token ID | 6164 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ubs | +0.006 |
ales | +0.006 |
ooth | +0.005 |
gif | +0.005 |
Chains | +0.005 |
Neg logit contributions | |
attent | -0.008 |
Rik | -0.007 |
� | -0.007 |
Crash | -0.007 |
Deng | -0.007 |
Token | put |
Token ID | 1234 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ubs | +0.170 |
ales | +0.160 |
ooth | +0.157 |
gif | +0.149 |
Chains | +0.147 |
Neg logit contributions | |
attent | -0.177 |
Rik | -0.160 |
� | -0.157 |
Crash | -0.157 |
abled | -0.155 |
Token | it |
Token ID | 340 |
Feature activation | -5.63e-03 |
Pos logit contributions | |
attent | +0.087 |
Rik | +0.078 |
� | +0.076 |
Deng | +0.076 |
Crash | +0.076 |
Neg logit contributions | |
ubs | -0.093 |
ales | -0.088 |
ooth | -0.087 |
gif | -0.082 |
Chains | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | +7.98e-03 |
Pos logit contributions | |
attent | +0.004 |
Rik | +0.004 |
� | +0.004 |
Crash | +0.004 |
Deng | +0.004 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.003 |
Chains | -0.003 |
Token | Be |
Token ID | 1355 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ubs | +0.006 |
ales | +0.006 |
ooth | +0.006 |
gif | +0.005 |
Chains | +0.005 |
Neg logit contributions | |
attent | -0.006 |
Rik | -0.005 |
� | -0.005 |
Crash | -0.005 |
Deng | -0.005 |
Token | ale |
Token ID | 1000 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
ubs | +0.080 |
ales | +0.075 |
ooth | +0.074 |
gif | +0.070 |
Chains | +0.069 |
Neg logit contributions | |
attent | -0.086 |
Rik | -0.077 |
� | -0.076 |
Crash | -0.076 |
Deng | -0.075 |
Token | has |
Token ID | 468 |
Feature activation | +2.57e-03 |
Pos logit contributions | |
ubs | +0.361 |
ales | +0.339 |
ooth | +0.335 |
gif | +0.315 |
Chains | +0.312 |
Neg logit contributions | |
attent | -0.400 |
Rik | -0.361 |
Crash | -0.354 |
� | -0.354 |
abled | -0.352 |
Token | been |
Token ID | 587 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.002 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
� | -0.002 |
Crash | -0.002 |
Deng | -0.002 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
ubs | +0.028 |
ales | +0.027 |
ooth | +0.026 |
gif | +0.025 |
Chains | +0.024 |
Neg logit contributions | |
attent | -0.029 |
Rik | -0.026 |
� | -0.026 |
Crash | -0.026 |
Deng | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +9.33e-03 |
Pos logit contributions | |
ubs | +0.010 |
ales | +0.009 |
ooth | +0.009 |
gif | +0.009 |
Chains | +0.008 |
Neg logit contributions | |
attent | -0.010 |
Rik | -0.009 |
� | -0.009 |
Crash | -0.009 |
Deng | -0.009 |
Token | attention |
Token ID | 3241 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ubs | +0.007 |
ales | +0.006 |
ooth | +0.006 |
gif | +0.006 |
Chains | +0.006 |
Neg logit contributions | |
attent | -0.007 |
Rik | -0.006 |
� | -0.006 |
Crash | -0.006 |
Deng | -0.006 |
Token | plays |
Token ID | 5341 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
ubs | +0.095 |
ales | +0.090 |
ooth | +0.089 |
gif | +0.082 |
Chains | +0.082 |
Neg logit contributions | |
attent | -0.104 |
Rik | -0.094 |
Deng | -0.091 |
� | -0.091 |
Crash | -0.091 |
Token | that |
Token ID | 326 |
Feature activation | -3.27e-03 |
Pos logit contributions | |
ubs | +0.050 |
ales | +0.047 |
ooth | +0.046 |
gif | +0.044 |
Chains | +0.043 |
Neg logit contributions | |
attent | -0.054 |
Rik | -0.049 |
� | -0.048 |
Crash | -0.048 |
Deng | -0.047 |
Token | would |
Token ID | 561 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
attent | +0.003 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
Deng | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | make |
Token ID | 787 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
attent | +0.050 |
Rik | +0.046 |
� | +0.045 |
Crash | +0.045 |
Deng | +0.044 |
Neg logit contributions | |
ubs | -0.044 |
ales | -0.042 |
ooth | -0.041 |
gif | -0.039 |
Chains | -0.038 |
Token | good |
Token ID | 922 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ubs | +0.058 |
ales | +0.055 |
ooth | +0.054 |
gif | +0.051 |
Chains | +0.050 |
Neg logit contributions | |
attent | -0.063 |
Rik | -0.057 |
� | -0.056 |
Crash | -0.056 |
Deng | -0.055 |
Token | gif |
Token ID | 9381 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
ubs | +0.074 |
ales | +0.070 |
ooth | +0.069 |
gif | +0.064 |
Chains | +0.064 |
Neg logit contributions | |
attent | -0.087 |
Rik | -0.079 |
� | -0.077 |
Crash | -0.077 |
Deng | -0.076 |
Token | s |
Token ID | 82 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
ubs | +0.380 |
ales | +0.358 |
ooth | +0.355 |
gif | +0.332 |
Chains | +0.331 |
Neg logit contributions | |
attent | -0.380 |
Rik | -0.341 |
� | -0.334 |
Crash | -0.332 |
Deng | -0.331 |
Token | , |
Token ID | 11 |
Feature activation | +3.26e-04 |
Pos logit contributions | |
attent | +0.013 |
Rik | +0.012 |
� | +0.011 |
Crash | +0.011 |
Deng | +0.011 |
Neg logit contributions | |
ubs | -0.012 |
ales | -0.011 |
ooth | -0.011 |
gif | -0.011 |
Chains | -0.011 |
Token | with |
Token ID | 351 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
ubs | +0.000 |
ales | +0.000 |
ooth | +0.000 |
gif | +0.000 |
Chains | +0.000 |
Neg logit contributions | |
attent | -0.000 |
Rik | -0.000 |
� | -0.000 |
Crash | -0.000 |
Deng | -0.000 |
Token | B |
Token ID | 347 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
attent | +0.009 |
Rik | +0.009 |
� | +0.008 |
Deng | +0.008 |
Crash | +0.008 |
Neg logit contributions | |
ubs | -0.008 |
ales | -0.008 |
ooth | -0.008 |
gif | -0.007 |
Chains | -0.007 |
Token | ugg |
Token ID | 6837 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
ubs | +0.103 |
ales | +0.096 |
ooth | +0.095 |
gif | +0.089 |
Chains | +0.089 |
Neg logit contributions | |
attent | -0.137 |
Rik | -0.125 |
� | -0.123 |
Crash | -0.123 |
abled | -0.122 |
Token | ago |
Token ID | 2084 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
attent | +0.071 |
Rik | +0.064 |
� | +0.063 |
Crash | +0.063 |
Deng | +0.063 |
Neg logit contributions | |
ubs | -0.060 |
ales | -0.056 |
ooth | -0.055 |
gif | -0.052 |
Chains | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
ubs | +0.117 |
ales | +0.110 |
ooth | +0.108 |
gif | +0.103 |
Chains | +0.101 |
Neg logit contributions | |
attent | -0.122 |
Rik | -0.110 |
� | -0.108 |
Crash | -0.107 |
Deng | -0.107 |
Token | Bin |
Token ID | 20828 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ubs | +0.008 |
ales | +0.008 |
ooth | +0.008 |
gif | +0.007 |
Chains | +0.007 |
Neg logit contributions | |
attent | -0.008 |
Rik | -0.007 |
� | -0.007 |
Crash | -0.007 |
abled | -0.007 |
Token | ney |
Token ID | 1681 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
attent | +0.070 |
Rik | +0.063 |
� | +0.062 |
Crash | +0.061 |
abled | +0.061 |
Neg logit contributions | |
ubs | -0.083 |
ales | -0.079 |
ooth | -0.078 |
gif | -0.074 |
Chains | -0.073 |
Token | Be |
Token ID | 1355 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
attent | +0.048 |
Rik | +0.043 |
� | +0.042 |
Crash | +0.042 |
abled | +0.042 |
Neg logit contributions | |
ubs | -0.046 |
ales | -0.043 |
ooth | -0.043 |
gif | -0.040 |
Chains | -0.040 |
Token | ale |
Token ID | 1000 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
ubs | +0.017 |
ales | +0.013 |
ooth | +0.012 |
gif | +0.008 |
Chains | +0.008 |
Neg logit contributions | |
attent | -0.130 |
Rik | -0.123 |
� | -0.121 |
Crash | -0.121 |
Deng | -0.121 |
Token | , |
Token ID | 11 |
Feature activation | +4.91e-03 |
Pos logit contributions | |
ubs | +0.375 |
ales | +0.359 |
ooth | +0.349 |
gif | +0.333 |
ale | +0.330 |
Neg logit contributions | |
attent | -0.378 |
Rik | -0.340 |
� | -0.337 |
Crash | -0.336 |
abled | -0.333 |
Token | Sandy |
Token ID | 17581 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
ubs | +0.004 |
ales | +0.003 |
ooth | +0.003 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.004 |
Rik | -0.003 |
� | -0.003 |
Crash | -0.003 |
abled | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
attent | +0.083 |
Rik | +0.076 |
� | +0.074 |
Crash | +0.074 |
Leader | +0.074 |
Neg logit contributions | |
ubs | -0.065 |
ales | -0.061 |
ooth | -0.060 |
gif | -0.056 |
Chains | -0.055 |
Token | husband |
Token ID | 5229 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ubs | +0.039 |
ales | +0.036 |
ooth | +0.036 |
gif | +0.033 |
Chains | +0.033 |
Neg logit contributions | |
attent | -0.053 |
Rik | -0.048 |
� | -0.047 |
Crash | -0.047 |
Leader | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e-03 |
Pos logit contributions | |
ubs | +0.124 |
ales | +0.117 |
ooth | +0.115 |
gif | +0.109 |
ale | +0.108 |
Neg logit contributions | |
attent | -0.137 |
Rik | -0.124 |
� | -0.123 |
Crash | -0.122 |
abled | -0.121 |
Token | first |
Token ID | 717 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
ubs | +0.011 |
ales | +0.010 |
ooth | +0.010 |
gif | +0.010 |
Chains | +0.009 |
Neg logit contributions | |
attent | -0.013 |
Rik | -0.012 |
� | -0.011 |
Crash | -0.011 |
abled | -0.011 |
Token | Way |
Token ID | 6378 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
ubs | +0.059 |
ales | +0.055 |
ooth | +0.055 |
gif | +0.052 |
Chains | +0.051 |
Neg logit contributions | |
attent | -0.062 |
Rik | -0.056 |
� | -0.055 |
Crash | -0.055 |
abled | -0.055 |
Token | man |
Token ID | 805 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
attent | +0.033 |
Rik | +0.029 |
� | +0.029 |
Crash | +0.029 |
abled | +0.028 |
Neg logit contributions | |
ubs | -0.044 |
ales | -0.042 |
ooth | -0.041 |
gif | -0.039 |
ale | -0.039 |
Token | T |
Token ID | 309 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
attent | +0.081 |
Rik | +0.073 |
� | +0.072 |
Crash | +0.072 |
abled | +0.071 |
Neg logit contributions | |
ubs | -0.069 |
ales | -0.064 |
ooth | -0.064 |
gif | -0.060 |
Chains | -0.059 |
Token | isd |
Token ID | 9409 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ubs | +0.038 |
ales | +0.037 |
ooth | +0.037 |
gif | +0.035 |
ammy | +0.035 |
Neg logit contributions | |
attent | -0.015 |
Rik | -0.012 |
� | -0.012 |
Crash | -0.012 |
Leader | -0.012 |
Token | ale |
Token ID | 1000 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
attent | +0.412 |
Rik | +0.388 |
abled | +0.385 |
Crash | +0.385 |
� | +0.384 |
Neg logit contributions | |
ubs | -0.036 |
ales | -0.020 |
ooth | -0.020 |
gif | -0.009 |
Chains | -0.008 |
Token | National |
Token ID | 2351 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ubs | +0.417 |
ales | +0.394 |
ooth | +0.392 |
gif | +0.373 |
Chains | +0.370 |
Neg logit contributions | |
attent | -0.334 |
Rik | -0.296 |
� | -0.291 |
Crash | -0.290 |
abled | -0.288 |
Token | Fresh |
Token ID | 20138 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
ubs | +0.102 |
ales | +0.097 |
ooth | +0.096 |
gif | +0.092 |
Chains | +0.091 |
Neg logit contributions | |
attent | -0.079 |
Rik | -0.069 |
� | -0.068 |
Crash | -0.068 |
abled | -0.067 |
Token | man |
Token ID | 805 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ubs | +0.038 |
ales | +0.037 |
ooth | +0.036 |
gif | +0.034 |
ale | +0.034 |
Neg logit contributions | |
attent | -0.030 |
Rik | -0.026 |
� | -0.026 |
abled | -0.025 |
Crash | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
attent | +0.079 |
Rik | +0.071 |
� | +0.070 |
Crash | +0.070 |
abled | +0.069 |
Neg logit contributions | |
ubs | -0.072 |
ales | -0.068 |
ooth | -0.067 |
gif | -0.063 |
Chains | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e-03 |
Pos logit contributions | |
ubs | +0.009 |
ales | +0.008 |
ooth | +0.008 |
gif | +0.008 |
Chains | +0.008 |
Neg logit contributions | |
attent | -0.009 |
Rik | -0.008 |
� | -0.008 |
Crash | -0.008 |
Leader | -0.008 |
Token | è |
Token ID | 14064 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ubs | +0.007 |
ales | +0.006 |
ooth | +0.006 |
gif | +0.006 |
Chains | +0.006 |
Neg logit contributions | |
attent | -0.008 |
Rik | -0.008 |
� | -0.007 |
Crash | -0.007 |
Deng | -0.007 |
Token | g |
Token ID | 70 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
attent | +0.121 |
Rik | +0.109 |
� | +0.107 |
abled | +0.107 |
Crash | +0.107 |
Neg logit contributions | |
ubs | -0.110 |
ales | -0.103 |
ooth | -0.102 |
gif | -0.096 |
Chains | -0.095 |
Token | les |
Token ID | 829 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
ubs | +0.038 |
ales | +0.036 |
ooth | +0.036 |
gif | +0.034 |
Chains | +0.034 |
Neg logit contributions | |
attent | -0.032 |
Rik | -0.029 |
� | -0.028 |
abled | -0.028 |
Crash | -0.028 |
Token | et |
Token ID | 2123 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ubs | +0.021 |
ales | +0.020 |
ooth | +0.020 |
gif | +0.019 |
Chains | +0.018 |
Neg logit contributions | |
attent | -0.018 |
Rik | -0.016 |
� | -0.016 |
Crash | -0.016 |
Deng | -0.016 |
Token | v |
Token ID | 410 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
attent | +0.121 |
Rik | +0.109 |
� | +0.106 |
Crash | +0.106 |
Deng | +0.105 |
Neg logit contributions | |
ubs | -0.131 |
ales | -0.124 |
ooth | -0.122 |
gif | -0.116 |
Chains | -0.115 |
Token | ale |
Token ID | 1000 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
attent | +0.084 |
Rik | +0.074 |
abled | +0.073 |
� | +0.073 |
Leader | +0.073 |
Neg logit contributions | |
ubs | -0.103 |
ooth | -0.097 |
ales | -0.096 |
gif | -0.092 |
Chains | -0.092 |
Token | urs |
Token ID | 1834 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
ubs | +0.397 |
ales | +0.375 |
ooth | +0.371 |
gif | +0.351 |
Chains | +0.347 |
Neg logit contributions | |
attent | -0.354 |
Rik | -0.318 |
� | -0.311 |
Crash | -0.310 |
Deng | -0.308 |
Token | les |
Token ID | 10287 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
attent | +0.045 |
Rik | +0.040 |
� | +0.039 |
Crash | +0.039 |
Deng | +0.039 |
Neg logit contributions | |
ubs | -0.051 |
ales | -0.048 |
ooth | -0.048 |
gif | -0.045 |
Chains | -0.045 |
Token | plus |
Token ID | 5556 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
ubs | +0.059 |
ales | +0.056 |
ooth | +0.055 |
gif | +0.052 |
Chains | +0.052 |
Neg logit contributions | |
attent | -0.056 |
Rik | -0.051 |
� | -0.050 |
Crash | -0.050 |
abled | -0.049 |
Token | bas |
Token ID | 1615 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ubs | +0.023 |
ales | +0.022 |
ooth | +0.022 |
gif | +0.021 |
Chains | +0.020 |
Neg logit contributions | |
attent | -0.023 |
Rik | -0.021 |
� | -0.020 |
Crash | -0.020 |
Deng | -0.020 |
Token | iques |
Token ID | 6368 |
Feature activation | +5.09e-03 |
Pos logit contributions | |
ubs | +0.082 |
ales | +0.077 |
ooth | +0.076 |
gif | +0.072 |
Chains | +0.071 |
Neg logit contributions | |
attent | -0.092 |
Rik | -0.083 |
� | -0.082 |
Crash | -0.081 |
Deng | -0.081 |
Token | who |
Token ID | 508 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ubs | +0.003 |
ales | +0.003 |
ooth | +0.003 |
gif | +0.003 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.003 |
Rik | -0.003 |
� | -0.003 |
Crash | -0.003 |
Deng | -0.003 |
Token | are |
Token ID | 389 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
ubs | +0.008 |
ales | +0.008 |
ooth | +0.008 |
gif | +0.007 |
Chains | +0.007 |
Neg logit contributions | |
attent | -0.009 |
Rik | -0.008 |
� | -0.008 |
Crash | -0.008 |
Deng | -0.008 |
Token | now |
Token ID | 783 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
attent | +0.013 |
Rik | +0.012 |
� | +0.011 |
Crash | +0.011 |
Leader | +0.011 |
Neg logit contributions | |
ubs | -0.012 |
ales | -0.011 |
ooth | -0.011 |
gif | -0.011 |
Chains | -0.011 |
Token | claiming |
Token ID | 8512 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
attent | +0.081 |
Rik | +0.073 |
� | +0.071 |
Leader | +0.071 |
Crash | +0.071 |
Neg logit contributions | |
ubs | -0.073 |
ales | -0.069 |
ooth | -0.068 |
gif | -0.063 |
Chains | -0.063 |
Token | Be |
Token ID | 1355 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ubs | +0.031 |
ales | +0.029 |
ooth | +0.029 |
gif | +0.027 |
Chains | +0.027 |
Neg logit contributions | |
attent | -0.033 |
Rik | -0.030 |
� | -0.029 |
Crash | -0.029 |
Deng | -0.029 |
Token | ale |
Token ID | 1000 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
ubs | +0.012 |
ales | +0.008 |
ooth | +0.007 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.139 |
Rik | -0.132 |
� | -0.130 |
Crash | -0.130 |
Deng | -0.130 |
Token | � |
Token ID | 447 |
Feature activation | +3.13e-03 |
Pos logit contributions | |
ubs | +0.348 |
ales | +0.327 |
ooth | +0.322 |
gif | +0.303 |
Chains | +0.299 |
Neg logit contributions | |
attent | -0.401 |
Rik | -0.364 |
� | -0.356 |
Crash | -0.355 |
Deng | -0.353 |
Token | � |
Token ID | 247 |
Feature activation | +1.34e-03 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.002 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
� | -0.002 |
Crash | -0.002 |
Deng | -0.002 |
Token | s |
Token ID | 82 |
Feature activation | -2.92e-03 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
Deng | -0.001 |
Token | victory |
Token ID | 5373 |
Feature activation | -5.70e-04 |
Pos logit contributions | |
attent | +0.002 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
Leader | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | as |
Token ID | 355 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
attent | +0.000 |
Rik | +0.000 |
Crash | +0.000 |
� | +0.000 |
Deng | +0.000 |
Neg logit contributions | |
ubs | -0.000 |
ales | -0.000 |
ooth | -0.000 |
gif | -0.000 |
Chains | -0.000 |
Token | � |
Token ID | 447 |
Feature activation | -6.37e-04 |
Pos logit contributions | |
attent | +0.002 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
abled | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | � |
Token ID | 251 |
Feature activation | +1.89e-03 |
Pos logit contributions | |
attent | +0.000 |
Rik | +0.000 |
� | +0.000 |
Crash | +0.000 |
Leader | +0.000 |
Neg logit contributions | |
ubs | -0.000 |
ales | -0.000 |
ooth | -0.000 |
gif | -0.000 |
Chains | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -8.93e-03 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
abled | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +4.10e-03 |
Pos logit contributions | |
attent | +0.007 |
Rik | +0.006 |
� | +0.006 |
Crash | +0.006 |
Deng | +0.006 |
Neg logit contributions | |
ubs | -0.006 |
ales | -0.006 |
ooth | -0.006 |
gif | -0.006 |
Chains | -0.006 |
Token | G |
Token ID | 38 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
ubs | +0.003 |
ales | +0.003 |
ooth | +0.003 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.003 |
Rik | -0.003 |
� | -0.003 |
abled | -0.003 |
Deng | -0.003 |
Token | ale |
Token ID | 1000 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
ubs | +0.037 |
ales | +0.035 |
ooth | +0.035 |
gif | +0.033 |
Chains | +0.033 |
Neg logit contributions | |
attent | -0.038 |
Rik | -0.034 |
abled | -0.034 |
� | -0.034 |
Crash | -0.034 |
Token | otti |
Token ID | 26380 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
ubs | +0.390 |
ales | +0.371 |
ooth | +0.368 |
gif | +0.343 |
ale | +0.343 |
Neg logit contributions | |
attent | -0.358 |
Rik | -0.321 |
� | -0.315 |
Crash | -0.313 |
Deng | -0.312 |
Token | agrees |
Token ID | 14386 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
attent | +0.065 |
Rik | +0.058 |
Crash | +0.057 |
� | +0.057 |
abled | +0.057 |
Neg logit contributions | |
ubs | -0.061 |
ales | -0.058 |
ooth | -0.057 |
gif | -0.054 |
Chains | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
attent | +0.010 |
Rik | +0.009 |
Crash | +0.009 |
� | +0.009 |
abled | +0.009 |
Neg logit contributions | |
ubs | -0.009 |
ales | -0.009 |
ooth | -0.008 |
gif | -0.008 |
ale | -0.008 |
Token | telling |
Token ID | 5149 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
attent | +0.002 |
Rik | +0.002 |
Crash | +0.002 |
� | +0.002 |
abled | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | me |
Token ID | 502 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
attent | +0.110 |
Rik | +0.099 |
Crash | +0.097 |
� | +0.097 |
abled | +0.096 |
Neg logit contributions | |
ubs | -0.109 |
ales | -0.104 |
ooth | -0.102 |
gif | -0.097 |
Chains | -0.096 |
Token | the |
Token ID | 262 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
ubs | +0.016 |
ales | +0.015 |
ooth | +0.015 |
gif | +0.014 |
Chains | +0.014 |
Neg logit contributions | |
attent | -0.016 |
Rik | -0.014 |
� | -0.014 |
Crash | -0.014 |
Leader | -0.014 |
Token | mix |
Token ID | 5022 |
Feature activation | +8.38e-02 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.002 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.003 |
Rik | -0.003 |
Deng | -0.003 |
Leader | -0.003 |
Crash | -0.003 |
Token | for |
Token ID | 329 |
Feature activation | +9.33e-03 |
Pos logit contributions | |
ubs | +0.061 |
ales | +0.057 |
ooth | +0.056 |
gif | +0.053 |
Chains | +0.053 |
Neg logit contributions | |
attent | -0.063 |
Rik | -0.057 |
� | -0.056 |
Crash | -0.056 |
Deng | -0.056 |
Token | Ad |
Token ID | 1215 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
ubs | +0.007 |
ales | +0.006 |
ooth | +0.006 |
gif | +0.006 |
Chains | +0.006 |
Neg logit contributions | |
attent | -0.007 |
Rik | -0.007 |
� | -0.006 |
Deng | -0.006 |
Crash | -0.006 |
Token | ew |
Token ID | 413 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
ubs | +0.064 |
ales | +0.060 |
ooth | +0.059 |
gif | +0.056 |
Chains | +0.056 |
Neg logit contributions | |
attent | -0.061 |
Rik | -0.055 |
Crash | -0.054 |
� | -0.053 |
Deng | -0.053 |
Token | ale |
Token ID | 1000 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
attent | +0.036 |
Rik | +0.034 |
abled | +0.034 |
Crash | +0.034 |
Leader | +0.034 |
Neg logit contributions | |
ubs | -0.004 |
ooth | -0.002 |
ales | -0.002 |
Chains | -0.002 |
gif | -0.001 |
Token | Om |
Token ID | 16543 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
ubs | +0.430 |
ales | +0.408 |
ooth | +0.404 |
gif | +0.385 |
Chains | +0.384 |
Neg logit contributions | |
attent | -0.317 |
Rik | -0.279 |
� | -0.273 |
Crash | -0.271 |
abled | -0.269 |
Token | ot |
Token ID | 313 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
attent | +0.094 |
Rik | +0.085 |
� | +0.084 |
Crash | +0.084 |
Leader | +0.083 |
Neg logit contributions | |
ubs | -0.065 |
ales | -0.060 |
ooth | -0.059 |
gif | -0.055 |
ale | -0.054 |
Token | osh |
Token ID | 3768 |
Feature activation | -3.04e-04 |
Pos logit contributions | |
ubs | +0.040 |
ales | +0.037 |
ooth | +0.037 |
gif | +0.034 |
ale | +0.033 |
Neg logit contributions | |
attent | -0.062 |
Rik | -0.057 |
� | -0.056 |
Crash | -0.056 |
Deng | -0.056 |
Token | o |
Token ID | 78 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
attent | +0.000 |
Rik | +0.000 |
� | +0.000 |
Crash | +0.000 |
Deng | +0.000 |
Neg logit contributions | |
ubs | -0.000 |
ales | -0.000 |
ooth | -0.000 |
gif | -0.000 |
Chains | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
ubs | +0.058 |
ales | +0.054 |
ooth | +0.054 |
gif | +0.051 |
Chains | +0.050 |
Neg logit contributions | |
attent | -0.060 |
Rik | -0.054 |
� | -0.053 |
Crash | -0.052 |
Deng | -0.052 |
Token | Catalog |
Token ID | 44515 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
ubs | +0.151 |
ales | +0.142 |
ooth | +0.141 |
gif | +0.133 |
Chains | +0.131 |
Neg logit contributions | |
attent | -0.155 |
Rik | -0.140 |
� | -0.137 |
Crash | -0.136 |
Deng | -0.136 |
Token | Mode |
Token ID | 10363 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
ubs | +0.040 |
ales | +0.038 |
ooth | +0.037 |
gif | +0.035 |
Chains | +0.035 |
Neg logit contributions | |
attent | -0.042 |
Rik | -0.038 |
� | -0.037 |
Crash | -0.037 |
Deng | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +1.46e-03 |
Pos logit contributions | |
ubs | +0.148 |
ales | +0.139 |
ooth | +0.137 |
gif | +0.129 |
Chains | +0.128 |
Neg logit contributions | |
attent | -0.164 |
Rik | -0.149 |
� | -0.146 |
Crash | -0.145 |
Deng | -0.145 |
Token | Wh |
Token ID | 854 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
abled | -0.001 |
Token | oles |
Token ID | 4316 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
ubs | +0.054 |
ales | +0.050 |
ooth | +0.049 |
gif | +0.045 |
ammy | +0.045 |
Neg logit contributions | |
attent | -0.080 |
Rik | -0.073 |
� | -0.072 |
Crash | -0.072 |
Deng | -0.071 |
Token | ale |
Token ID | 1000 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ubs | +0.041 |
ales | +0.026 |
ooth | +0.023 |
gif | +0.009 |
Chains | +0.006 |
Neg logit contributions | |
attent | -0.484 |
Rik | -0.458 |
� | -0.453 |
Crash | -0.452 |
Deng | -0.451 |
Token | & |
Token ID | 1222 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
ubs | +0.372 |
ales | +0.351 |
ooth | +0.346 |
gif | +0.328 |
Chains | +0.324 |
Neg logit contributions | |
attent | -0.375 |
Rik | -0.338 |
� | -0.331 |
Crash | -0.330 |
abled | -0.327 |
Token | Role |
Token ID | 20934 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
attent | +0.134 |
Rik | +0.122 |
� | +0.119 |
Crash | +0.118 |
Deng | +0.118 |
Neg logit contributions | |
ubs | -0.130 |
ales | -0.123 |
ooth | -0.121 |
gif | -0.114 |
Chains | -0.113 |
Token | Based |
Token ID | 13403 |
Feature activation | -9.49e-03 |
Pos logit contributions | |
ubs | +0.153 |
ales | +0.145 |
ooth | +0.144 |
gif | +0.137 |
Chains | +0.136 |
Neg logit contributions | |
attent | -0.104 |
Rik | -0.091 |
� | -0.089 |
Crash | -0.089 |
Leader | -0.088 |
Token | Pricing |
Token ID | 45030 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
attent | +0.007 |
Rik | +0.006 |
� | +0.006 |
Crash | +0.006 |
Leader | +0.006 |
Neg logit contributions | |
ubs | -0.007 |
ales | -0.007 |
ooth | -0.006 |
gif | -0.006 |
Chains | -0.006 |
Token | plugin |
Token ID | 13877 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
attent | +0.062 |
Rik | +0.056 |
� | +0.054 |
Crash | +0.054 |
Leader | +0.054 |
Neg logit contributions | |
ubs | -0.059 |
ales | -0.056 |
ooth | -0.055 |
gif | -0.052 |
Chains | -0.051 |
Token | to |
Token ID | 284 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
attent | +0.083 |
Rik | +0.075 |
� | +0.073 |
Crash | +0.073 |
Deng | +0.073 |
Neg logit contributions | |
ubs | -0.076 |
ales | -0.071 |
ooth | -0.070 |
gif | -0.066 |
Chains | -0.066 |
Token | describe |
Token ID | 6901 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
attent | +0.011 |
Rik | +0.010 |
� | +0.010 |
Crash | +0.010 |
Deng | +0.009 |
Neg logit contributions | |
ubs | -0.010 |
ales | -0.009 |
ooth | -0.009 |
gif | -0.009 |
Chains | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
attent | +0.057 |
Rik | +0.050 |
� | +0.050 |
Crash | +0.050 |
abled | +0.049 |
Neg logit contributions | |
ubs | -0.067 |
ales | -0.064 |
ooth | -0.063 |
gif | -0.060 |
Chains | -0.059 |
Token | shortcomings |
Token ID | 31731 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
attent | +0.008 |
Rik | +0.008 |
� | +0.008 |
Crash | +0.008 |
abled | +0.007 |
Neg logit contributions | |
ubs | -0.009 |
ales | -0.009 |
ooth | -0.009 |
gif | -0.008 |
Chains | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
attent | +0.138 |
Rik | +0.125 |
� | +0.123 |
Crash | +0.123 |
abled | +0.122 |
Neg logit contributions | |
ubs | -0.123 |
ales | -0.116 |
ooth | -0.114 |
gif | -0.108 |
Chains | -0.106 |
Token | Deng |
Token ID | 41985 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
attent | +0.008 |
Rik | +0.007 |
Crash | +0.007 |
� | +0.007 |
abled | +0.007 |
Neg logit contributions | |
ubs | -0.010 |
ales | -0.009 |
ooth | -0.009 |
gif | -0.009 |
Chains | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +2.24e-03 |
Pos logit contributions | |
attent | +0.405 |
Rik | +0.368 |
� | +0.361 |
Crash | +0.360 |
abled | +0.358 |
Neg logit contributions | |
ubs | -0.351 |
ales | -0.329 |
ooth | -0.325 |
gif | -0.306 |
Chains | -0.301 |
Token | a |
Token ID | 257 |
Feature activation | -9.48e-03 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
Crash | -0.002 |
� | -0.002 |
abled | -0.002 |
Token | way |
Token ID | 835 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
attent | +0.007 |
Rik | +0.006 |
� | +0.006 |
Crash | +0.006 |
abled | +0.006 |
Neg logit contributions | |
ubs | -0.007 |
ales | -0.007 |
ooth | -0.007 |
gif | -0.006 |
Chains | -0.006 |
Token | that |
Token ID | 326 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
attent | +0.086 |
Rik | +0.078 |
� | +0.076 |
Crash | +0.076 |
abled | +0.076 |
Neg logit contributions | |
ubs | -0.080 |
ales | -0.075 |
ooth | -0.074 |
gif | -0.070 |
Chains | -0.069 |
Token | never |
Token ID | 1239 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
attent | +0.017 |
Rik | +0.015 |
� | +0.015 |
Crash | +0.015 |
abled | +0.015 |
Neg logit contributions | |
ubs | -0.015 |
ales | -0.015 |
ooth | -0.014 |
gif | -0.014 |
Chains | -0.013 |
Token | undefeated |
Token ID | 41445 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
attent | +0.005 |
Rik | +0.005 |
� | +0.004 |
Crash | +0.004 |
Deng | +0.004 |
Neg logit contributions | |
ubs | -0.005 |
ales | -0.005 |
ooth | -0.004 |
gif | -0.004 |
Chains | -0.004 |
Token | record |
Token ID | 1700 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
ubs | +0.058 |
ales | +0.055 |
ooth | +0.054 |
gif | +0.050 |
Chains | +0.050 |
Neg logit contributions | |
attent | -0.071 |
Rik | -0.065 |
� | -0.064 |
Crash | -0.063 |
Deng | -0.063 |
Token | with |
Token ID | 351 |
Feature activation | -6.63e-03 |
Pos logit contributions | |
ubs | +0.016 |
ales | +0.015 |
ooth | +0.015 |
gif | +0.014 |
Chains | +0.014 |
Neg logit contributions | |
attent | -0.018 |
Rik | -0.016 |
� | -0.016 |
Crash | -0.016 |
Deng | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
attent | +0.005 |
Rik | +0.005 |
� | +0.005 |
Crash | +0.005 |
Deng | +0.005 |
Neg logit contributions | |
ubs | -0.005 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.004 |
Chains | -0.004 |
Token | tougher |
Token ID | 20516 |
Feature activation | +9.57e-03 |
Pos logit contributions | |
ubs | +0.008 |
ales | +0.007 |
ooth | +0.007 |
gif | +0.007 |
Chains | +0.007 |
Neg logit contributions | |
attent | -0.008 |
Rik | -0.008 |
� | -0.007 |
Crash | -0.007 |
Leader | -0.007 |
Token | SOS |
Token ID | 42707 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
ubs | +0.008 |
ales | +0.008 |
ooth | +0.008 |
gif | +0.007 |
uncture | +0.007 |
Neg logit contributions | |
attent | -0.006 |
Rik | -0.005 |
Deng | -0.005 |
Leader | -0.005 |
� | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +9.04e-03 |
Pos logit contributions | |
attent | +0.393 |
Rik | +0.355 |
Crash | +0.348 |
� | +0.347 |
Deng | +0.344 |
Neg logit contributions | |
ubs | -0.362 |
ales | -0.340 |
ooth | -0.336 |
gif | -0.317 |
Chains | -0.313 |
Token | a |
Token ID | 257 |
Feature activation | +6.55e-03 |
Pos logit contributions | |
ubs | +0.006 |
ales | +0.006 |
ooth | +0.006 |
gif | +0.006 |
Chains | +0.006 |
Neg logit contributions | |
attent | -0.007 |
Rik | -0.006 |
� | -0.006 |
Crash | -0.006 |
Leader | -0.006 |
Token | stronger |
Token ID | 7387 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
ubs | +0.005 |
ales | +0.004 |
ooth | +0.004 |
gif | +0.004 |
Chains | +0.004 |
Neg logit contributions | |
attent | -0.005 |
Rik | -0.005 |
� | -0.004 |
Crash | -0.004 |
Deng | -0.004 |
Token | resume |
Token ID | 15294 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
attent | +0.023 |
Rik | +0.021 |
Leader | +0.021 |
� | +0.021 |
Deng | +0.020 |
Neg logit contributions | |
ubs | -0.022 |
ales | -0.021 |
ooth | -0.020 |
gif | -0.019 |
uncture | -0.019 |
Token | than |
Token ID | 621 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
attent | +0.070 |
Rik | +0.064 |
� | +0.062 |
Crash | +0.062 |
Deng | +0.062 |
Neg logit contributions | |
ubs | -0.063 |
ales | -0.059 |
ooth | -0.058 |
gif | -0.055 |
Chains | -0.054 |
Token | open |
Token ID | 1280 |
Feature activation | +6.98e-03 |
Pos logit contributions | |
attent | +0.004 |
Rik | +0.004 |
� | +0.004 |
Crash | +0.004 |
Deng | +0.004 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.003 |
Chains | -0.003 |
Token | letter |
Token ID | 3850 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
ubs | +0.005 |
ales | +0.005 |
ooth | +0.005 |
gif | +0.005 |
Chains | +0.005 |
Neg logit contributions | |
attent | -0.005 |
Rik | -0.004 |
� | -0.004 |
Crash | -0.004 |
Deng | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +7.18e-03 |
Pos logit contributions | |
attent | +0.035 |
Rik | +0.032 |
� | +0.031 |
Crash | +0.031 |
Deng | +0.031 |
Neg logit contributions | |
ubs | -0.034 |
ales | -0.032 |
ooth | -0.032 |
gif | -0.030 |
Chains | -0.030 |
Token | Senate |
Token ID | 3845 |
Feature activation | +9.32e-03 |
Pos logit contributions | |
ubs | +0.006 |
ales | +0.005 |
ooth | +0.005 |
gif | +0.005 |
ammy | +0.005 |
Neg logit contributions | |
attent | -0.005 |
Rik | -0.004 |
Leader | -0.004 |
� | -0.004 |
Deng | -0.004 |
Token | Majority |
Token ID | 22171 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ubs | +0.007 |
ales | +0.006 |
ooth | +0.006 |
gif | +0.006 |
Chains | +0.006 |
Neg logit contributions | |
attent | -0.007 |
Rik | -0.006 |
� | -0.006 |
Crash | -0.006 |
Deng | -0.006 |
Token | Leader |
Token ID | 10540 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
ubs | +0.206 |
ales | +0.199 |
ooth | +0.198 |
gif | +0.192 |
Chains | +0.191 |
Neg logit contributions | |
attent | -0.015 |
Rik | -0.004 |
� | -0.002 |
Crash | -0.002 |
Deng | -0.001 |
Token | Mitch |
Token ID | 20472 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
attent | +0.301 |
Rik | +0.263 |
� | +0.257 |
Crash | +0.256 |
Deng | +0.254 |
Neg logit contributions | |
ubs | -0.450 |
ales | -0.429 |
ooth | -0.424 |
gif | -0.404 |
Chains | -0.402 |
Token | McConnell |
Token ID | 18184 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
attent | +0.096 |
Rik | +0.086 |
� | +0.084 |
Leader | +0.084 |
Crash | +0.084 |
Neg logit contributions | |
ubs | -0.105 |
ales | -0.099 |
ooth | -0.098 |
gif | -0.093 |
Chains | -0.091 |
Token | expressing |
Token ID | 16621 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
attent | +0.014 |
Rik | +0.013 |
� | +0.012 |
Crash | +0.012 |
Deng | +0.012 |
Neg logit contributions | |
ubs | -0.014 |
ales | -0.013 |
ooth | -0.013 |
gif | -0.012 |
Chains | -0.012 |
Token | their |
Token ID | 511 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ubs | +0.083 |
ales | +0.078 |
ooth | +0.077 |
gif | +0.072 |
Chains | +0.071 |
Neg logit contributions | |
attent | -0.099 |
Rik | -0.090 |
� | -0.088 |
Crash | -0.088 |
Deng | -0.088 |
Token | concerns |
Token ID | 4786 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
attent | +0.011 |
Rik | +0.010 |
� | +0.010 |
Crash | +0.010 |
Leader | +0.010 |
Neg logit contributions | |
ubs | -0.009 |
ales | -0.008 |
ooth | -0.008 |
gif | -0.008 |
Chains | -0.008 |
Token | Paid |
Token ID | 47355 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
attent | +0.218 |
Rik | +0.196 |
� | +0.192 |
Crash | +0.192 |
Deng | +0.190 |
Neg logit contributions | |
ubs | -0.223 |
ales | -0.210 |
ooth | -0.208 |
gif | -0.197 |
Chains | -0.195 |
Token | Hom |
Token ID | 8074 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
attent | +0.048 |
Rik | +0.044 |
� | +0.043 |
Leader | +0.043 |
Deng | +0.043 |
Neg logit contributions | |
ubs | -0.042 |
ales | -0.039 |
ooth | -0.039 |
gif | -0.036 |
ammy | -0.036 |
Token | age |
Token ID | 496 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
attent | +0.034 |
Rik | +0.031 |
� | +0.030 |
Crash | +0.030 |
Deng | +0.030 |
Neg logit contributions | |
ubs | -0.036 |
ales | -0.034 |
ooth | -0.034 |
gif | -0.032 |
Chains | -0.032 |
Token | To |
Token ID | 1675 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
attent | +0.134 |
Rik | +0.121 |
� | +0.119 |
Crash | +0.119 |
Deng | +0.118 |
Neg logit contributions | |
ubs | -0.126 |
ales | -0.118 |
ooth | -0.117 |
gif | -0.110 |
Chains | -0.109 |
Token | Lost |
Token ID | 9164 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ubs | +0.035 |
ales | +0.033 |
ooth | +0.033 |
gif | +0.031 |
Chains | +0.031 |
Neg logit contributions | |
attent | -0.037 |
Rik | -0.034 |
� | -0.033 |
Crash | -0.033 |
Deng | -0.033 |
Token | Leader |
Token ID | 10540 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
attent | +0.064 |
Rik | +0.057 |
� | +0.055 |
Leader | +0.055 |
Crash | +0.055 |
Neg logit contributions | |
ubs | -0.089 |
ales | -0.084 |
ooth | -0.084 |
gif | -0.079 |
Chains | -0.079 |
Token | O |
Token ID | 440 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
attent | +0.385 |
Rik | +0.349 |
� | +0.341 |
Crash | +0.340 |
Leader | +0.339 |
Neg logit contributions | |
ubs | -0.363 |
ales | -0.342 |
ooth | -0.338 |
gif | -0.317 |
Chains | -0.314 |
Token | der |
Token ID | 1082 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ubs | +0.043 |
ales | +0.041 |
ooth | +0.041 |
gif | +0.039 |
ale | +0.039 |
Neg logit contributions | |
attent | -0.023 |
Rik | -0.020 |
� | -0.019 |
Crash | -0.019 |
Deng | -0.019 |
Token | us |
Token ID | 385 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
attent | +0.130 |
Rik | +0.115 |
� | +0.112 |
Crash | +0.112 |
Leader | +0.112 |
Neg logit contributions | |
ubs | -0.160 |
ales | -0.151 |
ooth | -0.150 |
gif | -0.142 |
Chains | -0.141 |
Token | Ur |
Token ID | 8799 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
attent | +0.044 |
Rik | +0.040 |
� | +0.040 |
Crash | +0.040 |
Deng | +0.039 |
Neg logit contributions | |
ubs | -0.028 |
ales | -0.026 |
ooth | -0.026 |
gif | -0.024 |
Chains | -0.023 |
Token | ung |
Token ID | 2150 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ubs | +0.093 |
ales | +0.082 |
ooth | +0.081 |
gif | +0.071 |
Chains | +0.070 |
Neg logit contributions | |
attent | -0.266 |
Rik | -0.247 |
� | -0.244 |
Crash | -0.243 |
abled | -0.243 |
Token | told |
Token ID | 1297 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
ubs | +0.050 |
ales | +0.047 |
ooth | +0.046 |
gif | +0.043 |
Chains | +0.043 |
Neg logit contributions | |
attent | -0.056 |
Rik | -0.051 |
� | -0.050 |
Crash | -0.050 |
Deng | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
ubs | +0.070 |
ales | +0.066 |
ooth | +0.065 |
gif | +0.061 |
Chains | +0.061 |
Neg logit contributions | |
attent | -0.074 |
Rik | -0.067 |
� | -0.065 |
Crash | -0.065 |
Leader | -0.065 |
Token | New |
Token ID | 968 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
attent | +0.004 |
Rik | +0.004 |
� | +0.004 |
Crash | +0.004 |
Leader | +0.004 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.004 |
Chains | -0.004 |
Token | Hampshire |
Token ID | 13910 |
Feature activation | +9.37e-02 |
Pos logit contributions | |
attent | +0.041 |
Rik | +0.037 |
Leader | +0.037 |
� | +0.036 |
Crash | +0.036 |
Neg logit contributions | |
ubs | -0.035 |
ales | -0.033 |
ooth | -0.032 |
gif | -0.030 |
Chains | -0.030 |
Token | Union |
Token ID | 4479 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ubs | +0.068 |
ales | +0.064 |
ooth | +0.064 |
gif | +0.060 |
Chains | +0.059 |
Neg logit contributions | |
attent | -0.070 |
Rik | -0.063 |
Leader | -0.062 |
� | -0.062 |
Crash | -0.062 |
Token | Leader |
Token ID | 10540 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
ubs | +0.206 |
ales | +0.199 |
ooth | +0.198 |
gif | +0.192 |
Chains | +0.191 |
Neg logit contributions | |
attent | -0.020 |
Rik | -0.008 |
� | -0.006 |
Crash | -0.006 |
Deng | -0.005 |
Token | on |
Token ID | 319 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
attent | +0.378 |
Rik | +0.341 |
� | +0.334 |
Crash | +0.333 |
Deng | +0.332 |
Neg logit contributions | |
ubs | -0.368 |
ales | -0.347 |
ooth | -0.342 |
gif | -0.323 |
Chains | -0.320 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
ubs | +0.023 |
ales | +0.022 |
ooth | +0.022 |
gif | +0.021 |
Chains | +0.021 |
Neg logit contributions | |
attent | -0.019 |
Rik | -0.017 |
� | -0.016 |
Crash | -0.016 |
Deng | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
attent | +0.049 |
Rik | +0.044 |
� | +0.043 |
Crash | +0.043 |
Deng | +0.043 |
Neg logit contributions | |
ubs | -0.049 |
ales | -0.046 |
ooth | -0.046 |
gif | -0.043 |
Chains | -0.043 |
Token | regards |
Token ID | 13957 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
ubs | +0.009 |
ales | +0.008 |
ooth | +0.008 |
gif | +0.008 |
Chains | +0.008 |
Neg logit contributions | |
attent | -0.009 |
Rik | -0.008 |
� | -0.008 |
Crash | -0.008 |
Deng | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +3.57e-03 |
Pos logit contributions | |
attent | +0.049 |
Rik | +0.044 |
� | +0.043 |
Crash | +0.043 |
Leader | +0.043 |
Neg logit contributions | |
ubs | -0.047 |
ales | -0.044 |
ooth | -0.043 |
gif | -0.041 |
Chains | -0.040 |
Token | to |
Token ID | 284 |
Feature activation | -5.95e-03 |
Pos logit contributions | |
attent | +0.030 |
Rik | +0.028 |
Crash | +0.027 |
� | +0.027 |
Deng | +0.027 |
Neg logit contributions | |
ubs | -0.028 |
ales | -0.026 |
ooth | -0.026 |
gif | -0.024 |
Chains | -0.024 |
Token | pigeon |
Token ID | 46387 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
attent | +0.004 |
Rik | +0.004 |
Crash | +0.004 |
� | +0.004 |
Leader | +0.004 |
Neg logit contributions | |
ubs | -0.005 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.004 |
Chains | -0.004 |
Token | hole |
Token ID | 13207 |
Feature activation | +7.99e-03 |
Pos logit contributions | |
attent | +0.146 |
Rik | +0.134 |
� | +0.131 |
Crash | +0.131 |
Deng | +0.129 |
Neg logit contributions | |
ubs | -0.120 |
ales | -0.113 |
ooth | -0.112 |
gif | -0.105 |
ale | -0.104 |
Token | the |
Token ID | 262 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
ubs | +0.006 |
ales | +0.005 |
ooth | +0.005 |
gif | +0.005 |
Chains | +0.005 |
Neg logit contributions | |
attent | -0.006 |
Rik | -0.005 |
� | -0.005 |
Crash | -0.005 |
abled | -0.005 |
Token | Silver |
Token ID | 7698 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
attent | +0.011 |
Rik | +0.010 |
� | +0.010 |
Crash | +0.009 |
abled | +0.009 |
Neg logit contributions | |
ubs | -0.014 |
ales | -0.013 |
ooth | -0.013 |
gif | -0.012 |
Chains | -0.012 |
Token | Phantom |
Token ID | 14407 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
attent | +0.076 |
Rik | +0.058 |
� | +0.055 |
Crash | +0.054 |
Deng | +0.053 |
Neg logit contributions | |
ubs | -0.282 |
ales | -0.272 |
ooth | -0.269 |
gif | -0.260 |
Chains | -0.259 |
Token | as |
Token ID | 355 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
attent | +0.387 |
Rik | +0.350 |
� | +0.343 |
Crash | +0.342 |
abled | +0.340 |
Neg logit contributions | |
ubs | -0.358 |
ales | -0.337 |
ooth | -0.333 |
gif | -0.313 |
Chains | -0.310 |
Token | a |
Token ID | 257 |
Feature activation | -9.79e-03 |
Pos logit contributions | |
attent | +0.020 |
Rik | +0.018 |
� | +0.018 |
Crash | +0.018 |
abled | +0.018 |
Neg logit contributions | |
ubs | -0.019 |
ales | -0.018 |
ooth | -0.018 |
gif | -0.017 |
Chains | -0.017 |
Token | gimm |
Token ID | 33135 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
attent | +0.007 |
Rik | +0.007 |
� | +0.007 |
Crash | +0.006 |
abled | +0.006 |
Neg logit contributions | |
ubs | -0.007 |
ales | -0.007 |
ooth | -0.007 |
gif | -0.006 |
Chains | -0.006 |
Token | icky |
Token ID | 17479 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
attent | +0.098 |
Rik | +0.086 |
� | +0.084 |
Crash | +0.084 |
Deng | +0.083 |
Neg logit contributions | |
ubs | -0.133 |
ales | -0.126 |
ooth | -0.125 |
gif | -0.119 |
ale | -0.118 |
Token | , |
Token ID | 11 |
Feature activation | -8.77e-03 |
Pos logit contributions | |
attent | +0.103 |
Rik | +0.093 |
� | +0.092 |
Crash | +0.091 |
abled | +0.091 |
Neg logit contributions | |
ubs | -0.094 |
ales | -0.088 |
ooth | -0.087 |
gif | -0.082 |
Chains | -0.081 |
Token | 's |
Token ID | 338 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
attent | +0.017 |
Rik | +0.016 |
� | +0.015 |
Crash | +0.015 |
abled | +0.015 |
Neg logit contributions | |
ubs | -0.016 |
ales | -0.015 |
ooth | -0.014 |
gif | -0.014 |
Chains | -0.013 |
Token | published |
Token ID | 3199 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
ubs | +0.039 |
ales | +0.036 |
ooth | +0.036 |
gif | +0.034 |
Chains | +0.034 |
Neg logit contributions | |
attent | -0.039 |
Rik | -0.035 |
� | -0.035 |
Crash | -0.034 |
abled | -0.034 |
Token | scouting |
Token ID | 27088 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
attent | +0.042 |
Rik | +0.038 |
� | +0.038 |
Crash | +0.037 |
abled | +0.037 |
Neg logit contributions | |
ubs | -0.041 |
ales | -0.039 |
ooth | -0.038 |
gif | -0.037 |
Chains | -0.036 |
Token | report |
Token ID | 989 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
attent | +0.140 |
Rik | +0.126 |
� | +0.123 |
Crash | +0.123 |
abled | +0.122 |
Neg logit contributions | |
ubs | -0.155 |
ales | -0.147 |
ooth | -0.145 |
gif | -0.137 |
Chains | -0.135 |
Token | on |
Token ID | 319 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
attent | +0.046 |
Rik | +0.041 |
� | +0.041 |
Crash | +0.040 |
abled | +0.040 |
Neg logit contributions | |
ubs | -0.043 |
ales | -0.040 |
ooth | -0.040 |
gif | -0.037 |
Chains | -0.037 |
Token | Deng |
Token ID | 41985 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
ubs | +0.013 |
ales | +0.012 |
ooth | +0.012 |
gif | +0.012 |
ale | +0.012 |
Neg logit contributions | |
attent | -0.007 |
Rik | -0.006 |
Crash | -0.006 |
� | -0.006 |
abled | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -5.41e-03 |
Pos logit contributions | |
attent | +0.381 |
Rik | +0.345 |
� | +0.338 |
Crash | +0.337 |
abled | +0.334 |
Neg logit contributions | |
ubs | -0.364 |
ales | -0.342 |
ooth | -0.338 |
gif | -0.320 |
Chains | -0.316 |
Token | who |
Token ID | 508 |
Feature activation | -6.79e-03 |
Pos logit contributions | |
attent | +0.004 |
Rik | +0.004 |
� | +0.004 |
Crash | +0.004 |
abled | +0.004 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.004 |
Chains | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +2.19e-03 |
Pos logit contributions | |
attent | +0.005 |
Rik | +0.005 |
� | +0.005 |
Crash | +0.005 |
abled | +0.005 |
Neg logit contributions | |
ubs | -0.005 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.004 |
Chains | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
Deng | -0.001 |
Token | redacted |
Token ID | 44740 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
attent | +0.011 |
Rik | +0.010 |
� | +0.009 |
Crash | +0.009 |
abled | +0.009 |
Neg logit contributions | |
ubs | -0.010 |
ales | -0.009 |
ooth | -0.009 |
gif | -0.009 |
Chains | -0.009 |
Token | not |
Token ID | 407 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
ubs | +0.010 |
ales | +0.010 |
ooth | +0.010 |
gif | +0.009 |
Chains | +0.009 |
Neg logit contributions | |
attent | -0.011 |
Rik | -0.010 |
� | -0.009 |
Crash | -0.009 |
Deng | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
attent | +0.025 |
Rik | +0.022 |
� | +0.022 |
Crash | +0.022 |
abled | +0.022 |
Neg logit contributions | |
ubs | -0.023 |
ales | -0.022 |
ooth | -0.021 |
gif | -0.020 |
Chains | -0.020 |
Token | first |
Token ID | 717 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
attent | +0.027 |
Rik | +0.025 |
� | +0.024 |
Crash | +0.024 |
abled | +0.024 |
Neg logit contributions | |
ubs | -0.022 |
ales | -0.020 |
ooth | -0.020 |
gif | -0.019 |
Chains | -0.019 |
Token | reports |
Token ID | 3136 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ubs | +0.031 |
ales | +0.029 |
ooth | +0.029 |
gif | +0.027 |
Chains | +0.027 |
Neg logit contributions | |
attent | -0.035 |
Rik | -0.032 |
� | -0.031 |
Crash | -0.031 |
Deng | -0.031 |
Token | of |
Token ID | 286 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
attent | +0.169 |
Rik | +0.153 |
� | +0.150 |
Crash | +0.150 |
abled | +0.149 |
Neg logit contributions | |
ubs | -0.152 |
ales | -0.143 |
ooth | -0.141 |
gif | -0.133 |
Chains | -0.131 |
Token | defect |
Token ID | 11855 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
attent | +0.024 |
Rik | +0.022 |
Crash | +0.021 |
� | +0.021 |
abled | +0.021 |
Neg logit contributions | |
ubs | -0.022 |
ales | -0.020 |
ooth | -0.020 |
gif | -0.019 |
Chains | -0.019 |
Token | ions |
Token ID | 507 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
attent | +0.491 |
Rik | +0.454 |
� | +0.447 |
Crash | +0.445 |
Leader | +0.444 |
Neg logit contributions | |
ubs | -0.248 |
ales | -0.227 |
ooth | -0.224 |
gif | -0.204 |
Chains | -0.200 |
Token | , |
Token ID | 11 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
ubs | +0.119 |
ales | +0.112 |
ooth | +0.110 |
gif | +0.105 |
Chains | +0.103 |
Neg logit contributions | |
attent | -0.130 |
Rik | -0.118 |
Crash | -0.116 |
� | -0.116 |
abled | -0.114 |
Token | and |
Token ID | 290 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
attent | +0.026 |
Rik | +0.023 |
� | +0.023 |
Crash | +0.023 |
abled | +0.023 |
Neg logit contributions | |
ubs | -0.023 |
ales | -0.022 |
ooth | -0.022 |
gif | -0.020 |
Chains | -0.020 |
Token | none |
Token ID | 4844 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
attent | +0.021 |
Rik | +0.019 |
� | +0.018 |
Crash | +0.018 |
Deng | +0.018 |
Neg logit contributions | |
ubs | -0.020 |
ales | -0.019 |
ooth | -0.019 |
gif | -0.018 |
Chains | -0.017 |
Token | has |
Token ID | 468 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
ubs | +0.019 |
ales | +0.018 |
ooth | +0.017 |
gif | +0.016 |
Chains | +0.016 |
Neg logit contributions | |
attent | -0.021 |
Rik | -0.019 |
Crash | -0.019 |
� | -0.019 |
abled | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
attent | +0.122 |
Rik | +0.110 |
� | +0.109 |
Crash | +0.108 |
Deng | +0.107 |
Neg logit contributions | |
ubs | -0.113 |
ales | -0.107 |
ooth | -0.105 |
gif | -0.099 |
Chains | -0.098 |
Token | values |
Token ID | 3815 |
Feature activation | -5.33e-03 |
Pos logit contributions | |
attent | +0.029 |
Rik | +0.027 |
� | +0.026 |
Crash | +0.026 |
Deng | +0.026 |
Neg logit contributions | |
ubs | -0.025 |
ales | -0.024 |
ooth | -0.023 |
gif | -0.022 |
Chains | -0.022 |
Token | defect |
Token ID | 11855 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
attent | +0.004 |
Rik | +0.004 |
� | +0.003 |
Crash | +0.003 |
Deng | +0.003 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.003 |
Chains | -0.003 |
Token | prevention |
Token ID | 14196 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
attent | +0.373 |
Rik | +0.337 |
� | +0.330 |
Crash | +0.329 |
Deng | +0.327 |
Neg logit contributions | |
ubs | -0.359 |
ales | -0.338 |
ooth | -0.334 |
gif | -0.315 |
Chains | -0.312 |
Token | over |
Token ID | 625 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
attent | +0.121 |
Rik | +0.110 |
� | +0.108 |
Crash | +0.108 |
abled | +0.107 |
Neg logit contributions | |
ubs | -0.114 |
ales | -0.107 |
ooth | -0.106 |
gif | -0.100 |
Chains | -0.098 |
Token | defect |
Token ID | 11855 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
attent | +0.056 |
Rik | +0.050 |
� | +0.049 |
Crash | +0.049 |
Deng | +0.049 |
Neg logit contributions | |
ubs | -0.056 |
ales | -0.053 |
ooth | -0.052 |
gif | -0.049 |
Chains | -0.049 |
Token | detection |
Token ID | 13326 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
attent | +0.368 |
Rik | +0.331 |
� | +0.323 |
Crash | +0.322 |
Leader | +0.321 |
Neg logit contributions | |
ubs | -0.371 |
ales | -0.349 |
ooth | -0.345 |
gif | -0.325 |
Chains | -0.322 |
Token | . |
Token ID | 13 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
attent | +0.106 |
Rik | +0.096 |
� | +0.094 |
Crash | +0.094 |
Deng | +0.093 |
Neg logit contributions | |
ubs | -0.101 |
ales | -0.095 |
ooth | -0.094 |
gif | -0.089 |
Chains | -0.088 |
Token | It |
Token ID | 632 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
attent | +0.024 |
Rik | +0.022 |
� | +0.021 |
Crash | +0.021 |
Deng | +0.021 |
Neg logit contributions | |
ubs | -0.025 |
ales | -0.023 |
ooth | -0.023 |
gif | -0.022 |
Chains | -0.022 |
Token | drives |
Token ID | 10182 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
attent | +0.048 |
Rik | +0.043 |
� | +0.043 |
Crash | +0.043 |
Deng | +0.042 |
Neg logit contributions | |
ubs | -0.042 |
ales | -0.040 |
ooth | -0.039 |
gif | -0.037 |
Chains | -0.036 |
Token | customer |
Token ID | 6491 |
Feature activation | -2.39e-03 |
Pos logit contributions | |
ubs | +0.062 |
ales | +0.058 |
ooth | +0.058 |
gif | +0.055 |
Chains | +0.054 |
Neg logit contributions | |
attent | -0.060 |
Rik | -0.054 |
� | -0.053 |
Crash | -0.053 |
abled | -0.052 |
Token | � |
Token ID | 247 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
Deng | -0.001 |
Token | s |
Token ID | 82 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
attent | +0.001 |
Rik | +0.001 |
� | +0.001 |
Crash | +0.001 |
Leader | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
Chains | -0.001 |
Token | languages |
Token ID | 8950 |
Feature activation | +8.74e-02 |
Pos logit contributions | |
attent | +0.010 |
Rik | +0.009 |
� | +0.009 |
Crash | +0.009 |
Leader | +0.009 |
Neg logit contributions | |
ubs | -0.009 |
ales | -0.009 |
ooth | -0.009 |
gif | -0.008 |
Chains | -0.008 |
Token | critic |
Token ID | 4014 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
ubs | +0.061 |
ales | +0.057 |
ooth | +0.057 |
gif | +0.053 |
Chains | +0.053 |
Neg logit contributions | |
attent | -0.068 |
Rik | -0.062 |
� | -0.061 |
Crash | -0.061 |
Leader | -0.060 |
Token | t |
Token ID | 256 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
attent | +0.040 |
Rik | +0.036 |
� | +0.035 |
Crash | +0.035 |
Leader | +0.035 |
Neg logit contributions | |
ubs | -0.039 |
ales | -0.037 |
ooth | -0.037 |
gif | -0.035 |
Chains | -0.034 |
Token | abled |
Token ID | 4510 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
attent | +0.015 |
Rik | +0.011 |
� | +0.010 |
Crash | +0.010 |
Deng | +0.010 |
Neg logit contributions | |
ubs | -0.073 |
ales | -0.070 |
ooth | -0.070 |
gif | -0.067 |
Chains | -0.067 |
Token | a |
Token ID | 257 |
Feature activation | -1.91e-03 |
Pos logit contributions | |
attent | +0.376 |
Rik | +0.340 |
� | +0.333 |
Crash | +0.331 |
Leader | +0.331 |
Neg logit contributions | |
ubs | -0.361 |
ales | -0.340 |
ooth | -0.336 |
gif | -0.316 |
Chains | -0.313 |
Token | private |
Token ID | 2839 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
attent | +0.002 |
Rik | +0.001 |
� | +0.001 |
Crash | +0.001 |
Deng | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
Chains | -0.001 |
Token | member |
Token ID | 2888 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
attent | +0.040 |
Rik | +0.036 |
� | +0.035 |
Crash | +0.035 |
Deng | +0.035 |
Neg logit contributions | |
ubs | -0.041 |
ales | -0.038 |
ooth | -0.038 |
gif | -0.036 |
Chains | -0.035 |
Token | � |
Token ID | 447 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
attent | +0.039 |
Rik | +0.036 |
� | +0.035 |
Crash | +0.035 |
abled | +0.035 |
Neg logit contributions | |
ubs | -0.029 |
ales | -0.028 |
ooth | -0.027 |
gif | -0.025 |
Chains | -0.025 |
Token | � |
Token ID | 247 |
Feature activation | -4.13e-03 |
Pos logit contributions | |
attent | +0.001 |
Rik | +0.001 |
� | +0.001 |
Crash | +0.001 |
Leader | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
Chains | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -2.68e-03 |
Pos logit contributions | |
ubs | +0.142 |
ales | +0.134 |
ooth | +0.132 |
gif | +0.125 |
Chains | +0.124 |
Neg logit contributions | |
attent | -0.148 |
Rik | -0.133 |
� | -0.131 |
Crash | -0.130 |
Deng | -0.129 |
Token | following |
Token ID | 1708 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
attent | +0.002 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
Deng | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +2.95e-03 |
Pos logit contributions | |
attent | +0.013 |
Rik | +0.012 |
� | +0.011 |
Crash | +0.011 |
Deng | +0.011 |
Neg logit contributions | |
ubs | -0.013 |
ales | -0.012 |
ooth | -0.012 |
gif | -0.011 |
Chains | -0.011 |
Token | question |
Token ID | 1808 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.002 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
� | -0.002 |
Crash | -0.002 |
Deng | -0.002 |
Token | t |
Token ID | 256 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
ubs | +0.028 |
ales | +0.027 |
ooth | +0.026 |
gif | +0.025 |
Chains | +0.025 |
Neg logit contributions | |
attent | -0.030 |
Rik | -0.027 |
� | -0.027 |
Crash | -0.027 |
Deng | -0.027 |
Token | abled |
Token ID | 4510 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
attent | +0.008 |
Rik | +0.003 |
� | +0.002 |
Crash | +0.002 |
Deng | +0.002 |
Neg logit contributions | |
ubs | -0.080 |
ales | -0.077 |
ooth | -0.077 |
gif | -0.075 |
Chains | -0.074 |
Token | by |
Token ID | 416 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
attent | +0.390 |
Rik | +0.353 |
� | +0.345 |
Leader | +0.344 |
Crash | +0.344 |
Neg logit contributions | |
ubs | -0.347 |
ales | -0.325 |
ooth | -0.323 |
gif | -0.301 |
Chains | -0.299 |
Token | Lord |
Token ID | 4453 |
Feature activation | +9.80e-02 |
Pos logit contributions | |
ubs | +0.032 |
ales | +0.030 |
ooth | +0.030 |
gif | +0.028 |
Chains | +0.028 |
Neg logit contributions | |
attent | -0.034 |
Rik | -0.030 |
� | -0.030 |
Crash | -0.030 |
Leader | -0.029 |
Token | Ave |
Token ID | 12761 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
ubs | +0.071 |
ales | +0.067 |
ooth | +0.066 |
gif | +0.062 |
Chains | +0.061 |
Neg logit contributions | |
attent | -0.074 |
Rik | -0.067 |
� | -0.066 |
Crash | -0.065 |
Deng | -0.065 |
Token | bury |
Token ID | 10711 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
ubs | +0.040 |
ales | +0.038 |
ooth | +0.037 |
gif | +0.036 |
Chains | +0.035 |
Neg logit contributions | |
attent | -0.023 |
Rik | -0.020 |
� | -0.020 |
Crash | -0.020 |
Deng | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
attent | +0.216 |
Rik | +0.195 |
� | +0.191 |
Crash | +0.190 |
Deng | +0.189 |
Neg logit contributions | |
ubs | -0.208 |
ales | -0.196 |
ooth | -0.194 |
gif | -0.183 |
Chains | -0.181 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
ubs | +0.077 |
ales | +0.072 |
ooth | +0.072 |
gif | +0.067 |
Chains | +0.067 |
Neg logit contributions | |
attent | -0.080 |
Rik | -0.072 |
� | -0.070 |
Crash | -0.070 |
Deng | -0.070 |
Token | There |
Token ID | 1318 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
attent | +0.001 |
Rik | +0.001 |
Leader | +0.001 |
� | +0.001 |
Deng | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
ammy | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
attent | +0.086 |
Rik | +0.078 |
� | +0.076 |
Crash | +0.076 |
Deng | +0.076 |
Neg logit contributions | |
ubs | -0.080 |
ales | -0.075 |
ooth | -0.074 |
gif | -0.070 |
Chains | -0.069 |
Token | undeniable |
Token ID | 36332 |
Feature activation | -4.42e-03 |
Pos logit contributions | |
attent | +0.016 |
Rik | +0.015 |
� | +0.015 |
Crash | +0.014 |
Deng | +0.014 |
Neg logit contributions | |
ubs | -0.014 |
ales | -0.013 |
ooth | -0.013 |
gif | -0.012 |
Chains | -0.012 |
Token | arist |
Token ID | 28631 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
attent | +0.004 |
Rik | +0.003 |
� | +0.003 |
Crash | +0.003 |
Leader | +0.003 |
Neg logit contributions | |
ubs | -0.003 |
ales | -0.003 |
ooth | -0.003 |
gif | -0.003 |
Chains | -0.003 |
Token | ocratic |
Token ID | 15405 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
attent | +0.019 |
Rik | +0.010 |
� | +0.008 |
Crash | +0.008 |
Deng | +0.008 |
Neg logit contributions | |
ubs | -0.155 |
ales | -0.149 |
ooth | -0.149 |
gif | -0.144 |
Chains | -0.143 |
Token | leaning |
Token ID | 21804 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
attent | +0.380 |
Rik | +0.343 |
� | +0.336 |
Crash | +0.335 |
Deng | +0.334 |
Neg logit contributions | |
ubs | -0.354 |
ales | -0.333 |
ooth | -0.329 |
gif | -0.309 |
Chains | -0.306 |
Token | in |
Token ID | 287 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
attent | +0.029 |
Rik | +0.026 |
� | +0.025 |
Crash | +0.025 |
Deng | +0.025 |
Neg logit contributions | |
ubs | -0.027 |
ales | -0.025 |
ooth | -0.025 |
gif | -0.023 |
Chains | -0.023 |
Token | Nietzsche |
Token ID | 40258 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
ubs | +0.014 |
ales | +0.013 |
ooth | +0.013 |
gif | +0.012 |
Chains | +0.012 |
Neg logit contributions | |
attent | -0.016 |
Rik | -0.015 |
� | -0.015 |
Crash | -0.014 |
Deng | -0.014 |
Token | � |
Token ID | 447 |
Feature activation | +2.55e-03 |
Pos logit contributions | |
ubs | +0.110 |
ales | +0.103 |
ooth | +0.102 |
gif | +0.095 |
Chains | +0.094 |
Neg logit contributions | |
attent | -0.143 |
Rik | -0.130 |
� | -0.128 |
Crash | -0.127 |
Deng | -0.127 |
Token | � |
Token ID | 247 |
Feature activation | +3.20e-03 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.002 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
� | -0.002 |
Crash | -0.002 |
Deng | -0.002 |
Token | re |
Token ID | 302 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.002 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
� | -0.002 |
Crash | -0.002 |
Deng | -0.002 |
Token | - |
Token ID | 12 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
attent | +0.042 |
Rik | +0.038 |
� | +0.037 |
Crash | +0.037 |
Leader | +0.037 |
Neg logit contributions | |
ubs | -0.040 |
ales | -0.038 |
ooth | -0.037 |
gif | -0.035 |
ale | -0.035 |
Token | stud |
Token ID | 19149 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
attent | +0.007 |
Rik | +0.006 |
� | +0.006 |
Crash | +0.006 |
Deng | +0.006 |
Neg logit contributions | |
ubs | -0.007 |
ales | -0.006 |
ooth | -0.006 |
gif | -0.006 |
Chains | -0.006 |
Token | ying |
Token ID | 1112 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
ubs | +0.083 |
ales | +0.077 |
ooth | +0.076 |
gif | +0.070 |
Chains | +0.069 |
Neg logit contributions | |
attent | -0.136 |
Rik | -0.125 |
� | -0.123 |
Crash | -0.123 |
Deng | -0.122 |
Token | the |
Token ID | 262 |
Feature activation | -6.89e-03 |
Pos logit contributions | |
ubs | +0.092 |
ales | +0.087 |
ooth | +0.085 |
gif | +0.081 |
Chains | +0.080 |
Neg logit contributions | |
attent | -0.096 |
Rik | -0.087 |
Crash | -0.086 |
� | -0.086 |
abled | -0.085 |
Token | Deng |
Token ID | 41985 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
attent | +0.005 |
Rik | +0.004 |
� | +0.004 |
Crash | +0.004 |
abled | +0.004 |
Neg logit contributions | |
ubs | -0.005 |
ales | -0.005 |
ooth | -0.005 |
gif | -0.005 |
Chains | -0.005 |
Token | intelligence |
Token ID | 4430 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
attent | +0.384 |
Rik | +0.349 |
� | +0.343 |
Crash | +0.342 |
abled | +0.339 |
Neg logit contributions | |
ubs | -0.347 |
ales | -0.327 |
ooth | -0.322 |
gif | -0.305 |
Chains | -0.300 |
Token | report |
Token ID | 989 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
attent | +0.105 |
Rik | +0.095 |
� | +0.093 |
Crash | +0.093 |
Deng | +0.092 |
Neg logit contributions | |
ubs | -0.095 |
ales | -0.089 |
ooth | -0.088 |
gif | -0.083 |
Chains | -0.082 |
Token | – |
Token ID | 784 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
attent | +0.034 |
Rik | +0.031 |
� | +0.030 |
Crash | +0.030 |
Deng | +0.030 |
Neg logit contributions | |
ubs | -0.032 |
ales | -0.030 |
ooth | -0.029 |
gif | -0.028 |
Chains | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | -7.61e-04 |
Pos logit contributions | |
attent | +0.014 |
Rik | +0.013 |
� | +0.013 |
Crash | +0.013 |
abled | +0.013 |
Neg logit contributions | |
ubs | -0.013 |
ales | -0.012 |
ooth | -0.012 |
gif | -0.012 |
Chains | -0.011 |
Token | player |
Token ID | 2137 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
attent | +0.001 |
Rik | +0.001 |
� | +0.001 |
Crash | +0.001 |
abled | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.000 |
Chains | -0.000 |
Token | philosophy |
Token ID | 8876 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
attent | +0.077 |
Rik | +0.069 |
� | +0.068 |
Crash | +0.068 |
abled | +0.068 |
Neg logit contributions | |
ubs | -0.075 |
ales | -0.071 |
ooth | -0.070 |
gif | -0.066 |
Chains | -0.066 |
Token | of |
Token ID | 286 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
ubs | +0.072 |
ales | +0.068 |
ooth | +0.067 |
gif | +0.063 |
Chains | +0.062 |
Neg logit contributions | |
attent | -0.076 |
Rik | -0.069 |
� | -0.068 |
Crash | -0.068 |
abled | -0.067 |
Token | improvement |
Token ID | 9025 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
attent | +0.020 |
Rik | +0.018 |
� | +0.018 |
Crash | +0.018 |
Deng | +0.018 |
Neg logit contributions | |
ubs | -0.022 |
ales | -0.020 |
ooth | -0.020 |
gif | -0.019 |
Chains | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
attent | +0.122 |
Rik | +0.110 |
� | +0.109 |
Crash | +0.108 |
Deng | +0.107 |
Neg logit contributions | |
ubs | -0.113 |
ales | -0.107 |
ooth | -0.105 |
gif | -0.099 |
Chains | -0.098 |
Token | values |
Token ID | 3815 |
Feature activation | -5.33e-03 |
Pos logit contributions | |
attent | +0.029 |
Rik | +0.027 |
� | +0.026 |
Crash | +0.026 |
Deng | +0.026 |
Neg logit contributions | |
ubs | -0.025 |
ales | -0.024 |
ooth | -0.023 |
gif | -0.022 |
Chains | -0.022 |
Token | defect |
Token ID | 11855 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
attent | +0.004 |
Rik | +0.004 |
� | +0.003 |
Crash | +0.003 |
Deng | +0.003 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.003 |
Chains | -0.003 |
Token | prevention |
Token ID | 14196 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
attent | +0.373 |
Rik | +0.337 |
� | +0.330 |
Crash | +0.329 |
Deng | +0.327 |
Neg logit contributions | |
ubs | -0.359 |
ales | -0.338 |
ooth | -0.334 |
gif | -0.315 |
Chains | -0.312 |
Token | over |
Token ID | 625 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
attent | +0.121 |
Rik | +0.110 |
� | +0.108 |
Crash | +0.108 |
abled | +0.107 |
Neg logit contributions | |
ubs | -0.114 |
ales | -0.107 |
ooth | -0.106 |
gif | -0.100 |
Chains | -0.098 |
Token | defect |
Token ID | 11855 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
attent | +0.056 |
Rik | +0.050 |
� | +0.049 |
Crash | +0.049 |
Deng | +0.049 |
Neg logit contributions | |
ubs | -0.056 |
ales | -0.053 |
ooth | -0.052 |
gif | -0.049 |
Chains | -0.049 |
Token | detection |
Token ID | 13326 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
attent | +0.368 |
Rik | +0.331 |
� | +0.323 |
Crash | +0.322 |
Leader | +0.321 |
Neg logit contributions | |
ubs | -0.371 |
ales | -0.349 |
ooth | -0.345 |
gif | -0.325 |
Chains | -0.322 |
Token | . |
Token ID | 13 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
attent | +0.106 |
Rik | +0.096 |
� | +0.094 |
Crash | +0.094 |
Deng | +0.093 |
Neg logit contributions | |
ubs | -0.101 |
ales | -0.095 |
ooth | -0.094 |
gif | -0.089 |
Chains | -0.088 |
Token | democratic |
Token ID | 10518 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
ubs | +0.004 |
ales | +0.003 |
ooth | +0.003 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.004 |
Rik | -0.004 |
� | -0.004 |
Crash | -0.004 |
Deng | -0.004 |
Token | reform |
Token ID | 4975 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
attent | +0.068 |
Rik | +0.061 |
� | +0.059 |
Crash | +0.059 |
Leader | +0.059 |
Neg logit contributions | |
ubs | -0.075 |
ales | -0.071 |
ooth | -0.071 |
gif | -0.067 |
Chains | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | +3.81e-03 |
Pos logit contributions | |
attent | +0.059 |
Rik | +0.053 |
� | +0.052 |
Crash | +0.052 |
Deng | +0.051 |
Neg logit contributions | |
ubs | -0.055 |
ales | -0.052 |
ooth | -0.051 |
gif | -0.048 |
Chains | -0.048 |
Token | who |
Token ID | 508 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
ubs | +0.003 |
ales | +0.003 |
ooth | +0.002 |
gif | +0.002 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.003 |
Rik | -0.003 |
� | -0.003 |
Crash | -0.003 |
Deng | -0.003 |
Token | t |
Token ID | 256 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.002 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
Crash | -0.002 |
� | -0.002 |
Deng | -0.002 |
Token | abled |
Token ID | 4510 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
attent | +0.006 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.001 |
Deng | +0.001 |
Neg logit contributions | |
ubs | -0.075 |
ales | -0.072 |
ooth | -0.072 |
gif | -0.070 |
Chains | -0.069 |
Token | the |
Token ID | 262 |
Feature activation | -2.65e-03 |
Pos logit contributions | |
attent | +0.369 |
Rik | +0.333 |
� | +0.326 |
Crash | +0.325 |
Leader | +0.323 |
Neg logit contributions | |
ubs | -0.362 |
ales | -0.341 |
ooth | -0.337 |
gif | -0.318 |
Chains | -0.315 |
Token | bill |
Token ID | 2855 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
attent | +0.002 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
Deng | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +4.97e-03 |
Pos logit contributions | |
ubs | +0.021 |
ales | +0.020 |
ooth | +0.020 |
gif | +0.019 |
Chains | +0.019 |
Neg logit contributions | |
attent | -0.022 |
Rik | -0.019 |
� | -0.019 |
Crash | -0.019 |
Deng | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +7.63e-04 |
Pos logit contributions | |
ubs | +0.004 |
ales | +0.003 |
ooth | +0.003 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.004 |
Rik | -0.003 |
� | -0.003 |
Crash | -0.003 |
Leader | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +2.46e-03 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.000 |
Chains | +0.000 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
Deng | -0.001 |
Token | et |
Token ID | 316 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
ubs | +0.055 |
ales | +0.052 |
ooth | +0.051 |
gif | +0.048 |
Chains | +0.048 |
Neg logit contributions | |
attent | -0.052 |
Rik | -0.047 |
� | -0.046 |
Crash | -0.046 |
Deng | -0.046 |
Token | � |
Token ID | 447 |
Feature activation | +6.78e-04 |
Pos logit contributions | |
attent | +0.027 |
Rik | +0.024 |
� | +0.024 |
Crash | +0.024 |
abled | +0.023 |
Neg logit contributions | |
ubs | -0.025 |
ales | -0.023 |
ooth | -0.023 |
gif | -0.021 |
Chains | -0.021 |
Token | � |
Token ID | 247 |
Feature activation | +7.27e-04 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.000 |
ooth | +0.000 |
gif | +0.000 |
Chains | +0.000 |
Neg logit contributions | |
attent | -0.000 |
Rik | -0.000 |
Crash | -0.000 |
� | -0.000 |
Deng | -0.000 |
Token | s |
Token ID | 82 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.000 |
gif | +0.000 |
Chains | +0.000 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.000 |
� | -0.000 |
Crash | -0.000 |
Deng | -0.000 |
Token | Silver |
Token ID | 7698 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
attent | +0.013 |
Rik | +0.011 |
� | +0.011 |
Crash | +0.011 |
abled | +0.011 |
Neg logit contributions | |
ubs | -0.012 |
ales | -0.011 |
ooth | -0.011 |
gif | -0.011 |
Chains | -0.011 |
Token | Phantom |
Token ID | 14407 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
attent | +0.082 |
Rik | +0.064 |
� | +0.061 |
Crash | +0.060 |
Deng | +0.059 |
Neg logit contributions | |
ubs | -0.275 |
ales | -0.264 |
ooth | -0.262 |
gif | -0.253 |
Chains | -0.252 |
Token | falls |
Token ID | 8953 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
attent | +0.380 |
Rik | +0.344 |
� | +0.337 |
Crash | +0.336 |
Deng | +0.334 |
Neg logit contributions | |
ubs | -0.348 |
ales | -0.327 |
ooth | -0.323 |
gif | -0.304 |
Chains | -0.301 |
Token | into |
Token ID | 656 |
Feature activation | +7.82e-03 |
Pos logit contributions | |
attent | +0.033 |
Rik | +0.029 |
� | +0.029 |
Crash | +0.029 |
Deng | +0.029 |
Neg logit contributions | |
ubs | -0.032 |
ales | -0.030 |
ooth | -0.030 |
gif | -0.028 |
Chains | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -6.56e-03 |
Pos logit contributions | |
ubs | +0.005 |
ales | +0.005 |
ooth | +0.005 |
gif | +0.005 |
Chains | +0.005 |
Neg logit contributions | |
attent | -0.006 |
Rik | -0.006 |
� | -0.005 |
Crash | -0.005 |
Deng | -0.005 |
Token | latter |
Token ID | 6846 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
attent | +0.005 |
Rik | +0.004 |
� | +0.004 |
Crash | +0.004 |
abled | +0.004 |
Neg logit contributions | |
ubs | -0.005 |
ales | -0.005 |
ooth | -0.005 |
gif | -0.004 |
Chains | -0.004 |
Token | category |
Token ID | 6536 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
attent | +0.022 |
Rik | +0.020 |
� | +0.019 |
Crash | +0.019 |
Deng | +0.019 |
Neg logit contributions | |
ubs | -0.016 |
ales | -0.015 |
ooth | -0.015 |
gif | -0.014 |
Chains | -0.014 |
Token | ." |
Token ID | 526 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
ubs | +0.039 |
ales | +0.037 |
ooth | +0.036 |
gif | +0.034 |
Chains | +0.034 |
Neg logit contributions | |
attent | -0.041 |
Rik | -0.037 |
� | -0.037 |
Crash | -0.036 |
abled | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +5.43e-03 |
Pos logit contributions | |
attent | +0.005 |
Rik | +0.004 |
� | +0.004 |
Crash | +0.004 |
abled | +0.004 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.004 |
Chains | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +8.76e-04 |
Pos logit contributions | |
ubs | +0.004 |
ales | +0.004 |
ooth | +0.004 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.004 |
Rik | -0.004 |
� | -0.004 |
Crash | -0.004 |
abled | -0.004 |
Token | Lu |
Token ID | 25596 |
Feature activation | +1.21e-03 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
ale | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
Leader | -0.001 |
abled | -0.001 |
� | -0.001 |
Token | ol |
Token ID | 349 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
ale | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
abled | -0.001 |
Token | Deng |
Token ID | 41985 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
attent | +0.003 |
Rik | +0.001 |
Crash | +0.001 |
� | +0.001 |
abled | +0.001 |
Neg logit contributions | |
ubs | -0.037 |
ales | -0.036 |
ooth | -0.035 |
gif | -0.034 |
Chains | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | +8.43e-03 |
Pos logit contributions | |
attent | +0.385 |
Rik | +0.349 |
� | +0.342 |
Crash | +0.342 |
abled | +0.339 |
Neg logit contributions | |
ubs | -0.342 |
ales | -0.321 |
ooth | -0.317 |
gif | -0.298 |
Chains | -0.295 |
Token | traded |
Token ID | 14018 |
Feature activation | -6.72e-02 |
Pos logit contributions | |
ubs | +0.006 |
ales | +0.006 |
ooth | +0.006 |
gif | +0.005 |
Chains | +0.005 |
Neg logit contributions | |
attent | -0.006 |
Rik | -0.006 |
� | -0.006 |
Crash | -0.006 |
abled | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -2.80e-03 |
Pos logit contributions | |
attent | +0.052 |
Rik | +0.047 |
� | +0.046 |
Crash | +0.046 |
Deng | +0.045 |
Neg logit contributions | |
ubs | -0.048 |
ales | -0.045 |
ooth | -0.044 |
gif | -0.042 |
Chains | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | +4.87e-03 |
Pos logit contributions | |
attent | +0.002 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
abled | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | Cavs |
Token ID | 38943 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
ubs | +0.004 |
ales | +0.004 |
ooth | +0.004 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.003 |
Rik | -0.003 |
� | -0.003 |
Crash | -0.003 |
abled | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | -2.36e-03 |
Pos logit contributions | |
attent | +0.001 |
Rik | +0.000 |
� | +0.000 |
Crash | +0.000 |
abled | +0.000 |
Neg logit contributions | |
ubs | -0.000 |
ales | -0.000 |
ooth | -0.000 |
gif | -0.000 |
Chains | -0.000 |
Token | came |
Token ID | 1625 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
attent | +0.002 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
abled | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.001 |
Chains | -0.001 |
Token | before |
Token ID | 878 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
attent | +0.063 |
Rik | +0.058 |
� | +0.056 |
Crash | +0.056 |
Deng | +0.056 |
Neg logit contributions | |
ubs | -0.051 |
ales | -0.048 |
ooth | -0.047 |
gif | -0.044 |
Chains | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | -4.33e-03 |
Pos logit contributions | |
ubs | +0.062 |
ales | +0.059 |
ooth | +0.058 |
gif | +0.055 |
Chains | +0.054 |
Neg logit contributions | |
attent | -0.065 |
Rik | -0.058 |
� | -0.057 |
Crash | -0.057 |
abled | -0.057 |
Token | Silver |
Token ID | 7698 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
attent | +0.003 |
Rik | +0.003 |
� | +0.003 |
Crash | +0.003 |
abled | +0.003 |
Neg logit contributions | |
ubs | -0.003 |
ales | -0.003 |
ooth | -0.003 |
gif | -0.003 |
Chains | -0.003 |
Token | Phantom |
Token ID | 14407 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
attent | +0.061 |
Rik | +0.044 |
� | +0.041 |
Crash | +0.041 |
Deng | +0.040 |
Neg logit contributions | |
ubs | -0.272 |
ales | -0.262 |
ooth | -0.260 |
gif | -0.252 |
Chains | -0.250 |
Token | now |
Token ID | 783 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
attent | +0.381 |
Rik | +0.345 |
� | +0.338 |
Crash | +0.338 |
Deng | +0.336 |
Neg logit contributions | |
ubs | -0.346 |
ales | -0.325 |
ooth | -0.321 |
gif | -0.302 |
Chains | -0.298 |
Token | seems |
Token ID | 2331 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
attent | +0.070 |
Rik | +0.063 |
� | +0.061 |
Crash | +0.061 |
Deng | +0.061 |
Neg logit contributions | |
ubs | -0.079 |
ales | -0.074 |
ooth | -0.073 |
gif | -0.070 |
Chains | -0.069 |
Token | somehow |
Token ID | 7599 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
attent | +0.061 |
Rik | +0.055 |
� | +0.054 |
Crash | +0.054 |
abled | +0.053 |
Neg logit contributions | |
ubs | -0.056 |
ales | -0.053 |
ooth | -0.052 |
gif | -0.050 |
Chains | -0.049 |
Token | cumbersome |
Token ID | 44491 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
attent | +0.072 |
Rik | +0.065 |
Crash | +0.064 |
� | +0.064 |
abled | +0.063 |
Neg logit contributions | |
ubs | -0.070 |
ales | -0.066 |
ooth | -0.065 |
gif | -0.061 |
Chains | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
attent | +0.044 |
Rik | +0.040 |
� | +0.039 |
Crash | +0.039 |
Deng | +0.039 |
Neg logit contributions | |
ubs | -0.041 |
ales | -0.038 |
ooth | -0.038 |
gif | -0.036 |
Chains | -0.035 |
Token | at |
Token ID | 265 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
attent | +0.103 |
Rik | +0.089 |
� | +0.087 |
Crash | +0.086 |
Deng | +0.086 |
Neg logit contributions | |
ubs | -0.180 |
ales | -0.171 |
ooth | -0.168 |
gif | -0.161 |
ale | -0.160 |
Token | ribe |
Token ID | 4892 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
ubs | +0.014 |
ales | +0.013 |
ooth | +0.013 |
gif | +0.012 |
Chains | +0.012 |
Neg logit contributions | |
attent | -0.016 |
Rik | -0.015 |
� | -0.014 |
Crash | -0.014 |
Deng | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
ubs | +0.021 |
ales | +0.020 |
ooth | +0.020 |
gif | +0.019 |
Chains | +0.019 |
Neg logit contributions | |
attent | -0.023 |
Rik | -0.021 |
� | -0.020 |
Crash | -0.020 |
abled | -0.020 |
Token | Lu |
Token ID | 6026 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
ubs | +0.025 |
ales | +0.023 |
ooth | +0.023 |
gif | +0.022 |
Chains | +0.022 |
Neg logit contributions | |
attent | -0.026 |
Rik | -0.023 |
� | -0.023 |
Crash | -0.023 |
abled | -0.023 |
Token | ol |
Token ID | 349 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
attent | +0.060 |
Rik | +0.054 |
� | +0.053 |
Crash | +0.053 |
Deng | +0.052 |
Neg logit contributions | |
ubs | -0.061 |
ales | -0.057 |
ooth | -0.056 |
gif | -0.053 |
Chains | -0.053 |
Token | Deng |
Token ID | 41985 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
attent | +0.004 |
Rik | +0.002 |
Deng | +0.002 |
� | +0.002 |
Crash | +0.002 |
Neg logit contributions | |
ubs | -0.023 |
ales | -0.022 |
ooth | -0.022 |
gif | -0.021 |
Chains | -0.021 |
Token | as |
Token ID | 355 |
Feature activation | -4.73e-03 |
Pos logit contributions | |
attent | +0.379 |
Rik | +0.343 |
� | +0.336 |
Crash | +0.335 |
abled | +0.333 |
Neg logit contributions | |
ubs | -0.347 |
ales | -0.326 |
ooth | -0.321 |
gif | -0.304 |
Chains | -0.299 |
Token | belonging |
Token ID | 16686 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
attent | +0.003 |
Rik | +0.003 |
� | +0.003 |
Crash | +0.003 |
abled | +0.003 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.003 |
ooth | -0.003 |
gif | -0.003 |
Chains | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +8.31e-03 |
Pos logit contributions | |
ubs | +0.068 |
ales | +0.064 |
ooth | +0.063 |
gif | +0.059 |
Chains | +0.059 |
Neg logit contributions | |
attent | -0.073 |
Rik | -0.066 |
� | -0.064 |
Crash | -0.064 |
Deng | -0.064 |
Token | someone |
Token ID | 2130 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ubs | +0.006 |
ales | +0.006 |
ooth | +0.006 |
gif | +0.005 |
Chains | +0.005 |
Neg logit contributions | |
attent | -0.006 |
Rik | -0.006 |
� | -0.005 |
Crash | -0.005 |
abled | -0.005 |
Token | else |
Token ID | 2073 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ubs | +0.086 |
ales | +0.080 |
ooth | +0.079 |
gif | +0.075 |
Chains | +0.074 |
Neg logit contributions | |
attent | -0.097 |
Rik | -0.088 |
� | -0.086 |
Crash | -0.086 |
Deng | -0.085 |
Token | 18 |
Token ID | 1248 |
Feature activation | -8.58e-03 |
Pos logit contributions | |
ubs | +0.007 |
ales | +0.007 |
ooth | +0.007 |
gif | +0.006 |
Chains | +0.006 |
Neg logit contributions | |
attent | -0.007 |
Rik | -0.006 |
� | -0.006 |
Crash | -0.006 |
Deng | -0.006 |
Token | 75 |
Token ID | 2425 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
attent | +0.006 |
Rik | +0.006 |
� | +0.006 |
Crash | +0.006 |
Deng | +0.006 |
Neg logit contributions | |
ubs | -0.006 |
ales | -0.006 |
ooth | -0.006 |
gif | -0.005 |
Chains | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e-03 |
Pos logit contributions | |
ubs | +0.027 |
ales | +0.025 |
ooth | +0.025 |
gif | +0.024 |
Chains | +0.023 |
Neg logit contributions | |
attent | -0.029 |
Rik | -0.026 |
� | -0.025 |
Crash | -0.025 |
abled | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
abled | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
attent | +0.005 |
Rik | +0.005 |
� | +0.005 |
Deng | +0.005 |
Crash | +0.005 |
Neg logit contributions | |
ubs | -0.005 |
ales | -0.005 |
ooth | -0.005 |
gif | -0.004 |
Chains | -0.004 |
Token | Bird |
Token ID | 42562 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.001 |
ale | +0.001 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
� | -0.002 |
Deng | -0.002 |
Crash | -0.002 |
Token | sey |
Token ID | 4397 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
attent | +0.290 |
Rik | +0.254 |
� | +0.248 |
Crash | +0.247 |
Deng | +0.245 |
Neg logit contributions | |
ubs | -0.430 |
ales | -0.410 |
ooth | -0.405 |
gif | -0.387 |
Chains | -0.383 |
Token | e |
Token ID | 68 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
attent | +0.108 |
Rik | +0.096 |
� | +0.093 |
Crash | +0.093 |
Deng | +0.092 |
Neg logit contributions | |
ubs | -0.139 |
ales | -0.132 |
ooth | -0.131 |
gif | -0.124 |
Chains | -0.123 |
Token | view |
Token ID | 1570 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
attent | +0.078 |
Rik | +0.071 |
� | +0.069 |
Crash | +0.069 |
Deng | +0.069 |
Neg logit contributions | |
ubs | -0.076 |
ales | -0.072 |
ooth | -0.071 |
gif | -0.067 |
Chains | -0.066 |
Token | of |
Token ID | 286 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
attent | +0.028 |
Rik | +0.025 |
� | +0.025 |
Crash | +0.025 |
Leader | +0.025 |
Neg logit contributions | |
ubs | -0.026 |
ales | -0.024 |
ooth | -0.024 |
gif | -0.023 |
Chains | -0.022 |
Token | Brigham |
Token ID | 37434 |
Feature activation | +5.92e-03 |
Pos logit contributions | |
attent | +0.003 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
Deng | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | visit |
Token ID | 3187 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
ubs | +0.101 |
ales | +0.096 |
ooth | +0.095 |
gif | +0.090 |
Chains | +0.089 |
Neg logit contributions | |
attent | -0.091 |
Rik | -0.082 |
� | -0.080 |
Crash | -0.080 |
Deng | -0.079 |
Token | their |
Token ID | 511 |
Feature activation | -6.14e-03 |
Pos logit contributions | |
attent | +0.025 |
Rik | +0.022 |
� | +0.022 |
Crash | +0.022 |
abled | +0.021 |
Neg logit contributions | |
ubs | -0.026 |
ales | -0.024 |
ooth | -0.024 |
gif | -0.023 |
Chains | -0.023 |
Token | website |
Token ID | 3052 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
attent | +0.005 |
Rik | +0.004 |
� | +0.004 |
Crash | +0.004 |
Deng | +0.004 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.004 |
Chains | -0.004 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
ubs | +0.020 |
ales | +0.019 |
ooth | +0.018 |
gif | +0.018 |
Chains | +0.017 |
Neg logit contributions | |
attent | -0.020 |
Rik | -0.018 |
� | -0.018 |
Crash | -0.018 |
abled | -0.018 |
Token | T |
Token ID | 51 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
ubs | +0.009 |
ales | +0.009 |
ooth | +0.009 |
gif | +0.008 |
Chains | +0.008 |
Neg logit contributions | |
attent | -0.010 |
Rik | -0.009 |
� | -0.008 |
Deng | -0.008 |
Crash | -0.008 |
Token | inder |
Token ID | 5540 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
ubs | +0.043 |
ales | +0.040 |
ooth | +0.039 |
gif | +0.037 |
Chains | +0.037 |
Neg logit contributions | |
attent | -0.050 |
Rik | -0.046 |
� | -0.045 |
Crash | -0.045 |
abled | -0.045 |
Token | is |
Token ID | 318 |
Feature activation | -8.96e-03 |
Pos logit contributions | |
ubs | +0.280 |
ales | +0.263 |
ooth | +0.260 |
gif | +0.245 |
Chains | +0.242 |
Neg logit contributions | |
attent | -0.296 |
Rik | -0.268 |
� | -0.262 |
Crash | -0.261 |
Deng | -0.260 |
Token | reportedly |
Token ID | 7478 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
attent | +0.007 |
Rik | +0.006 |
� | +0.006 |
Crash | +0.006 |
Deng | +0.006 |
Neg logit contributions | |
ubs | -0.006 |
ales | -0.006 |
ooth | -0.006 |
gif | -0.006 |
Chains | -0.006 |
Token | sw |
Token ID | 1509 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
ubs | +0.032 |
ales | +0.030 |
ooth | +0.030 |
gif | +0.028 |
Chains | +0.028 |
Neg logit contributions | |
attent | -0.036 |
Rik | -0.032 |
� | -0.032 |
Crash | -0.032 |
Deng | -0.031 |
Token | iping |
Token ID | 34690 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
ubs | +0.099 |
ales | +0.094 |
ooth | +0.093 |
gif | +0.088 |
Chains | +0.087 |
Neg logit contributions | |
attent | -0.085 |
Rik | -0.076 |
� | -0.074 |
Crash | -0.073 |
Deng | -0.073 |
Token | left |
Token ID | 1364 |
Feature activation | -8.29e-03 |
Pos logit contributions | |
ubs | +0.113 |
ales | +0.106 |
ooth | +0.104 |
gif | +0.097 |
Chains | +0.097 |
Neg logit contributions | |
attent | -0.134 |
Rik | -0.122 |
� | -0.119 |
Leader | -0.119 |
Deng | -0.119 |
Token | � |
Token ID | 6184 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
attent | +0.030 |
Rik | +0.027 |
� | +0.027 |
Crash | +0.027 |
abled | +0.026 |
Neg logit contributions | |
ubs | -0.030 |
ales | -0.028 |
ooth | -0.028 |
gif | -0.026 |
Chains | -0.026 |
Token | � |
Token ID | 229 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ubs | +0.073 |
ales | +0.069 |
ooth | +0.068 |
gif | +0.065 |
Chains | +0.065 |
Neg logit contributions | |
attent | -0.060 |
Rik | -0.053 |
� | -0.052 |
Leader | -0.051 |
Crash | -0.051 |
Token | an |
Token ID | 272 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
attent | +0.169 |
Rik | +0.152 |
� | +0.149 |
Crash | +0.148 |
abled | +0.147 |
Neg logit contributions | |
ubs | -0.179 |
ales | -0.168 |
ooth | -0.167 |
gif | -0.158 |
Chains | -0.156 |
Token | ak |
Token ID | 461 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
attent | +0.094 |
Rik | +0.084 |
� | +0.083 |
Crash | +0.082 |
Deng | +0.082 |
Neg logit contributions | |
ubs | -0.096 |
ales | -0.090 |
ooth | -0.089 |
gif | -0.084 |
Chains | -0.083 |
Token | k |
Token ID | 74 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
attent | +0.072 |
Rik | +0.065 |
� | +0.064 |
Crash | +0.063 |
Deng | +0.063 |
Neg logit contributions | |
ubs | -0.065 |
ales | -0.061 |
ooth | -0.060 |
gif | -0.057 |
Chains | -0.056 |
Token | ale |
Token ID | 1000 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
ubs | +0.033 |
ales | +0.031 |
ooth | +0.030 |
gif | +0.028 |
Chains | +0.028 |
Neg logit contributions | |
attent | -0.050 |
Rik | -0.046 |
� | -0.045 |
Crash | -0.045 |
Leader | -0.045 |
Token | lies |
Token ID | 7363 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
ubs | +0.363 |
ales | +0.343 |
ooth | +0.337 |
gif | +0.318 |
Chains | +0.315 |
Neg logit contributions | |
attent | -0.379 |
Rik | -0.342 |
Crash | -0.334 |
� | -0.334 |
Deng | -0.332 |
Token | the |
Token ID | 262 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
ubs | +0.035 |
ales | +0.033 |
ooth | +0.032 |
gif | +0.031 |
Chains | +0.030 |
Neg logit contributions | |
attent | -0.036 |
Rik | -0.033 |
� | -0.032 |
Crash | -0.032 |
abled | -0.032 |
Token | site |
Token ID | 2524 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
attent | +0.001 |
Rik | +0.001 |
� | +0.001 |
Crash | +0.001 |
Deng | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
Chains | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | +4.62e-03 |
Pos logit contributions | |
ubs | +0.020 |
ales | +0.019 |
ooth | +0.018 |
gif | +0.017 |
Chains | +0.017 |
Neg logit contributions | |
attent | -0.021 |
Rik | -0.019 |
� | -0.019 |
Crash | -0.019 |
Deng | -0.019 |
Token | ancient |
Token ID | 6156 |
Feature activation | +5.51e-03 |
Pos logit contributions | |
ubs | +0.003 |
ales | +0.003 |
ooth | +0.003 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.003 |
Rik | -0.003 |
� | -0.003 |
Crash | -0.003 |
abled | -0.003 |
Token | areas |
Token ID | 3006 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ubs | +0.180 |
ales | +0.169 |
ooth | +0.167 |
gif | +0.157 |
Chains | +0.155 |
Neg logit contributions | |
attent | -0.198 |
Rik | -0.179 |
� | -0.175 |
Crash | -0.175 |
Deng | -0.174 |
Token | ( |
Token ID | 357 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
ubs | +0.130 |
ales | +0.122 |
ooth | +0.121 |
gif | +0.114 |
Chains | +0.113 |
Neg logit contributions | |
attent | -0.135 |
Rik | -0.122 |
� | -0.120 |
Crash | -0.119 |
Deng | -0.119 |
Token | we |
Token ID | 732 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
ubs | +0.042 |
ales | +0.040 |
ooth | +0.039 |
gif | +0.037 |
Chains | +0.037 |
Neg logit contributions | |
attent | -0.038 |
Rik | -0.034 |
� | -0.033 |
Crash | -0.033 |
Deng | -0.033 |
Token | have |
Token ID | 423 |
Feature activation | +3.11e-04 |
Pos logit contributions | |
ubs | +0.051 |
ales | +0.048 |
ooth | +0.047 |
gif | +0.044 |
Chains | +0.044 |
Neg logit contributions | |
attent | -0.059 |
Rik | -0.053 |
� | -0.052 |
Crash | -0.052 |
Deng | -0.052 |
Token | 30 |
Token ID | 1542 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
ubs | +0.000 |
ales | +0.000 |
ooth | +0.000 |
gif | +0.000 |
ammy | +0.000 |
Neg logit contributions | |
attent | -0.000 |
Rik | -0.000 |
� | -0.000 |
Crash | -0.000 |
Deng | -0.000 |
Token | trucks |
Token ID | 13960 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
attent | +0.058 |
Rik | +0.053 |
� | +0.052 |
Crash | +0.051 |
Leader | +0.051 |
Neg logit contributions | |
ubs | -0.046 |
ales | -0.043 |
ooth | -0.042 |
gif | -0.040 |
ammy | -0.039 |
Token | & |
Token ID | 1222 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ubs | +0.193 |
ales | +0.182 |
ooth | +0.179 |
gif | +0.169 |
Chains | +0.167 |
Neg logit contributions | |
attent | -0.203 |
Rik | -0.184 |
� | -0.180 |
Crash | -0.179 |
Deng | -0.178 |
Token | 40 |
Token ID | 2319 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
attent | +0.136 |
Rik | +0.122 |
� | +0.120 |
Crash | +0.119 |
Deng | +0.119 |
Neg logit contributions | |
ubs | -0.128 |
ales | -0.120 |
ooth | -0.119 |
gif | -0.111 |
Chains | -0.110 |
Token | pl |
Token ID | 458 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
attent | +0.078 |
Rik | +0.071 |
� | +0.070 |
Crash | +0.070 |
Leader | +0.069 |
Neg logit contributions | |
ubs | -0.059 |
ales | -0.055 |
ooth | -0.055 |
gif | -0.051 |
Chains | -0.050 |
Token | ows |
Token ID | 1666 |
Feature activation | +7.83e-02 |
Pos logit contributions | |
attent | +0.019 |
Rik | +0.018 |
� | +0.017 |
Crash | +0.017 |
abled | +0.017 |
Neg logit contributions | |
ubs | -0.014 |
ales | -0.013 |
ooth | -0.013 |
gif | -0.012 |
Chains | -0.012 |
Token | in |
Token ID | 287 |
Feature activation | +8.82e-03 |
Pos logit contributions | |
ubs | +0.057 |
ales | +0.054 |
ooth | +0.053 |
gif | +0.050 |
Chains | +0.050 |
Neg logit contributions | |
attent | -0.059 |
Rik | -0.053 |
� | -0.052 |
Crash | -0.052 |
Deng | -0.051 |
Token | o |
Token ID | 78 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
ubs | +0.165 |
ales | +0.154 |
ooth | +0.152 |
gif | +0.143 |
Chains | +0.141 |
Neg logit contributions | |
attent | -0.204 |
Rik | -0.186 |
� | -0.182 |
Crash | -0.182 |
Deng | -0.181 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-03 |
Pos logit contributions | |
ubs | +0.054 |
ales | +0.051 |
ooth | +0.051 |
gif | +0.048 |
Chains | +0.047 |
Neg logit contributions | |
attent | -0.056 |
Rik | -0.050 |
� | -0.049 |
Crash | -0.049 |
Deng | -0.049 |
Token | meant |
Token ID | 4001 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
Deng | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | -3.43e-03 |
Pos logit contributions | |
attent | +0.029 |
Rik | +0.026 |
� | +0.026 |
Crash | +0.026 |
Deng | +0.026 |
Neg logit contributions | |
ubs | -0.028 |
ales | -0.026 |
ooth | -0.026 |
gif | -0.024 |
Chains | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -3.03e-04 |
Pos logit contributions | |
attent | +0.003 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
Deng | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | asteroid |
Token ID | 27460 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
attent | +0.000 |
Rik | +0.000 |
� | +0.000 |
Crash | +0.000 |
Deng | +0.000 |
Neg logit contributions | |
ubs | -0.000 |
ales | -0.000 |
ooth | -0.000 |
gif | -0.000 |
Chains | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
ubs | +0.208 |
ales | +0.195 |
ooth | +0.193 |
gif | +0.181 |
ammy | +0.180 |
Neg logit contributions | |
attent | -0.225 |
Rik | -0.203 |
Crash | -0.198 |
� | -0.198 |
Leader | -0.197 |
Token | not |
Token ID | 407 |
Feature activation | -5.16e-03 |
Pos logit contributions | |
ubs | +0.012 |
ales | +0.011 |
ooth | +0.011 |
gif | +0.010 |
Chains | +0.010 |
Neg logit contributions | |
attent | -0.013 |
Rik | -0.012 |
� | -0.012 |
Crash | -0.012 |
Deng | -0.011 |
Token | bright |
Token ID | 6016 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
attent | +0.004 |
Rik | +0.004 |
Crash | +0.003 |
� | +0.003 |
Deng | +0.003 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.003 |
ooth | -0.003 |
gif | -0.003 |
Chains | -0.003 |
Token | enough |
Token ID | 1576 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ubs | +0.014 |
ales | +0.013 |
ooth | +0.013 |
gif | +0.012 |
Chains | +0.012 |
Neg logit contributions | |
attent | -0.024 |
Rik | -0.022 |
� | -0.022 |
Crash | -0.022 |
abled | -0.022 |
Token | for |
Token ID | 329 |
Feature activation | +6.50e-03 |
Pos logit contributions | |
ubs | +0.115 |
ales | +0.108 |
ooth | +0.107 |
gif | +0.101 |
Chains | +0.100 |
Neg logit contributions | |
attent | -0.119 |
Rik | -0.108 |
� | -0.105 |
Crash | -0.105 |
Leader | -0.104 |
Token | into |
Token ID | 656 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
ubs | +0.083 |
ales | +0.078 |
ooth | +0.077 |
gif | +0.072 |
Chains | +0.071 |
Neg logit contributions | |
attent | -0.092 |
Rik | -0.083 |
� | -0.082 |
Crash | -0.082 |
Deng | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
ubs | +0.010 |
ales | +0.009 |
ooth | +0.009 |
gif | +0.009 |
Chains | +0.008 |
Neg logit contributions | |
attent | -0.010 |
Rik | -0.009 |
� | -0.009 |
Crash | -0.009 |
Deng | -0.009 |
Token | per |
Token ID | 583 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
attent | +0.012 |
Rik | +0.011 |
� | +0.011 |
Crash | +0.011 |
abled | +0.011 |
Neg logit contributions | |
ubs | -0.012 |
ales | -0.011 |
ooth | -0.011 |
gif | -0.010 |
Chains | -0.010 |
Token | ov |
Token ID | 709 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
attent | +0.055 |
Rik | +0.049 |
� | +0.048 |
Crash | +0.048 |
Leader | +0.047 |
Neg logit contributions | |
ubs | -0.068 |
ales | -0.065 |
ooth | -0.064 |
gif | -0.061 |
Chains | -0.060 |
Token | sk |
Token ID | 8135 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
attent | +0.046 |
Rik | +0.038 |
� | +0.037 |
Crash | +0.037 |
Deng | +0.036 |
Neg logit contributions | |
ubs | -0.107 |
ales | -0.103 |
ooth | -0.102 |
gif | -0.098 |
ale | -0.097 |
Token | ite |
Token ID | 578 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
attent | +0.282 |
Rik | +0.264 |
� | +0.260 |
Crash | +0.260 |
Leader | +0.259 |
Neg logit contributions | |
ubs | -0.079 |
ales | -0.068 |
ooth | -0.066 |
gif | -0.057 |
Chains | -0.056 |
Token | - |
Token ID | 12 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
ubs | +0.238 |
ales | +0.224 |
ooth | +0.222 |
gif | +0.209 |
Chains | +0.207 |
Neg logit contributions | |
attent | -0.246 |
Rik | -0.222 |
� | -0.218 |
Crash | -0.217 |
Deng | -0.215 |
Token | f |
Token ID | 69 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
attent | +0.012 |
Rik | +0.011 |
� | +0.011 |
Crash | +0.011 |
Leader | +0.011 |
Neg logit contributions | |
ubs | -0.017 |
ales | -0.016 |
ooth | -0.016 |
gif | -0.015 |
ale | -0.015 |
Token | lled |
Token ID | 3353 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
attent | +0.017 |
Rik | +0.015 |
� | +0.015 |
Crash | +0.015 |
abled | +0.015 |
Neg logit contributions | |
ubs | -0.017 |
ales | -0.016 |
ooth | -0.015 |
gif | -0.015 |
Chains | -0.014 |
Token | center |
Token ID | 3641 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
ubs | +0.228 |
ales | +0.215 |
ooth | +0.213 |
gif | +0.202 |
Chains | +0.199 |
Neg logit contributions | |
attent | -0.216 |
Rik | -0.195 |
� | -0.192 |
Crash | -0.191 |
abled | -0.189 |
Token | of |
Token ID | 286 |
Feature activation | -4.99e-03 |
Pos logit contributions | |
attent | +0.034 |
Rik | +0.031 |
� | +0.030 |
Crash | +0.030 |
Deng | +0.030 |
Neg logit contributions | |
ubs | -0.033 |
ales | -0.031 |
ooth | -0.031 |
gif | -0.029 |
Chains | -0.029 |
Token | 't |
Token ID | 470 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ubs | +0.016 |
ales | +0.015 |
ooth | +0.015 |
gif | +0.014 |
Chains | +0.014 |
Neg logit contributions | |
attent | -0.011 |
Rik | -0.010 |
� | -0.010 |
Crash | -0.010 |
Deng | -0.010 |
Token | going |
Token ID | 1016 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
attent | +0.094 |
Rik | +0.085 |
� | +0.083 |
Crash | +0.083 |
Deng | +0.082 |
Neg logit contributions | |
ubs | -0.089 |
ales | -0.084 |
ooth | -0.083 |
gif | -0.078 |
Chains | -0.077 |
Token | to |
Token ID | 284 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
attent | +0.021 |
Rik | +0.019 |
� | +0.018 |
Crash | +0.018 |
Leader | +0.018 |
Neg logit contributions | |
ubs | -0.020 |
ales | -0.019 |
ooth | -0.019 |
gif | -0.017 |
Chains | -0.017 |
Token | last |
Token ID | 938 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
attent | +0.009 |
Rik | +0.008 |
� | +0.008 |
Crash | +0.008 |
Deng | +0.008 |
Neg logit contributions | |
ubs | -0.008 |
ales | -0.008 |
ooth | -0.008 |
gif | -0.007 |
Chains | -0.007 |
Token | more |
Token ID | 517 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
attent | +0.075 |
Rik | +0.068 |
� | +0.066 |
Crash | +0.066 |
Deng | +0.066 |
Neg logit contributions | |
ubs | -0.068 |
ales | -0.064 |
ooth | -0.063 |
gif | -0.059 |
Chains | -0.059 |
Token | than |
Token ID | 621 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
ubs | +0.031 |
ales | +0.029 |
ooth | +0.029 |
gif | +0.027 |
Chains | +0.027 |
Neg logit contributions | |
attent | -0.043 |
Rik | -0.039 |
� | -0.038 |
Deng | -0.038 |
Crash | -0.038 |
Token | three |
Token ID | 1115 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
ubs | +0.050 |
ales | +0.047 |
ooth | +0.046 |
gif | +0.044 |
Chains | +0.043 |
Neg logit contributions | |
attent | -0.056 |
Rik | -0.050 |
� | -0.049 |
Crash | -0.049 |
abled | -0.049 |
Token | days |
Token ID | 1528 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
attent | +0.019 |
Rik | +0.017 |
� | +0.017 |
Crash | +0.017 |
Deng | +0.017 |
Neg logit contributions | |
ubs | -0.018 |
ales | -0.017 |
ooth | -0.017 |
gif | -0.016 |
Chains | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
ubs | +0.009 |
ales | +0.009 |
ooth | +0.008 |
gif | +0.008 |
Chains | +0.008 |
Neg logit contributions | |
attent | -0.010 |
Rik | -0.009 |
� | -0.009 |
Crash | -0.009 |
Deng | -0.009 |
Token | I |
Token ID | 314 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
attent | +0.010 |
Rik | +0.009 |
� | +0.009 |
Crash | +0.009 |
abled | +0.009 |
Neg logit contributions | |
ubs | -0.009 |
ales | -0.008 |
ooth | -0.008 |
gif | -0.008 |
Chains | -0.008 |
Token | got |
Token ID | 1392 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ubs | +0.022 |
ales | +0.021 |
ooth | +0.021 |
gif | +0.019 |
Chains | +0.019 |
Neg logit contributions | |
attent | -0.024 |
Rik | -0.022 |
� | -0.022 |
Crash | -0.022 |
Deng | -0.022 |
Token | own |
Token ID | 898 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
attent | +0.110 |
Rik | +0.100 |
� | +0.098 |
Crash | +0.098 |
Deng | +0.097 |
Neg logit contributions | |
ubs | -0.098 |
ales | -0.092 |
ooth | -0.090 |
gif | -0.085 |
Chains | -0.084 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e-03 |
Pos logit contributions | |
attent | +0.057 |
Rik | +0.051 |
� | +0.050 |
Crash | +0.050 |
Deng | +0.050 |
Neg logit contributions | |
ubs | -0.054 |
ales | -0.051 |
ooth | -0.050 |
gif | -0.047 |
Chains | -0.047 |
Token | fund |
Token ID | 1814 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
Deng | -0.001 |
Token | secondary |
Token ID | 9233 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
attent | +0.074 |
Rik | +0.066 |
� | +0.065 |
Crash | +0.065 |
Deng | +0.064 |
Neg logit contributions | |
ubs | -0.070 |
ales | -0.065 |
ooth | -0.065 |
gif | -0.061 |
Chains | -0.060 |
Token | teams |
Token ID | 3466 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ubs | +0.112 |
ales | +0.105 |
ooth | +0.104 |
gif | +0.099 |
Chains | +0.097 |
Neg logit contributions | |
attent | -0.113 |
Rik | -0.102 |
� | -0.101 |
Crash | -0.100 |
Deng | -0.099 |
Token | ( |
Token ID | 357 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
attent | +0.110 |
Rik | +0.100 |
� | +0.098 |
Crash | +0.098 |
Deng | +0.097 |
Neg logit contributions | |
ubs | -0.101 |
ales | -0.095 |
ooth | -0.093 |
gif | -0.088 |
Chains | -0.087 |
Token | a |
Token ID | 64 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ubs | +0.034 |
ales | +0.032 |
ooth | +0.032 |
gif | +0.030 |
ale | +0.030 |
Neg logit contributions | |
attent | -0.030 |
Rik | -0.027 |
� | -0.026 |
Deng | -0.026 |
Crash | -0.026 |
Token | la |
Token ID | 8591 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
attent | +0.084 |
Rik | +0.076 |
� | +0.074 |
Crash | +0.074 |
Deng | +0.073 |
Neg logit contributions | |
ubs | -0.080 |
ales | -0.075 |
ooth | -0.074 |
gif | -0.070 |
Chains | -0.069 |
Token | Toro |
Token ID | 42952 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
attent | +0.239 |
Rik | +0.213 |
� | +0.210 |
Crash | +0.209 |
abled | +0.208 |
Neg logit contributions | |
ubs | -0.249 |
ales | -0.234 |
ooth | -0.230 |
gif | -0.219 |
Chains | -0.217 |
Token | Ros |
Token ID | 10018 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
attent | +0.082 |
Rik | +0.071 |
� | +0.068 |
Crash | +0.068 |
Deng | +0.068 |
Neg logit contributions | |
ubs | -0.154 |
ales | -0.147 |
ooth | -0.146 |
gif | -0.139 |
Chains | -0.138 |
Token | so |
Token ID | 568 |
Feature activation | +5.99e-03 |
Pos logit contributions | |
attent | +0.152 |
Rik | +0.138 |
� | +0.136 |
Crash | +0.136 |
abled | +0.134 |
Neg logit contributions | |
ubs | -0.133 |
ales | -0.128 |
ooth | -0.124 |
gif | -0.116 |
ale | -0.116 |
Token | likely |
Token ID | 1884 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
attent | +0.004 |
Rik | +0.004 |
� | +0.004 |
Crash | +0.004 |
abled | +0.004 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.003 |
Chains | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
attent | +0.057 |
Rik | +0.052 |
� | +0.051 |
Crash | +0.051 |
Deng | +0.051 |
Neg logit contributions | |
ubs | -0.053 |
ales | -0.050 |
ooth | -0.049 |
gif | -0.046 |
Chains | -0.046 |
Token | be |
Token ID | 307 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
ubs | +0.011 |
ales | +0.010 |
ooth | +0.010 |
gif | +0.009 |
Chains | +0.009 |
Neg logit contributions | |
attent | -0.013 |
Rik | -0.012 |
� | -0.012 |
Crash | -0.012 |
Leader | -0.012 |
Token | some |
Token ID | 617 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
ubs | +0.036 |
ales | +0.034 |
ooth | +0.034 |
gif | +0.032 |
Chains | +0.031 |
Neg logit contributions | |
attent | -0.040 |
Rik | -0.036 |
� | -0.035 |
Crash | -0.035 |
abled | -0.035 |
Token | consequences |
Token ID | 6948 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
ubs | +0.045 |
ales | +0.043 |
ooth | +0.042 |
gif | +0.040 |
Chains | +0.039 |
Neg logit contributions | |
attent | -0.047 |
Rik | -0.043 |
Crash | -0.042 |
� | -0.042 |
abled | -0.041 |
Token | for |
Token ID | 329 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ubs | +0.195 |
ales | +0.183 |
ooth | +0.181 |
gif | +0.171 |
Chains | +0.169 |
Neg logit contributions | |
attent | -0.209 |
Rik | -0.190 |
� | -0.186 |
Crash | -0.186 |
abled | -0.184 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ubs | +0.009 |
ales | +0.008 |
ooth | +0.008 |
gif | +0.008 |
Chains | +0.008 |
Neg logit contributions | |
attent | -0.010 |
Rik | -0.009 |
� | -0.009 |
Crash | -0.008 |
Leader | -0.008 |
Token | housing |
Token ID | 5627 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
ubs | +0.008 |
ales | +0.008 |
ooth | +0.008 |
gif | +0.007 |
Chains | +0.007 |
Neg logit contributions | |
attent | -0.009 |
Rik | -0.008 |
� | -0.008 |
Leader | -0.008 |
Crash | -0.008 |
Token | market |
Token ID | 1910 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
ubs | +0.036 |
ales | +0.034 |
ooth | +0.033 |
gif | +0.031 |
Chains | +0.031 |
Neg logit contributions | |
attent | -0.033 |
Rik | -0.030 |
� | -0.029 |
Crash | -0.029 |
Deng | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
attent | +0.037 |
Rik | +0.033 |
� | +0.032 |
Crash | +0.032 |
Deng | +0.032 |
Neg logit contributions | |
ubs | -0.035 |
ales | -0.033 |
ooth | -0.033 |
gif | -0.031 |
Chains | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +9.97e-03 |
Pos logit contributions | |
ubs | +0.015 |
ales | +0.014 |
ooth | +0.014 |
gif | +0.013 |
Chains | +0.013 |
Neg logit contributions | |
attent | -0.016 |
Rik | -0.014 |
� | -0.014 |
Crash | -0.014 |
Leader | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.57e-04 |
Pos logit contributions | |
ubs | +0.038 |
ales | +0.036 |
ooth | +0.035 |
gif | +0.033 |
Chains | +0.033 |
Neg logit contributions | |
attent | -0.039 |
Rik | -0.035 |
� | -0.035 |
Crash | -0.034 |
abled | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +2.44e-03 |
Pos logit contributions | |
attent | +0.000 |
Rik | +0.000 |
� | +0.000 |
Crash | +0.000 |
Deng | +0.000 |
Neg logit contributions | |
ubs | -0.000 |
ales | -0.000 |
ooth | -0.000 |
gif | -0.000 |
Chains | -0.000 |
Token | Having |
Token ID | 14698 |
Feature activation | +6.63e-03 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.002 |
Chains | +0.002 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
Deng | -0.002 |
� | -0.002 |
Leader | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +1.74e-03 |
Pos logit contributions | |
ubs | +0.005 |
ales | +0.004 |
ooth | +0.004 |
gif | +0.004 |
Chains | +0.004 |
Neg logit contributions | |
attent | -0.005 |
Rik | -0.005 |
� | -0.004 |
Crash | -0.004 |
Deng | -0.004 |
Token | large |
Token ID | 1588 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
Deng | -0.001 |
Token | national |
Token ID | 2260 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
attent | +0.014 |
Rik | +0.013 |
� | +0.013 |
Crash | +0.013 |
Deng | +0.012 |
Neg logit contributions | |
ubs | -0.013 |
ales | -0.012 |
ooth | -0.012 |
gif | -0.011 |
Chains | -0.011 |
Token | debt |
Token ID | 5057 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
ubs | +0.055 |
ales | +0.052 |
ooth | +0.051 |
gif | +0.048 |
Chains | +0.047 |
Neg logit contributions | |
attent | -0.066 |
Rik | -0.060 |
� | -0.059 |
Crash | -0.059 |
Deng | -0.058 |
Token | doesn |
Token ID | 1595 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
ubs | +0.018 |
ales | +0.017 |
ooth | +0.017 |
gif | +0.016 |
Chains | +0.016 |
Neg logit contributions | |
attent | -0.020 |
Rik | -0.018 |
� | -0.018 |
Crash | -0.017 |
Deng | -0.017 |
Token | � |
Token ID | 447 |
Feature activation | +1.89e-03 |
Pos logit contributions | |
ubs | +0.064 |
ales | +0.061 |
ooth | +0.060 |
gif | +0.057 |
Chains | +0.057 |
Neg logit contributions | |
attent | -0.046 |
Rik | -0.041 |
� | -0.040 |
Crash | -0.040 |
abled | -0.039 |
Token | � |
Token ID | 247 |
Feature activation | +4.72e-03 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
Deng | -0.001 |
Token | t |
Token ID | 83 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
ubs | +0.003 |
ales | +0.003 |
ooth | +0.003 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.004 |
Rik | -0.004 |
� | -0.004 |
Crash | -0.004 |
Deng | -0.004 |
Token | when |
Token ID | 618 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
attent | +0.029 |
Rik | +0.026 |
Deng | +0.026 |
Leader | +0.026 |
� | +0.026 |
Neg logit contributions | |
ubs | -0.028 |
ales | -0.026 |
ooth | -0.026 |
gif | -0.024 |
ammy | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | -6.68e-03 |
Pos logit contributions | |
attent | +0.125 |
Rik | +0.112 |
Deng | +0.109 |
Leader | +0.109 |
� | +0.109 |
Neg logit contributions | |
ubs | -0.117 |
ales | -0.110 |
ooth | -0.109 |
gif | -0.102 |
ammy | -0.101 |
Token | candidate |
Token ID | 4540 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
attent | +0.006 |
Rik | +0.005 |
Leader | +0.005 |
� | +0.005 |
Deng | +0.005 |
Neg logit contributions | |
ubs | -0.004 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.004 |
Chains | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
ubs | +0.047 |
ales | +0.044 |
ooth | +0.044 |
gif | +0.041 |
ammy | +0.041 |
Neg logit contributions | |
attent | -0.049 |
Rik | -0.044 |
� | -0.043 |
Deng | -0.043 |
Leader | -0.043 |
Token | online |
Token ID | 2691 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
ubs | +0.038 |
ales | +0.036 |
ooth | +0.035 |
gif | +0.033 |
Chains | +0.033 |
Neg logit contributions | |
attent | -0.041 |
Rik | -0.037 |
Leader | -0.036 |
� | -0.036 |
Deng | -0.036 |
Token | persona |
Token ID | 27822 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
ubs | +0.102 |
ales | +0.096 |
ooth | +0.095 |
gif | +0.090 |
Chains | +0.089 |
Neg logit contributions | |
attent | -0.107 |
Rik | -0.096 |
� | -0.094 |
Crash | -0.094 |
Leader | -0.093 |
Token | is |
Token ID | 318 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
ubs | +0.055 |
ales | +0.052 |
ooth | +0.051 |
gif | +0.048 |
Chains | +0.048 |
Neg logit contributions | |
attent | -0.061 |
Rik | -0.055 |
� | -0.054 |
Crash | -0.053 |
Deng | -0.053 |
Token | so |
Token ID | 523 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
attent | +0.023 |
Rik | +0.020 |
� | +0.020 |
Crash | +0.020 |
Deng | +0.020 |
Neg logit contributions | |
ubs | -0.021 |
ales | -0.019 |
ooth | -0.019 |
gif | -0.018 |
Chains | -0.018 |
Token | vastly |
Token ID | 22056 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ubs | +0.055 |
ales | +0.052 |
ooth | +0.051 |
gif | +0.048 |
Chains | +0.048 |
Neg logit contributions | |
attent | -0.057 |
Rik | -0.052 |
� | -0.051 |
Crash | -0.050 |
Deng | -0.050 |
Token | different |
Token ID | 1180 |
Feature activation | -9.45e-02 |
Pos logit contributions | |
attent | +0.074 |
Rik | +0.066 |
� | +0.064 |
Crash | +0.064 |
Deng | +0.064 |
Neg logit contributions | |
ubs | -0.090 |
ales | -0.085 |
ooth | -0.084 |
gif | -0.080 |
Chains | -0.079 |
Token | from |
Token ID | 422 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
attent | +0.072 |
Rik | +0.065 |
� | +0.064 |
Crash | +0.064 |
Deng | +0.064 |
Neg logit contributions | |
ubs | -0.067 |
ales | -0.063 |
ooth | -0.062 |
gif | -0.059 |
Chains | -0.058 |
Token | eligible |
Token ID | 8867 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ubs | +0.024 |
ales | +0.023 |
ooth | +0.023 |
uncture | +0.022 |
Chains | +0.022 |
Neg logit contributions | |
attent | -0.026 |
Rik | -0.024 |
Leader | -0.023 |
abled | -0.023 |
Deng | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | +5.32e-03 |
Pos logit contributions | |
ubs | +0.159 |
ales | +0.150 |
ooth | +0.148 |
gif | +0.140 |
Chains | +0.139 |
Neg logit contributions | |
attent | -0.164 |
Rik | -0.148 |
� | -0.145 |
Crash | -0.144 |
abled | -0.144 |
Token | food |
Token ID | 2057 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
ubs | +0.004 |
ales | +0.004 |
ooth | +0.004 |
gif | +0.004 |
Chains | +0.004 |
Neg logit contributions | |
attent | -0.004 |
Rik | -0.003 |
� | -0.003 |
Crash | -0.003 |
Leader | -0.003 |
Token | stamps |
Token ID | 25560 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
ubs | +0.058 |
ales | +0.055 |
ooth | +0.055 |
ammy | +0.051 |
gif | +0.051 |
Neg logit contributions | |
attent | -0.047 |
Rik | -0.041 |
� | -0.040 |
Crash | -0.040 |
Leader | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +5.11e-03 |
Pos logit contributions | |
attent | +0.042 |
Rik | +0.037 |
abled | +0.036 |
Leader | +0.036 |
Crash | +0.036 |
Neg logit contributions | |
ubs | -0.038 |
ales | -0.035 |
ooth | -0.035 |
Chains | -0.033 |
uncture | -0.033 |
Token | Medicaid |
Token ID | 13594 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
ubs | +0.004 |
ales | +0.003 |
ooth | +0.003 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.004 |
Rik | -0.004 |
� | -0.003 |
Crash | -0.003 |
Deng | -0.003 |
Token | receive |
Token ID | 3328 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
attent | +0.042 |
Rik | +0.038 |
Leader | +0.037 |
Crash | +0.037 |
� | +0.037 |
Neg logit contributions | |
ubs | -0.037 |
ales | -0.035 |
ooth | -0.034 |
uncture | -0.032 |
gif | -0.032 |
Token | cell |
Token ID | 2685 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
ubs | +0.075 |
ales | +0.071 |
ooth | +0.070 |
gif | +0.066 |
Chains | +0.065 |
Neg logit contributions | |
attent | -0.069 |
Rik | -0.061 |
� | -0.060 |
Crash | -0.060 |
Leader | -0.060 |
Token | phone |
Token ID | 3072 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
attent | +0.072 |
Rik | +0.066 |
� | +0.064 |
Crash | +0.064 |
Leader | +0.064 |
Neg logit contributions | |
ubs | -0.058 |
ales | -0.054 |
ooth | -0.053 |
gif | -0.050 |
Chains | -0.050 |
Token | subsidies |
Token ID | 16230 |
Feature activation | -2.43e-03 |
Pos logit contributions | |
ubs | +0.043 |
ales | +0.040 |
ooth | +0.040 |
gif | +0.037 |
Chains | +0.037 |
Neg logit contributions | |
attent | -0.048 |
Rik | -0.043 |
� | -0.042 |
Crash | -0.042 |
Leader | -0.042 |
Token | through |
Token ID | 832 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
attent | +0.002 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
Deng | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
ubs | +0.047 |
ales | +0.044 |
ooth | +0.044 |
gif | +0.041 |
Chains | +0.041 |
Neg logit contributions | |
attent | -0.051 |
Rik | -0.046 |
� | -0.045 |
Crash | -0.045 |
Deng | -0.045 |
Token | only |
Token ID | 691 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
attent | +0.014 |
Rik | +0.012 |
� | +0.012 |
Crash | +0.012 |
Deng | +0.012 |
Neg logit contributions | |
ubs | -0.012 |
ales | -0.011 |
ooth | -0.011 |
gif | -0.010 |
Chains | -0.010 |
Token | previous |
Token ID | 2180 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
ubs | +0.029 |
ales | +0.027 |
ooth | +0.027 |
gif | +0.025 |
Chains | +0.025 |
Neg logit contributions | |
attent | -0.033 |
Rik | -0.030 |
� | -0.029 |
Crash | -0.029 |
Deng | -0.029 |
Token | pictures |
Token ID | 5986 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
ubs | +0.007 |
ales | +0.007 |
ooth | +0.007 |
gif | +0.006 |
Chains | +0.006 |
Neg logit contributions | |
attent | -0.009 |
Rik | -0.008 |
� | -0.008 |
Crash | -0.008 |
Deng | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ubs | +0.069 |
ales | +0.065 |
ooth | +0.064 |
gif | +0.061 |
Chains | +0.060 |
Neg logit contributions | |
attent | -0.074 |
Rik | -0.067 |
� | -0.065 |
Crash | -0.065 |
Deng | -0.065 |
Token | of |
Token ID | 286 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
attent | +0.011 |
Rik | +0.010 |
� | +0.010 |
Crash | +0.010 |
Deng | +0.009 |
Neg logit contributions | |
ubs | -0.010 |
ales | -0.009 |
ooth | -0.009 |
gif | -0.009 |
Chains | -0.009 |
Token | Hal |
Token ID | 11023 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
attent | +0.013 |
Rik | +0.012 |
� | +0.011 |
Crash | +0.011 |
Deng | +0.011 |
Neg logit contributions | |
ubs | -0.012 |
ales | -0.011 |
ooth | -0.011 |
gif | -0.011 |
Chains | -0.011 |
Token | ley |
Token ID | 1636 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
ubs | +0.022 |
ales | +0.021 |
ooth | +0.020 |
gif | +0.019 |
Chains | +0.019 |
Neg logit contributions | |
attent | -0.018 |
Rik | -0.016 |
� | -0.016 |
Crash | -0.016 |
Deng | -0.015 |
Token | 's |
Token ID | 338 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
attent | +0.066 |
Rik | +0.060 |
Crash | +0.059 |
� | +0.059 |
Leader | +0.058 |
Neg logit contributions | |
ubs | -0.054 |
ales | -0.050 |
ooth | -0.050 |
gif | -0.046 |
ammy | -0.046 |
Token | Comet |
Token ID | 36238 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ubs | +0.044 |
ales | +0.041 |
ooth | +0.041 |
gif | +0.039 |
uncture | +0.039 |
Neg logit contributions | |
attent | -0.031 |
Rik | -0.027 |
Crash | -0.027 |
� | -0.027 |
Leader | -0.026 |
Token | taken |
Token ID | 2077 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
attent | +0.077 |
Rik | +0.069 |
Leader | +0.068 |
Crash | +0.068 |
Deng | +0.067 |
Neg logit contributions | |
ubs | -0.075 |
ales | -0.070 |
ooth | -0.069 |
gif | -0.065 |
ammy | -0.065 |
Token | Not |
Token ID | 1892 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
ubs | +0.005 |
ales | +0.005 |
ooth | +0.005 |
gif | +0.004 |
Chains | +0.004 |
Neg logit contributions | |
attent | -0.005 |
Rik | -0.004 |
� | -0.004 |
Crash | -0.004 |
Leader | -0.004 |
Token | - |
Token ID | 12 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
attent | +0.012 |
Rik | +0.011 |
� | +0.011 |
Crash | +0.011 |
Deng | +0.010 |
Neg logit contributions | |
ubs | -0.012 |
ales | -0.011 |
ooth | -0.011 |
gif | -0.010 |
Chains | -0.010 |
Token | Associated |
Token ID | 29014 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
attent | +0.008 |
Rik | +0.007 |
� | +0.007 |
Deng | +0.007 |
Leader | +0.007 |
Neg logit contributions | |
ubs | -0.019 |
ales | -0.018 |
ooth | -0.018 |
gif | -0.017 |
Chains | -0.017 |
Token | T |
Token ID | 309 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
attent | +0.203 |
Rik | +0.184 |
� | +0.181 |
Crash | +0.180 |
Deng | +0.179 |
Neg logit contributions | |
ubs | -0.173 |
ales | -0.162 |
ooth | -0.160 |
gif | -0.151 |
Chains | -0.149 |
Token | x |
Token ID | 87 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ubs | +0.015 |
ales | +0.015 |
ooth | +0.015 |
gif | +0.014 |
Chains | +0.014 |
Neg logit contributions | |
attent | -0.010 |
Rik | -0.008 |
� | -0.008 |
Crash | -0.008 |
Deng | -0.008 |
Token | - |
Token ID | 12 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
attent | +0.104 |
Rik | +0.093 |
� | +0.091 |
Crash | +0.091 |
Deng | +0.090 |
Neg logit contributions | |
ubs | -0.103 |
ales | -0.097 |
ooth | -0.096 |
gif | -0.091 |
Chains | -0.090 |
Token | Power |
Token ID | 13434 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
attent | +0.015 |
Rik | +0.014 |
� | +0.014 |
Crash | +0.014 |
Leader | +0.013 |
Neg logit contributions | |
ubs | -0.016 |
ales | -0.016 |
ooth | -0.015 |
gif | -0.015 |
Chains | -0.014 |
Token | = |
Token ID | 28 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
attent | +0.021 |
Rik | +0.019 |
� | +0.019 |
Crash | +0.019 |
Deng | +0.019 |
Neg logit contributions | |
ubs | -0.013 |
ales | -0.012 |
ooth | -0.012 |
gif | -0.011 |
Chains | -0.011 |
Token | 20 |
Token ID | 1238 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
ubs | +0.097 |
ales | +0.092 |
ooth | +0.091 |
gif | +0.086 |
ale | +0.085 |
Neg logit contributions | |
attent | -0.088 |
Rik | -0.079 |
� | -0.077 |
Crash | -0.076 |
Deng | -0.076 |
Token | dB |
Token ID | 30221 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
attent | +0.028 |
Rik | +0.024 |
� | +0.023 |
Crash | +0.023 |
abled | +0.023 |
Neg logit contributions | |
ubs | -0.057 |
ales | -0.054 |
ooth | -0.054 |
gif | -0.052 |
Chains | -0.051 |
Token | m |
Token ID | 76 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
attent | +0.205 |
Rik | +0.187 |
� | +0.183 |
Crash | +0.183 |
Deng | +0.182 |
Neg logit contributions | |
ubs | -0.160 |
ales | -0.150 |
ooth | -0.148 |
gif | -0.138 |
Chains | -0.137 |
Token | � |
Token ID | 447 |
Feature activation | -3.18e-03 |
Pos logit contributions | |
attent | +0.003 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
Deng | +0.002 |
Neg logit contributions | |
ubs | -0.003 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | � |
Token ID | 247 |
Feature activation | -9.19e-03 |
Pos logit contributions | |
attent | +0.002 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
Deng | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | s |
Token ID | 82 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
attent | +0.007 |
Rik | +0.006 |
� | +0.006 |
Crash | +0.006 |
Deng | +0.006 |
Neg logit contributions | |
ubs | -0.007 |
ales | -0.006 |
ooth | -0.006 |
gif | -0.006 |
Chains | -0.006 |
Token | review |
Token ID | 2423 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
attent | +0.011 |
Rik | +0.010 |
� | +0.010 |
Crash | +0.010 |
Deng | +0.010 |
Neg logit contributions | |
ubs | -0.011 |
ales | -0.011 |
ooth | -0.010 |
gif | -0.010 |
Chains | -0.010 |
Token | gave |
Token ID | 2921 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
attent | +0.065 |
Rik | +0.059 |
� | +0.058 |
Crash | +0.058 |
Deng | +0.057 |
Neg logit contributions | |
ubs | -0.060 |
ales | -0.057 |
ooth | -0.056 |
gif | -0.053 |
Chains | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e-03 |
Pos logit contributions | |
ubs | +0.033 |
ales | +0.031 |
ooth | +0.031 |
gif | +0.029 |
Chains | +0.029 |
Neg logit contributions | |
attent | -0.035 |
Rik | -0.031 |
� | -0.031 |
Crash | -0.031 |
Deng | -0.031 |
Token | dram |
Token ID | 4850 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
attent | +0.001 |
Rik | +0.001 |
� | +0.001 |
Crash | +0.001 |
Deng | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
Chains | -0.001 |
Token | at |
Token ID | 265 |
Feature activation | +3.97e-03 |
Pos logit contributions | |
attent | +0.176 |
Rik | +0.160 |
� | +0.156 |
Crash | +0.156 |
Leader | +0.156 |
Neg logit contributions | |
ubs | -0.156 |
ales | -0.146 |
ooth | -0.145 |
gif | -0.137 |
Chains | -0.135 |
Token | ization |
Token ID | 1634 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
ubs | +0.003 |
ales | +0.003 |
ooth | +0.003 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
� | -0.002 |
Crash | -0.002 |
Deng | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -3.92e-03 |
Pos logit contributions | |
attent | +0.050 |
Rik | +0.046 |
� | +0.045 |
Crash | +0.045 |
Leader | +0.044 |
Neg logit contributions | |
ubs | -0.048 |
ales | -0.045 |
ooth | -0.045 |
gif | -0.042 |
Chains | -0.042 |
Token | O |
Token ID | 440 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
attent | +0.003 |
Rik | +0.003 |
� | +0.003 |
Crash | +0.003 |
Deng | +0.003 |
Neg logit contributions | |
ubs | -0.003 |
ales | -0.003 |
ooth | -0.003 |
gif | -0.002 |
Chains | -0.002 |
Token | would |
Token ID | 561 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
attent | +0.003 |
Rik | +0.002 |
� | +0.002 |
Crash | +0.002 |
Deng | +0.002 |
Neg logit contributions | |
ubs | -0.002 |
ales | -0.002 |
ooth | -0.002 |
gif | -0.002 |
Chains | -0.002 |
Token | take |
Token ID | 1011 |
Feature activation | -9.11e-03 |
Pos logit contributions | |
attent | +0.050 |
Rik | +0.045 |
Crash | +0.044 |
� | +0.044 |
Deng | +0.044 |
Neg logit contributions | |
ubs | -0.046 |
ales | -0.043 |
ooth | -0.043 |
gif | -0.040 |
Chains | -0.040 |
Token | him |
Token ID | 683 |
Feature activation | -7.49e-03 |
Pos logit contributions | |
attent | +0.007 |
Rik | +0.007 |
� | +0.006 |
Crash | +0.006 |
Deng | +0.006 |
Neg logit contributions | |
ubs | -0.006 |
ales | -0.006 |
ooth | -0.006 |
gif | -0.005 |
Chains | -0.005 |
Token | prisoner |
Token ID | 17234 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
attent | +0.006 |
Rik | +0.005 |
� | +0.005 |
Crash | +0.005 |
abled | +0.005 |
Neg logit contributions | |
ubs | -0.005 |
ales | -0.005 |
ooth | -0.005 |
gif | -0.004 |
Chains | -0.004 |
Token | if |
Token ID | 611 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
ubs | +0.086 |
ales | +0.081 |
ooth | +0.080 |
gif | +0.075 |
Chains | +0.074 |
Neg logit contributions | |
attent | -0.091 |
Rik | -0.083 |
� | -0.081 |
Crash | -0.081 |
Deng | -0.080 |
Token | he |
Token ID | 339 |
Feature activation | +2.48e-04 |
Pos logit contributions | |
attent | +0.008 |
Rik | +0.007 |
� | +0.007 |
Crash | +0.007 |
abled | +0.007 |
Neg logit contributions | |
ubs | -0.008 |
ales | -0.008 |
ooth | -0.007 |
gif | -0.007 |
Chains | -0.007 |
Token | could |
Token ID | 714 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
ubs | +0.000 |
ales | +0.000 |
ooth | +0.000 |
gif | +0.000 |
Chains | +0.000 |
Neg logit contributions | |
attent | -0.000 |
Rik | -0.000 |
� | -0.000 |
Crash | -0.000 |
Deng | -0.000 |
Token | .[ |
Token ID | 3693 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
ubs | +0.028 |
ales | +0.027 |
ooth | +0.026 |
gif | +0.025 |
Chains | +0.024 |
Neg logit contributions | |
attent | -0.030 |
Rik | -0.028 |
� | -0.027 |
Crash | -0.027 |
Deng | -0.027 |
Token | 28 |
Token ID | 2078 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
ubs | +0.056 |
ales | +0.053 |
ooth | +0.052 |
gif | +0.049 |
Chains | +0.048 |
Neg logit contributions | |
attent | -0.066 |
Rik | -0.060 |
� | -0.059 |
Crash | -0.059 |
Deng | -0.059 |
Token | ] |
Token ID | 60 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
ubs | +0.031 |
ales | +0.029 |
ooth | +0.029 |
gif | +0.027 |
Chains | +0.027 |
Neg logit contributions | |
attent | -0.042 |
Rik | -0.039 |
� | -0.038 |
Crash | -0.038 |
Deng | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
ubs | +0.056 |
ales | +0.053 |
ooth | +0.052 |
gif | +0.049 |
Chains | +0.049 |
Neg logit contributions | |
attent | -0.057 |
Rik | -0.052 |
� | -0.050 |
Crash | -0.050 |
Deng | -0.050 |
Token | was |
Token ID | 373 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
Deng | -0.001 |
Token | initiated |
Token ID | 16862 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
ubs | +0.011 |
ales | +0.010 |
ooth | +0.010 |
gif | +0.009 |
Chains | +0.009 |
Neg logit contributions | |
attent | -0.010 |
Rik | -0.009 |
� | -0.008 |
Crash | -0.008 |
Deng | -0.008 |
Token | three |
Token ID | 1115 |
Feature activation | +1.93e-03 |
Pos logit contributions | |
ubs | +0.016 |
ales | +0.015 |
ooth | +0.015 |
gif | +0.014 |
Chains | +0.014 |
Neg logit contributions | |
attent | -0.018 |
Rik | -0.017 |
� | -0.016 |
Crash | -0.016 |
Deng | -0.016 |
Token | years |
Token ID | 812 |
Feature activation | -8.89e-02 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
Deng | -0.001 |
Token | ago |
Token ID | 2084 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
attent | +0.079 |
Rik | +0.073 |
� | +0.071 |
Crash | +0.071 |
abled | +0.071 |
Neg logit contributions | |
ubs | -0.052 |
ales | -0.048 |
ooth | -0.048 |
gif | -0.044 |
Chains | -0.044 |
Token | required |
Token ID | 2672 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
ubs | +0.110 |
ales | +0.104 |
ooth | +0.102 |
gif | +0.096 |
Chains | +0.095 |
Neg logit contributions | |
attent | -0.120 |
Rik | -0.108 |
� | -0.106 |
Crash | -0.106 |
Deng | -0.105 |
Token | users |
Token ID | 2985 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
attent | +0.232 |
Rik | +0.211 |
� | +0.205 |
Crash | +0.205 |
Deng | +0.204 |
Neg logit contributions | |
ubs | -0.219 |
ales | -0.206 |
ooth | -0.204 |
gif | -0.191 |
Chains | -0.190 |
Token | to |
Token ID | 284 |
Feature activation | +2.60e-03 |
Pos logit contributions | |
ubs | +0.050 |
ales | +0.048 |
ooth | +0.047 |
gif | +0.044 |
Chains | +0.044 |
Neg logit contributions | |
attent | -0.052 |
Rik | -0.047 |
� | -0.046 |
Crash | -0.046 |
abled | -0.046 |
Token | register |
Token ID | 7881 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
ubs | +0.002 |
ales | +0.002 |
ooth | +0.002 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.002 |
Rik | -0.002 |
� | -0.002 |
Crash | -0.002 |
Deng | -0.002 |
Token | their |
Token ID | 511 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
ubs | +0.053 |
ales | +0.050 |
ooth | +0.049 |
gif | +0.046 |
Chains | +0.046 |
Neg logit contributions | |
attent | -0.055 |
Rik | -0.050 |
� | -0.048 |
Crash | -0.048 |
Deng | -0.048 |
Token | numbers |
Token ID | 3146 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
attent | +0.010 |
Rik | +0.009 |
� | +0.009 |
Crash | +0.009 |
Deng | +0.008 |
Neg logit contributions | |
ubs | -0.008 |
ales | -0.008 |
ooth | -0.008 |
gif | -0.007 |
Chains | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +9.69e-03 |
Pos logit contributions | |
attent | +0.053 |
Rik | +0.048 |
� | +0.047 |
Crash | +0.047 |
Deng | +0.047 |
Neg logit contributions | |
ubs | -0.047 |
ales | -0.044 |
ooth | -0.044 |
gif | -0.041 |
Chains | -0.041 |
Token | involved |
Token ID | 2950 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
ubs | +0.007 |
ales | +0.006 |
ooth | +0.006 |
gif | +0.006 |
Chains | +0.006 |
Neg logit contributions | |
attent | -0.008 |
Rik | -0.007 |
� | -0.007 |
Deng | -0.007 |
Crash | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
attent | +0.031 |
Rik | +0.028 |
� | +0.027 |
Crash | +0.027 |
Deng | +0.027 |
Neg logit contributions | |
ubs | -0.027 |
ales | -0.026 |
ooth | -0.025 |
gif | -0.024 |
Chains | -0.024 |
Token | everything |
Token ID | 2279 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
ubs | +0.009 |
ales | +0.009 |
ooth | +0.009 |
gif | +0.008 |
Chains | +0.008 |
Neg logit contributions | |
attent | -0.010 |
Rik | -0.009 |
� | -0.009 |
Crash | -0.009 |
Deng | -0.009 |
Token | – |
Token ID | 784 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
attent | +0.009 |
Rik | +0.008 |
� | +0.008 |
Crash | +0.008 |
abled | +0.008 |
Neg logit contributions | |
ubs | -0.008 |
ales | -0.008 |
ooth | -0.008 |
gif | -0.007 |
Chains | -0.007 |
Token | drib |
Token ID | 35003 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
attent | +0.013 |
Rik | +0.012 |
� | +0.011 |
Deng | +0.011 |
Crash | +0.011 |
Neg logit contributions | |
ubs | -0.012 |
ales | -0.012 |
ooth | -0.011 |
gif | -0.011 |
Chains | -0.011 |
Token | bling |
Token ID | 11108 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
attent | +0.224 |
Rik | +0.198 |
� | +0.194 |
Crash | +0.192 |
Deng | +0.191 |
Neg logit contributions | |
ubs | -0.303 |
ales | -0.288 |
ooth | -0.285 |
gif | -0.270 |
Chains | -0.268 |
Token | with |
Token ID | 351 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
attent | +0.081 |
Rik | +0.073 |
� | +0.071 |
Crash | +0.071 |
Deng | +0.071 |
Neg logit contributions | |
ubs | -0.075 |
ales | -0.070 |
ooth | -0.070 |
gif | -0.066 |
Chains | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | -9.52e-03 |
Pos logit contributions | |
attent | +0.010 |
Rik | +0.009 |
� | +0.008 |
Crash | +0.008 |
Deng | +0.008 |
Neg logit contributions | |
ubs | -0.009 |
ales | -0.009 |
ooth | -0.008 |
gif | -0.008 |
Chains | -0.008 |
Token | ball |
Token ID | 2613 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
attent | +0.007 |
Rik | +0.006 |
� | +0.006 |
Crash | +0.006 |
Deng | +0.006 |
Neg logit contributions | |
ubs | -0.007 |
ales | -0.007 |
ooth | -0.007 |
gif | -0.006 |
Chains | -0.006 |
Token | at |
Token ID | 379 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
attent | +0.038 |
Rik | +0.035 |
� | +0.034 |
Crash | +0.034 |
Deng | +0.034 |
Neg logit contributions | |
ubs | -0.036 |
ales | -0.033 |
ooth | -0.033 |
gif | -0.031 |
Chains | -0.031 |
Token | referendum |
Token ID | 11467 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
attent | +0.009 |
Rik | +0.009 |
� | +0.008 |
Crash | +0.008 |
Deng | +0.008 |
Neg logit contributions | |
ubs | -0.009 |
ales | -0.008 |
ooth | -0.008 |
gif | -0.008 |
Chains | -0.007 |
Token | supported |
Token ID | 4855 |
Feature activation | -1.89e-03 |
Pos logit contributions | |
ubs | +0.028 |
ales | +0.026 |
ooth | +0.026 |
gif | +0.024 |
Chains | +0.024 |
Neg logit contributions | |
attent | -0.032 |
Rik | -0.029 |
� | -0.028 |
Crash | -0.028 |
Deng | -0.028 |
Token | by |
Token ID | 416 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
attent | +0.002 |
Rik | +0.001 |
� | +0.001 |
Crash | +0.001 |
Deng | +0.001 |
Neg logit contributions | |
ubs | -0.001 |
ales | -0.001 |
ooth | -0.001 |
gif | -0.001 |
Chains | -0.001 |
Token | all |
Token ID | 477 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
ubs | +0.027 |
ales | +0.025 |
ooth | +0.025 |
gif | +0.023 |
Chains | +0.023 |
Neg logit contributions | |
attent | -0.028 |
Rik | -0.026 |
� | -0.025 |
Crash | -0.025 |
Deng | -0.025 |
Token | Sloven |
Token ID | 30694 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
attent | +0.033 |
Rik | +0.030 |
Crash | +0.029 |
� | +0.029 |
Deng | +0.029 |
Neg logit contributions | |
ubs | -0.032 |
ales | -0.030 |
ooth | -0.030 |
gif | -0.028 |
Chains | -0.028 |
Token | ian |
Token ID | 666 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ubs | +0.166 |
ales | +0.159 |
ooth | +0.157 |
gif | +0.151 |
Chains | +0.150 |
Neg logit contributions | |
attent | -0.071 |
Rik | -0.059 |
� | -0.057 |
Crash | -0.056 |
Deng | -0.056 |
Token | political |
Token ID | 1964 |
Feature activation | +4.02e-03 |
Pos logit contributions | |
attent | +0.192 |
Rik | +0.172 |
� | +0.168 |
Crash | +0.168 |
Leader | +0.167 |
Neg logit contributions | |
ubs | -0.203 |
ales | -0.192 |
ooth | -0.190 |
gif | -0.179 |
Chains | -0.178 |
Token | parties |
Token ID | 4671 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ubs | +0.003 |
ales | +0.003 |
ooth | +0.003 |
gif | +0.003 |
Chains | +0.003 |
Neg logit contributions | |
attent | -0.003 |
Rik | -0.002 |
� | -0.002 |
Crash | -0.002 |
Deng | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +1.77e-03 |
Pos logit contributions | |
attent | +0.079 |
Rik | +0.071 |
� | +0.070 |
Crash | +0.070 |
Deng | +0.069 |
Neg logit contributions | |
ubs | -0.070 |
ales | -0.066 |
ooth | -0.065 |
gif | -0.062 |
Chains | -0.061 |
Token | held |
Token ID | 2714 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
ubs | +0.001 |
ales | +0.001 |
ooth | +0.001 |
gif | +0.001 |
Chains | +0.001 |
Neg logit contributions | |
attent | -0.001 |
Rik | -0.001 |
� | -0.001 |
Crash | -0.001 |
Deng | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | +4.08e-03 |
Pos logit contributions | |
attent | +0.022 |
Rik | +0.020 |
� | +0.019 |
Crash | +0.019 |
Deng | +0.019 |
Neg logit contributions | |
ubs | -0.020 |
ales | -0.018 |
ooth | -0.018 |
gif | -0.017 |
Chains | -0.017 |
Token | com |
Token ID | 785 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
attent | +0.018 |
Rik | +0.016 |
� | +0.016 |
Crash | +0.016 |
Deng | +0.015 |
Neg logit contributions | |
ubs | -0.017 |
ales | -0.016 |
ooth | -0.016 |
gif | -0.015 |
Chains | -0.015 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
attent | +0.033 |
Rik | +0.030 |
� | +0.029 |
Crash | +0.029 |
Deng | +0.029 |
Neg logit contributions | |
ubs | -0.027 |
ales | -0.025 |
ooth | -0.024 |
gif | -0.023 |
Chains | -0.023 |
Token | 92 |
Token ID | 5892 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
ubs | +0.038 |
ales | +0.036 |
ooth | +0.036 |
gif | +0.034 |
ale | +0.034 |
Neg logit contributions | |
attent | -0.027 |
Rik | -0.024 |
� | -0.023 |
Crash | -0.023 |
Leader | -0.023 |
Token | ] |
Token ID | 60 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
attent | +0.018 |
Rik | +0.017 |
� | +0.016 |
Crash | +0.016 |
Deng | +0.016 |
Neg logit contributions | |
ubs | -0.014 |
ales | -0.013 |
ooth | -0.013 |
gif | -0.012 |
Chains | -0.012 |
Token | Ath |
Token ID | 13548 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
ubs | +0.031 |
ales | +0.029 |
ooth | +0.029 |
gif | +0.027 |
Chains | +0.027 |
Neg logit contributions | |
attent | -0.031 |
Rik | -0.028 |
� | -0.027 |
Crash | -0.027 |
Deng | -0.027 |
Token | lon |
Token ID | 14995 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
ubs | +0.019 |
ales | +0.018 |
ooth | +0.018 |
gif | +0.017 |
ale | +0.017 |
Neg logit contributions | |
attent | -0.009 |
Rik | -0.008 |
� | -0.008 |
Deng | -0.008 |
Crash | -0.008 |
Token | Sports |
Token ID | 7092 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
attent | +0.164 |
Rik | +0.143 |
� | +0.140 |
Crash | +0.139 |
Deng | +0.138 |
Neg logit contributions | |
ubs | -0.236 |
ales | -0.224 |
ooth | -0.222 |
gif | -0.212 |
Chains | -0.209 |
Token | ,[ |
Token ID | 17414 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
attent | +0.153 |
Rik | +0.139 |
� | +0.136 |
Crash | +0.136 |
Deng | +0.135 |
Neg logit contributions | |
ubs | -0.137 |
ales | -0.128 |
ooth | -0.127 |
gif | -0.119 |
Chains | -0.118 |
Token | 97 |
Token ID | 5607 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ubs | +0.038 |
ales | +0.036 |
ooth | +0.036 |
gif | +0.034 |
ale | +0.034 |
Neg logit contributions | |
attent | -0.028 |
Rik | -0.025 |
� | -0.024 |
Crash | -0.024 |
Leader | -0.024 |
Token | ] |
Token ID | 60 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
attent | +0.131 |
Rik | +0.120 |
� | +0.118 |
Crash | +0.117 |
Deng | +0.117 |
Neg logit contributions | |
ubs | -0.099 |
ales | -0.092 |
ooth | -0.091 |
gif | -0.085 |
Chains | -0.084 |
Token | Ble |
Token ID | 17175 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
ubs | +0.028 |
ales | +0.027 |
ooth | +0.026 |
gif | +0.025 |
Chains | +0.025 |
Neg logit contributions | |
attent | -0.029 |
Rik | -0.026 |
� | -0.025 |
Crash | -0.025 |
Deng | -0.025 |
Token | have |
Token ID | 423 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
attent | +0.021 |
Rik | +0.019 |
� | +0.018 |
Crash | +0.018 |
Deng | +0.018 |
Neg logit contributions | |
ubs | -0.018 |
ales | -0.017 |
ooth | -0.016 |
gif | -0.015 |
Chains | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -6.72e-03 |
Pos logit contributions | |
attent | +0.011 |
Rik | +0.010 |
� | +0.010 |
Crash | +0.010 |
Deng | +0.010 |
Neg logit contributions | |
ubs | -0.010 |
ales | -0.010 |
ooth | -0.010 |
gif | -0.009 |
Chains | -0.009 |
Token | go |
Token ID | 467 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
attent | +0.005 |
Rik | +0.005 |
� | +0.005 |
Crash | +0.005 |
Deng | +0.005 |
Neg logit contributions | |
ubs | -0.005 |
ales | -0.004 |
ooth | -0.004 |
gif | -0.004 |
Chains | -0.004 |
Token | through |
Token ID | 832 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
attent | +0.064 |
Rik | +0.058 |
� | +0.057 |
Crash | +0.056 |
Deng | +0.056 |
Neg logit contributions | |
ubs | -0.060 |
ales | -0.057 |
ooth | -0.056 |
gif | -0.053 |
Chains | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
attent | +0.058 |
Rik | +0.053 |
� | +0.052 |
Crash | +0.051 |
Deng | +0.051 |
Neg logit contributions | |
ubs | -0.055 |
ales | -0.052 |
ooth | -0.051 |
gif | -0.048 |
Chains | -0.048 |
Token | same |
Token ID | 976 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
attent | +0.010 |
Rik | +0.009 |
� | +0.009 |
Crash | +0.009 |
Deng | +0.009 |
Neg logit contributions | |
ubs | -0.010 |
ales | -0.010 |
ooth | -0.010 |
gif | -0.009 |
Chains | -0.009 |
Token | planning |
Token ID | 5410 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
attent | +0.196 |
Rik | +0.177 |
� | +0.173 |
Crash | +0.172 |
Deng | +0.172 |
Neg logit contributions | |
ubs | -0.193 |
ales | -0.181 |
ooth | -0.179 |
gif | -0.169 |
Chains | -0.167 |
Token | process |
Token ID | 1429 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
ubs | +0.043 |
ales | +0.041 |
ooth | +0.040 |
gif | +0.038 |
Chains | +0.038 |
Neg logit contributions | |
attent | -0.047 |
Rik | -0.042 |
� | -0.041 |
Crash | -0.041 |
Leader | -0.041 |
Token | as |
Token ID | 355 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
attent | +0.024 |
Rik | +0.022 |
� | +0.022 |
Crash | +0.022 |
abled | +0.022 |
Neg logit contributions | |
ubs | -0.023 |
ales | -0.022 |
ooth | -0.021 |
gif | -0.020 |
Chains | -0.020 |
Token | you |
Token ID | 345 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
attent | +0.019 |
Rik | +0.017 |
� | +0.017 |
Crash | +0.017 |
abled | +0.017 |
Neg logit contributions | |
ubs | -0.019 |
ales | -0.018 |
ooth | -0.018 |
gif | -0.017 |
Chains | -0.016 |
Token | would |
Token ID | 561 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
attent | +0.025 |
Rik | +0.023 |
� | +0.022 |
Crash | +0.022 |
Deng | +0.022 |
Neg logit contributions | |
ubs | -0.021 |
ales | -0.020 |
ooth | -0.019 |
gif | -0.018 |
Chains | -0.018 |