Token | , |
Token ID | 11 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
inn | +0.013 |
icky | +0.011 |
ches | +0.011 |
nie | +0.011 |
kernel | +0.011 |
Neg logit contributions | |
disl | -0.014 |
killed | -0.012 |
bows | -0.011 |
Gig | -0.011 |
statues | -0.011 |
Token | leaving |
Token ID | 4305 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
inn | +0.023 |
ches | +0.020 |
icky | +0.020 |
kernel | +0.020 |
aid | +0.019 |
Neg logit contributions | |
disl | -0.031 |
killed | -0.024 |
Sorry | -0.024 |
Gig | -0.024 |
endant | -0.024 |
Token | it |
Token ID | 340 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
disl | +0.017 |
killed | +0.014 |
Gig | +0.014 |
statues | +0.013 |
Tri | +0.013 |
Neg logit contributions | |
inn | -0.013 |
ches | -0.011 |
icky | -0.011 |
nie | -0.011 |
kernel | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
disl | +0.008 |
killed | +0.006 |
endant | +0.006 |
Thank | +0.006 |
Gig | +0.006 |
Neg logit contributions | |
inn | -0.006 |
ches | -0.005 |
icky | -0.005 |
kernel | -0.005 |
nie | -0.005 |
Token | its |
Token ID | 663 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
disl | +0.010 |
killed | +0.008 |
endant | +0.008 |
Sorry | +0.008 |
bows | +0.008 |
Neg logit contributions | |
inn | -0.008 |
ches | -0.007 |
icky | -0.007 |
kernel | -0.007 |
aid | -0.007 |
Token | former |
Token ID | 1966 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
disl | +0.004 |
killed | +0.003 |
Sorry | +0.003 |
Thank | +0.003 |
Gig | +0.003 |
Neg logit contributions | |
inn | -0.003 |
ches | -0.003 |
icky | -0.003 |
kernel | -0.003 |
aid | -0.003 |
Token | state |
Token ID | 1181 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
disl | +0.142 |
Sorry | +0.114 |
Thank | +0.112 |
Gig | +0.110 |
killed | +0.109 |
Neg logit contributions | |
inn | -0.164 |
ches | -0.148 |
icky | -0.147 |
aid | -0.146 |
nie | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
disl | +0.060 |
killed | +0.049 |
statues | +0.048 |
bows | +0.048 |
jewels | +0.048 |
Neg logit contributions | |
inn | -0.056 |
ches | -0.049 |
icky | -0.048 |
nie | -0.047 |
kernel | -0.047 |
Token | |
Token ID | 220 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
inn | +0.028 |
ches | +0.025 |
kernel | +0.025 |
icky | +0.024 |
nie | +0.024 |
Neg logit contributions | |
disl | -0.033 |
Gig | -0.026 |
Sorry | -0.026 |
Thank | -0.026 |
killed | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
disl | +0.019 |
killed | +0.015 |
Gig | +0.014 |
Sorry | +0.014 |
Thank | +0.014 |
Neg logit contributions | |
inn | -0.017 |
ches | -0.015 |
kernel | -0.015 |
nie | -0.015 |
icky | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
inn | +0.020 |
ches | +0.018 |
kernel | +0.018 |
nie | +0.018 |
icky | +0.018 |
Neg logit contributions | |
disl | -0.022 |
Thank | -0.017 |
killed | -0.017 |
Gig | -0.017 |
Sorry | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
disl | +0.012 |
Gig | +0.010 |
killed | +0.010 |
Tri | +0.010 |
statues | +0.010 |
Neg logit contributions | |
inn | -0.009 |
ches | -0.008 |
icky | -0.008 |
aid | -0.008 |
kernel | -0.008 |
Token | tree |
Token ID | 5509 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
disl | +0.017 |
Sorry | +0.013 |
killed | +0.013 |
Gig | +0.013 |
Thank | +0.013 |
Neg logit contributions | |
inn | -0.013 |
ches | -0.011 |
icky | -0.011 |
kernel | -0.011 |
aid | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
inn | +0.005 |
icky | +0.004 |
ches | +0.004 |
kernel | +0.004 |
ud | +0.004 |
Neg logit contributions | |
disl | -0.005 |
bows | -0.004 |
killed | -0.004 |
jewels | -0.004 |
Tri | -0.004 |
Token | its |
Token ID | 663 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
disl | +0.013 |
killed | +0.010 |
Gig | +0.010 |
Thank | +0.010 |
Sorry | +0.010 |
Neg logit contributions | |
inn | -0.011 |
ches | -0.009 |
icky | -0.009 |
kernel | -0.009 |
nie | -0.009 |
Token | once |
Token ID | 1752 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
disl | +0.016 |
killed | +0.013 |
Gig | +0.012 |
Thank | +0.012 |
endant | +0.012 |
Neg logit contributions | |
inn | -0.013 |
ches | -0.012 |
icky | -0.012 |
kernel | -0.011 |
nie | -0.011 |
Token | former |
Token ID | 1966 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
disl | +0.011 |
killed | +0.009 |
Thank | +0.009 |
jewels | +0.008 |
lucky | +0.008 |
Neg logit contributions | |
inn | -0.010 |
icky | -0.008 |
ches | -0.008 |
kernel | -0.008 |
ud | -0.008 |
Token | beauty |
Token ID | 8737 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
disl | +0.136 |
Sorry | +0.107 |
Thank | +0.104 |
killed | +0.104 |
Gig | +0.101 |
Neg logit contributions | |
inn | -0.168 |
ches | -0.155 |
icky | -0.152 |
nie | -0.152 |
aid | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
disl | +0.056 |
bows | +0.046 |
jewels | +0.044 |
statues | +0.044 |
Gig | +0.044 |
Neg logit contributions | |
inn | -0.055 |
icky | -0.048 |
kernel | -0.047 |
aid | -0.047 |
ches | -0.047 |
Token | He |
Token ID | 679 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
inn | +0.016 |
ches | +0.014 |
icky | +0.014 |
kernel | +0.014 |
nie | +0.013 |
Neg logit contributions | |
disl | -0.017 |
killed | -0.013 |
Gig | -0.013 |
Sorry | -0.013 |
Thank | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
inn | +0.017 |
icky | +0.015 |
ches | +0.014 |
kernel | +0.014 |
aid | +0.014 |
Neg logit contributions | |
disl | -0.017 |
killed | -0.014 |
Thank | -0.014 |
endant | -0.013 |
Gig | -0.013 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
inn | +0.016 |
ches | +0.014 |
icky | +0.014 |
kernel | +0.014 |
aid | +0.014 |
Neg logit contributions | |
disl | -0.012 |
killed | -0.009 |
Thank | -0.009 |
Gig | -0.009 |
endant | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
inn | +0.009 |
icky | +0.007 |
ches | +0.007 |
kernel | +0.007 |
aid | +0.007 |
Neg logit contributions | |
disl | -0.012 |
killed | -0.010 |
bows | -0.010 |
Gig | -0.010 |
endant | -0.010 |
Token | be |
Token ID | 307 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
disl | +0.013 |
killed | +0.010 |
Gig | +0.010 |
endant | +0.010 |
Thank | +0.010 |
Neg logit contributions | |
inn | -0.013 |
ches | -0.012 |
icky | -0.012 |
kernel | -0.012 |
aid | -0.012 |
Token | restored |
Token ID | 15032 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
inn | +0.000 |
ches | +0.000 |
nie | +0.000 |
aid | +0.000 |
' | +0.000 |
Neg logit contributions | |
disl | -0.000 |
Sorry | -0.000 |
mm | -0.000 |
Gig | -0.000 |
bows | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
inn | +0.026 |
icky | +0.022 |
kernel | +0.022 |
ches | +0.022 |
aid | +0.022 |
Neg logit contributions | |
disl | -0.024 |
Gig | -0.019 |
killed | -0.019 |
bows | -0.019 |
jewels | -0.019 |
Token | its |
Token ID | 663 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
disl | +0.010 |
endant | +0.008 |
Thank | +0.008 |
Gig | +0.008 |
killed | +0.008 |
Neg logit contributions | |
inn | -0.008 |
icky | -0.007 |
ches | -0.007 |
aid | -0.007 |
nie | -0.007 |
Token | former |
Token ID | 1966 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
disl | +0.012 |
killed | +0.009 |
endant | +0.009 |
Sorry | +0.009 |
Thank | +0.009 |
Neg logit contributions | |
inn | -0.009 |
aid | -0.009 |
nie | -0.008 |
icky | -0.008 |
ches | -0.008 |
Token | glory |
Token ID | 13476 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
disl | +0.134 |
Sorry | +0.105 |
Thank | +0.104 |
killed | +0.103 |
Gig | +0.102 |
Neg logit contributions | |
inn | -0.161 |
ches | -0.147 |
icky | -0.144 |
nie | -0.143 |
aid | -0.143 |
Token | ." |
Token ID | 526 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
disl | +0.010 |
jewels | +0.008 |
statues | +0.008 |
bows | +0.008 |
endant | +0.007 |
Neg logit contributions | |
inn | -0.012 |
kernel | -0.010 |
ches | -0.010 |
icky | -0.010 |
aid | -0.010 |
Token | |
Token ID | 220 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
inn | +0.011 |
ches | +0.011 |
kernel | +0.011 |
nie | +0.010 |
aid | +0.010 |
Neg logit contributions | |
disl | -0.011 |
Gig | -0.009 |
Tri | -0.008 |
Sorry | -0.008 |
Thank | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
disl | +0.016 |
Gig | +0.012 |
Tri | +0.012 |
killed | +0.012 |
endant | +0.012 |
Neg logit contributions | |
inn | -0.017 |
kernel | -0.017 |
nie | -0.016 |
ches | -0.016 |
strand | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
inn | +0.012 |
kernel | +0.012 |
ches | +0.012 |
nie | +0.012 |
aid | +0.011 |
Neg logit contributions | |
disl | -0.011 |
Gig | -0.009 |
Thank | -0.008 |
Tri | -0.008 |
Sorry | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
inn | +0.007 |
icky | +0.006 |
ches | +0.006 |
kernel | +0.006 |
nie | +0.006 |
Neg logit contributions | |
disl | -0.009 |
killed | -0.007 |
Gig | -0.007 |
jewels | -0.007 |
Sorry | -0.007 |
Token | village |
Token ID | 7404 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
inn | +0.001 |
aid | +0.001 |
kernel | +0.001 |
' | +0.001 |
icky | +0.001 |
Neg logit contributions | |
disl | -0.002 |
Sorry | -0.001 |
Tri | -0.001 |
endant | -0.001 |
Gig | -0.001 |
Token | back |
Token ID | 736 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
disl | +0.015 |
killed | +0.012 |
Sorry | +0.011 |
Gig | +0.011 |
endant | +0.011 |
Neg logit contributions | |
inn | -0.012 |
ches | -0.011 |
icky | -0.011 |
kernel | -0.011 |
nie | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
inn | +0.014 |
ches | +0.012 |
icky | +0.012 |
kernel | +0.012 |
nie | +0.011 |
Neg logit contributions | |
disl | -0.021 |
killed | -0.017 |
Gig | -0.017 |
endant | -0.017 |
Sorry | -0.017 |
Token | its |
Token ID | 663 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
disl | +0.016 |
endant | +0.013 |
killed | +0.013 |
bows | +0.013 |
Thank | +0.013 |
Neg logit contributions | |
inn | -0.013 |
icky | -0.011 |
ches | -0.011 |
kernel | -0.011 |
aid | -0.011 |
Token | former |
Token ID | 1966 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
disl | +0.016 |
killed | +0.013 |
Sorry | +0.012 |
endant | +0.012 |
Thank | +0.012 |
Neg logit contributions | |
inn | -0.014 |
ches | -0.012 |
icky | -0.012 |
aid | -0.012 |
kernel | -0.012 |
Token | glory |
Token ID | 13476 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
disl | +0.125 |
killed | +0.092 |
Sorry | +0.090 |
Thank | +0.090 |
Gig | +0.089 |
Neg logit contributions | |
inn | -0.169 |
ches | -0.155 |
icky | -0.153 |
kernel | -0.150 |
nie | -0.150 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
disl | +0.020 |
jewels | +0.015 |
bows | +0.015 |
statues | +0.015 |
endant | +0.015 |
Neg logit contributions | |
inn | -0.023 |
ches | -0.020 |
icky | -0.020 |
kernel | -0.020 |
ud | -0.020 |
Token | |
Token ID | 220 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
inn | +0.031 |
ches | +0.027 |
icky | +0.027 |
kernel | +0.027 |
nie | +0.026 |
Neg logit contributions | |
disl | -0.033 |
Thank | -0.026 |
Gig | -0.026 |
Sorry | -0.025 |
killed | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
disl | +0.009 |
killed | +0.007 |
Gig | +0.007 |
Sorry | +0.007 |
Tri | +0.007 |
Neg logit contributions | |
inn | -0.009 |
kernel | -0.009 |
ches | -0.009 |
nie | -0.008 |
strand | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
inn | +0.025 |
ches | +0.023 |
kernel | +0.022 |
nie | +0.022 |
ash | +0.021 |
Neg logit contributions | |
disl | -0.021 |
Thank | -0.017 |
Gig | -0.016 |
killed | -0.016 |
Tri | -0.016 |
Token | back |
Token ID | 736 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
inn | +0.023 |
ches | +0.021 |
icky | +0.021 |
kernel | +0.020 |
aid | +0.020 |
Neg logit contributions | |
disl | -0.031 |
Sorry | -0.025 |
killed | -0.025 |
endant | -0.025 |
Thank | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
inn | +0.021 |
ches | +0.018 |
icky | +0.018 |
kernel | +0.017 |
nie | +0.017 |
Neg logit contributions | |
disl | -0.032 |
killed | -0.026 |
Sorry | -0.026 |
endant | -0.025 |
Thank | -0.025 |
Token | village |
Token ID | 7404 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
aid | +0.004 |
inn | +0.004 |
' | +0.004 |
kernel | +0.003 |
chair | +0.003 |
Neg logit contributions | |
disl | -0.005 |
Sorry | -0.005 |
Gig | -0.004 |
bows | -0.004 |
mm | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
inn | +0.001 |
ches | +0.001 |
icky | +0.001 |
kernel | +0.001 |
nie | +0.001 |
Neg logit contributions | |
disl | -0.001 |
killed | -0.001 |
endant | -0.001 |
Gig | -0.001 |
Thank | -0.001 |
Token | its |
Token ID | 663 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
disl | +0.004 |
killed | +0.003 |
Gig | +0.003 |
Sorry | +0.003 |
Thank | +0.003 |
Neg logit contributions | |
inn | -0.003 |
ches | -0.002 |
icky | -0.002 |
kernel | -0.002 |
nie | -0.002 |
Token | former |
Token ID | 1966 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
disl | +0.008 |
killed | +0.006 |
Sorry | +0.006 |
endant | +0.006 |
Gig | +0.006 |
Neg logit contributions | |
inn | -0.007 |
ches | -0.006 |
icky | -0.006 |
aid | -0.006 |
kernel | -0.006 |
Token | state |
Token ID | 1181 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
disl | +0.121 |
killed | +0.089 |
Sorry | +0.088 |
Thank | +0.087 |
Gig | +0.087 |
Neg logit contributions | |
inn | -0.167 |
ches | -0.152 |
icky | -0.150 |
nie | -0.148 |
kernel | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
disl | +0.047 |
bows | +0.038 |
statues | +0.038 |
jewels | +0.038 |
killed | +0.038 |
Neg logit contributions | |
inn | -0.040 |
ches | -0.035 |
icky | -0.035 |
kernel | -0.034 |
nie | -0.033 |
Token | With |
Token ID | 2080 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
inn | +0.023 |
ches | +0.021 |
kernel | +0.021 |
nie | +0.020 |
icky | +0.020 |
Neg logit contributions | |
disl | -0.024 |
Gig | -0.019 |
Thank | -0.019 |
Sorry | -0.019 |
Tri | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
disl | +0.013 |
killed | +0.010 |
Gig | +0.010 |
Thank | +0.010 |
Sorry | +0.010 |
Neg logit contributions | |
inn | -0.010 |
ches | -0.009 |
icky | -0.009 |
kernel | -0.009 |
nie | -0.009 |
Token | help |
Token ID | 1037 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
disl | +0.006 |
Sorry | +0.005 |
endant | +0.005 |
bows | +0.005 |
Gig | +0.005 |
Neg logit contributions | |
inn | -0.005 |
kernel | -0.005 |
' | -0.005 |
aid | -0.005 |
ches | -0.005 |
Token | give |
Token ID | 1577 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
disl | +0.039 |
endant | +0.030 |
Sorry | +0.030 |
Gig | +0.030 |
killed | +0.029 |
Neg logit contributions | |
inn | -0.041 |
ches | -0.039 |
kernel | -0.038 |
aid | -0.037 |
icky | -0.037 |
Token | them |
Token ID | 606 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
disl | +0.020 |
Gig | +0.017 |
killed | +0.017 |
Thank | +0.017 |
jewels | +0.017 |
Neg logit contributions | |
inn | -0.013 |
icky | -0.011 |
ches | -0.010 |
kernel | -0.010 |
nie | -0.010 |
Token | towels |
Token ID | 38494 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
disl | +0.011 |
killed | +0.009 |
Gig | +0.009 |
Thank | +0.009 |
Sorry | +0.009 |
Neg logit contributions | |
inn | -0.009 |
ches | -0.008 |
icky | -0.008 |
kernel | -0.008 |
nie | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
disl | +0.017 |
killed | +0.014 |
Gig | +0.014 |
Thank | +0.014 |
endant | +0.014 |
Neg logit contributions | |
inn | -0.010 |
icky | -0.008 |
ches | -0.008 |
kernel | -0.008 |
nie | -0.008 |
Token | p |
Token ID | 279 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
disl | +0.029 |
Gig | +0.023 |
killed | +0.023 |
endant | +0.023 |
Sorry | +0.023 |
Neg logit contributions | |
inn | -0.025 |
ches | -0.023 |
kernel | -0.023 |
icky | -0.023 |
aid | -0.022 |
Token | aj |
Token ID | 1228 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
disl | +0.101 |
Thank | +0.084 |
Sorry | +0.084 |
killed | +0.083 |
Gig | +0.082 |
Neg logit contributions | |
inn | -0.058 |
ches | -0.049 |
icky | -0.048 |
kernel | -0.045 |
ash | -0.044 |
Token | amas |
Token ID | 17485 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
disl | +0.194 |
killed | +0.164 |
Gig | +0.163 |
endant | +0.160 |
Thank | +0.159 |
Neg logit contributions | |
inn | -0.075 |
icky | -0.067 |
ches | -0.065 |
nie | -0.058 |
ide | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
disl | +0.057 |
killed | +0.046 |
Gig | +0.046 |
Sorry | +0.046 |
endant | +0.046 |
Neg logit contributions | |
inn | -0.033 |
ches | -0.029 |
icky | -0.028 |
kernel | -0.027 |
aid | -0.027 |
Token | They |
Token ID | 1119 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
disl | +0.036 |
killed | +0.030 |
endant | +0.030 |
jewels | +0.029 |
bows | +0.029 |
Neg logit contributions | |
inn | -0.031 |
icky | -0.028 |
aid | -0.027 |
ches | -0.026 |
kernel | -0.026 |
Token | give |
Token ID | 1577 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
disl | +0.038 |
Sorry | +0.028 |
endant | +0.028 |
killed | +0.028 |
Gig | +0.028 |
Neg logit contributions | |
inn | -0.045 |
ches | -0.043 |
kernel | -0.042 |
icky | -0.041 |
aid | -0.041 |
Token | them |
Token ID | 606 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
disl | +0.021 |
Gig | +0.018 |
killed | +0.018 |
Thank | +0.017 |
jewels | +0.017 |
Neg logit contributions | |
inn | -0.012 |
icky | -0.010 |
ches | -0.010 |
aid | -0.010 |
kernel | -0.010 |
Token | We |
Token ID | 775 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
disl | +0.019 |
killed | +0.015 |
endant | +0.015 |
Gig | +0.014 |
Thank | +0.014 |
Neg logit contributions | |
inn | -0.020 |
icky | -0.018 |
ches | -0.018 |
aid | -0.018 |
nie | -0.018 |
Token | have |
Token ID | 423 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
inn | +0.041 |
ches | +0.039 |
icky | +0.036 |
' | +0.036 |
kernel | +0.036 |
Neg logit contributions | |
disl | -0.035 |
Gig | -0.027 |
endant | -0.026 |
Tri | -0.025 |
Thank | -0.025 |
Token | different |
Token ID | 1180 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
inn | +0.014 |
ches | +0.012 |
icky | +0.012 |
kernel | +0.012 |
nie | +0.012 |
Neg logit contributions | |
disl | -0.022 |
killed | -0.018 |
endant | -0.018 |
Gig | -0.018 |
Sorry | -0.018 |
Token | likes |
Token ID | 7832 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
disl | +0.033 |
Gig | +0.027 |
Thank | +0.027 |
killed | +0.027 |
Sorry | +0.027 |
Neg logit contributions | |
inn | -0.032 |
ches | -0.030 |
icky | -0.029 |
nie | -0.029 |
aid | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
disl | +0.004 |
killed | +0.003 |
jewels | +0.003 |
Gig | +0.003 |
statues | +0.003 |
Neg logit contributions | |
inn | -0.003 |
ches | -0.003 |
icky | -0.003 |
kernel | -0.003 |
nie | -0.003 |
Token | disl |
Token ID | 19621 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
disl | +0.022 |
Gig | +0.022 |
mm | +0.020 |
Tri | +0.020 |
Thank | +0.020 |
Neg logit contributions | |
inn | -0.024 |
ches | -0.024 |
mat | -0.024 |
nie | -0.024 |
aid | -0.023 |
Token | ikes |
Token ID | 7938 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
disl | +0.103 |
bows | +0.072 |
Sorry | +0.070 |
killed | +0.070 |
Thank | +0.070 |
Neg logit contributions | |
inn | -0.162 |
ches | -0.149 |
kernel | -0.147 |
icky | -0.146 |
aid | -0.145 |
Token | . |
Token ID | 13 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
inn | +0.001 |
aid | +0.001 |
kernel | +0.001 |
icky | +0.001 |
ches | +0.001 |
Neg logit contributions | |
disl | -0.001 |
killed | -0.001 |
Sorry | -0.001 |
bows | -0.001 |
Thank | -0.001 |
Token | We |
Token ID | 775 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
disl | +0.017 |
killed | +0.014 |
endant | +0.013 |
bows | +0.013 |
Gig | +0.013 |
Neg logit contributions | |
inn | -0.018 |
icky | -0.016 |
ches | -0.016 |
aid | -0.016 |
nie | -0.015 |
Token | can |
Token ID | 460 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
inn | +0.035 |
ches | +0.034 |
' | +0.032 |
scrub | +0.031 |
kernel | +0.031 |
Neg logit contributions | |
disl | -0.032 |
Gig | -0.026 |
endant | -0.025 |
statues | -0.025 |
mm | -0.025 |
Token | be |
Token ID | 307 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
disl | +0.008 |
killed | +0.007 |
Sorry | +0.006 |
Gig | +0.006 |
Thank | +0.006 |
Neg logit contributions | |
inn | -0.008 |
ches | -0.007 |
icky | -0.007 |
kernel | -0.007 |
nie | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
disl | +0.010 |
killed | +0.008 |
Thank | +0.008 |
Gig | +0.008 |
Tri | +0.007 |
Neg logit contributions | |
inn | -0.013 |
nie | -0.012 |
kernel | -0.012 |
ches | -0.011 |
pron | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
disl | +0.004 |
killed | +0.003 |
Thank | +0.003 |
Gig | +0.003 |
Sorry | +0.003 |
Neg logit contributions | |
inn | -0.003 |
ches | -0.003 |
nie | -0.003 |
kernel | -0.003 |
icky | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
inn | +0.003 |
ches | +0.003 |
icky | +0.003 |
kernel | +0.003 |
nie | +0.003 |
Neg logit contributions | |
disl | -0.004 |
killed | -0.003 |
Gig | -0.003 |
Sorry | -0.003 |
Thank | -0.003 |
Token | Rex |
Token ID | 47389 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
disl | +0.029 |
endant | +0.024 |
bows | +0.024 |
jewels | +0.024 |
Gig | +0.023 |
Neg logit contributions | |
inn | -0.020 |
icky | -0.017 |
ches | -0.017 |
aid | -0.016 |
kernel | -0.016 |
Token | sn |
Token ID | 3013 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
disl | +0.026 |
Gig | +0.020 |
endant | +0.020 |
killed | +0.020 |
Sorry | +0.020 |
Neg logit contributions | |
inn | -0.024 |
ches | -0.022 |
icky | -0.021 |
kernel | -0.021 |
aid | -0.021 |
Token | arl |
Token ID | 7063 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
disl | +0.024 |
killed | +0.019 |
jewels | +0.019 |
statues | +0.019 |
Gig | +0.019 |
Neg logit contributions | |
inn | -0.020 |
ches | -0.018 |
icky | -0.018 |
kernel | -0.017 |
aid | -0.017 |
Token | s |
Token ID | 82 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
disl | +0.163 |
killed | +0.133 |
Gig | +0.131 |
endant | +0.131 |
Thank | +0.131 |
Neg logit contributions | |
inn | -0.097 |
ches | -0.084 |
icky | -0.083 |
kernel | -0.080 |
aid | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
disl | +0.002 |
killed | +0.001 |
Thank | +0.001 |
Gig | +0.001 |
jewels | +0.001 |
Neg logit contributions | |
inn | -0.001 |
icky | -0.001 |
nie | -0.001 |
ches | -0.001 |
kernel | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
disl | +0.043 |
endant | +0.035 |
killed | +0.034 |
bows | +0.034 |
jewels | +0.034 |
Neg logit contributions | |
inn | -0.031 |
icky | -0.027 |
ches | -0.027 |
aid | -0.027 |
kernel | -0.026 |
Token | does |
Token ID | 857 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
disl | +0.012 |
Gig | +0.009 |
Sorry | +0.009 |
endant | +0.009 |
Thank | +0.009 |
Neg logit contributions | |
inn | -0.012 |
ches | -0.011 |
icky | -0.010 |
kernel | -0.010 |
aid | -0.010 |
Token | not |
Token ID | 407 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
disl | +0.008 |
endant | +0.006 |
Gig | +0.006 |
Sorry | +0.006 |
bows | +0.006 |
Neg logit contributions | |
inn | -0.008 |
ches | -0.008 |
aid | -0.008 |
icky | -0.007 |
kernel | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
disl | +0.107 |
Sorry | +0.088 |
Gig | +0.086 |
killed | +0.086 |
endant | +0.086 |
Neg logit contributions | |
inn | -0.041 |
ches | -0.036 |
kernel | -0.034 |
icky | -0.034 |
aid | -0.034 |
Token | trees |
Token ID | 7150 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
disl | +0.064 |
Sorry | +0.050 |
endant | +0.050 |
mm | +0.049 |
Gig | +0.049 |
Neg logit contributions | |
nie | -0.047 |
chair | -0.047 |
inn | -0.047 |
kernel | -0.046 |
aid | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
disl | +0.094 |
killed | +0.077 |
Sorry | +0.077 |
endant | +0.076 |
Thank | +0.076 |
Neg logit contributions | |
inn | -0.048 |
ches | -0.041 |
icky | -0.040 |
kernel | -0.039 |
aid | -0.038 |
Token | cars |
Token ID | 5006 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
disl | +0.076 |
Sorry | +0.060 |
endant | +0.060 |
mm | +0.059 |
Gig | +0.058 |
Neg logit contributions | |
nie | -0.052 |
chair | -0.052 |
corner | -0.052 |
kernel | -0.051 |
aid | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
disl | +0.114 |
Sorry | +0.093 |
Gig | +0.092 |
killed | +0.092 |
endant | +0.091 |
Neg logit contributions | |
inn | -0.056 |
ches | -0.048 |
icky | -0.046 |
kernel | -0.046 |
aid | -0.045 |
Token | shops |
Token ID | 12437 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
disl | +0.075 |
Sorry | +0.060 |
endant | +0.060 |
mm | +0.059 |
Gig | +0.057 |
Neg logit contributions | |
chair | -0.050 |
nie | -0.049 |
corner | -0.048 |
aid | -0.048 |
ches | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
disl | +0.191 |
Sorry | +0.157 |
Gig | +0.153 |
killed | +0.152 |
Thank | +0.152 |
Neg logit contributions | |
inn | -0.067 |
aid | -0.062 |
ches | -0.059 |
chair | -0.059 |
' | -0.059 |
Token | They |
Token ID | 1119 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
disl | +0.038 |
Gig | +0.029 |
Thank | +0.028 |
Sorry | +0.028 |
killed | +0.028 |
Neg logit contributions | |
inn | -0.045 |
ches | -0.041 |
kernel | -0.040 |
nie | -0.040 |
icky | -0.039 |
Token | observe |
Token ID | 12414 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
disl | +0.034 |
Gig | +0.026 |
mm | +0.025 |
endant | +0.025 |
Sorry | +0.025 |
Neg logit contributions | |
inn | -0.034 |
ches | -0.033 |
kernel | -0.032 |
aid | -0.032 |
' | -0.032 |
Token | everything |
Token ID | 2279 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
disl | +0.050 |
killed | +0.041 |
statues | +0.040 |
Gig | +0.040 |
bows | +0.040 |
Neg logit contributions | |
inn | -0.039 |
ches | -0.033 |
icky | -0.033 |
kernel | -0.032 |
nie | -0.032 |
Token | with |
Token ID | 351 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
disl | +0.052 |
statues | +0.043 |
bows | +0.043 |
killed | +0.043 |
jewels | +0.042 |
Neg logit contributions | |
inn | -0.042 |
icky | -0.036 |
ches | -0.036 |
aid | -0.035 |
kernel | -0.035 |
Token | special |
Token ID | 2041 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
disl | +0.043 |
killed | +0.033 |
Thank | +0.033 |
endant | +0.033 |
Sorry | +0.033 |
Neg logit contributions | |
inn | -0.042 |
ches | -0.038 |
icky | -0.038 |
nie | -0.037 |
kernel | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
inn | +0.017 |
ches | +0.015 |
icky | +0.015 |
kernel | +0.014 |
aid | +0.014 |
Neg logit contributions | |
disl | -0.020 |
bows | -0.016 |
killed | -0.016 |
Thank | -0.016 |
statues | -0.015 |
Token | On |
Token ID | 1550 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
inn | +0.001 |
kernel | +0.001 |
ler | +0.001 |
ches | +0.000 |
nie | +0.000 |
Neg logit contributions | |
disl | -0.000 |
Gig | -0.000 |
Thank | -0.000 |
Thank | -0.000 |
Tri | -0.000 |
Token | Wed |
Token ID | 3300 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
inn | +0.043 |
ches | +0.041 |
ud | +0.039 |
ash | +0.038 |
nie | +0.038 |
Neg logit contributions | |
disl | -0.038 |
Tri | -0.029 |
Thank | -0.029 |
killed | -0.028 |
Gig | -0.028 |
Token | nes |
Token ID | 2516 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
disl | +0.070 |
Thank | +0.059 |
killed | +0.059 |
bows | +0.058 |
Sorry | +0.058 |
Neg logit contributions | |
inn | -0.029 |
ches | -0.024 |
icky | -0.024 |
kernel | -0.024 |
aid | -0.023 |
Token | days |
Token ID | 12545 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
inn | +0.009 |
kernel | +0.008 |
ches | +0.008 |
icky | +0.008 |
nie | +0.008 |
Neg logit contributions | |
disl | -0.010 |
killed | -0.007 |
bows | -0.007 |
Tri | -0.007 |
Sorry | -0.007 |
Token | she |
Token ID | 673 |
Feature activation | -7.44e-02 |
Pos logit contributions | |
disl | +0.148 |
Thank | +0.119 |
bows | +0.119 |
Sorry | +0.119 |
killed | +0.119 |
Neg logit contributions | |
inn | -0.108 |
ches | -0.096 |
kernel | -0.093 |
icky | -0.093 |
aid | -0.090 |
Token | liked |
Token ID | 8288 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
inn | +0.002 |
icky | +0.002 |
kernel | +0.002 |
ches | +0.002 |
ide | +0.002 |
Neg logit contributions | |
disl | -0.002 |
killed | -0.001 |
Thank | -0.001 |
Sorry | -0.001 |
bows | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
disl | +0.028 |
Gig | +0.023 |
killed | +0.023 |
statues | +0.023 |
Thank | +0.023 |
Neg logit contributions | |
inn | -0.016 |
ches | -0.013 |
icky | -0.013 |
kernel | -0.012 |
aid | -0.012 |
Token | count |
Token ID | 954 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
disl | +0.012 |
killed | +0.009 |
Sorry | +0.009 |
Thank | +0.009 |
bows | +0.009 |
Neg logit contributions | |
inn | -0.014 |
ches | -0.013 |
icky | -0.013 |
kernel | -0.012 |
nie | -0.012 |
Token | ! |
Token ID | 0 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
inn | +0.014 |
ches | +0.012 |
icky | +0.012 |
kernel | +0.012 |
nie | +0.012 |
Neg logit contributions | |
disl | -0.019 |
killed | -0.015 |
Gig | -0.015 |
Sorry | -0.015 |
endant | -0.015 |
Token | all |
Token ID | 477 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
inn | +0.030 |
ches | +0.027 |
icky | +0.026 |
kernel | +0.026 |
nie | +0.025 |
Neg logit contributions | |
disl | -0.033 |
killed | -0.026 |
Sorry | -0.026 |
Gig | -0.026 |
Thank | -0.026 |
Token | fixed |
Token ID | 5969 |
Feature activation | -9.17e-02 |
Pos logit contributions | |
inn | +0.034 |
ches | +0.030 |
icky | +0.030 |
kernel | +0.029 |
aid | +0.029 |
Neg logit contributions | |
disl | -0.035 |
killed | -0.027 |
Thank | -0.026 |
endant | -0.026 |
bows | -0.026 |
Token | up |
Token ID | 510 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
inn | +0.002 |
icky | +0.002 |
kernel | +0.002 |
ches | +0.002 |
aid | +0.002 |
Neg logit contributions | |
disl | -0.003 |
bows | -0.002 |
killed | -0.002 |
jewels | -0.002 |
statues | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
inn | +0.036 |
ches | +0.032 |
icky | +0.031 |
kernel | +0.031 |
nie | +0.030 |
Neg logit contributions | |
disl | -0.054 |
killed | -0.043 |
Gig | -0.043 |
Sorry | -0.042 |
Thank | -0.042 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
disl | +0.001 |
endant | +0.001 |
killed | +0.001 |
Gig | +0.001 |
Sorry | +0.001 |
Neg logit contributions | |
inn | -0.001 |
ches | -0.001 |
kernel | -0.001 |
nie | -0.001 |
icky | -0.001 |
Token | brand |
Token ID | 4508 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
disl | +0.039 |
mm | +0.032 |
Sorry | +0.031 |
Gig | +0.030 |
killed | +0.030 |
Neg logit contributions | |
inn | -0.028 |
ches | -0.025 |
nie | -0.025 |
again | -0.024 |
kernel | -0.023 |
Token | new |
Token ID | 649 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
disl | +0.137 |
killed | +0.107 |
Sorry | +0.105 |
Thank | +0.105 |
endant | +0.105 |
Neg logit contributions | |
inn | -0.121 |
ches | -0.108 |
icky | -0.107 |
kernel | -0.105 |
aid | -0.104 |
Token | ! |
Token ID | 0 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
disl | +0.019 |
Sorry | +0.015 |
Thank | +0.015 |
Gig | +0.015 |
killed | +0.015 |
Neg logit contributions | |
inn | -0.010 |
ches | -0.009 |
icky | -0.008 |
nie | -0.008 |
aid | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
ches | +0.030 |
inn | +0.030 |
kernel | +0.028 |
ler | +0.028 |
le | +0.028 |
Neg logit contributions | |
disl | -0.024 |
Thank | -0.021 |
Sorry | -0.020 |
Gig | -0.020 |
Thank | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
inn | +0.015 |
ches | +0.015 |
kernel | +0.015 |
ler | +0.015 |
nie | +0.015 |
Neg logit contributions | |
disl | -0.008 |
Thank | -0.006 |
lucky | -0.006 |
Thank | -0.006 |
Gig | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
disl | +0.008 |
Thank | +0.008 |
lucky | +0.007 |
Thank | +0.006 |
Sorry | +0.006 |
Neg logit contributions | |
inn | -0.008 |
ches | -0.008 |
icky | -0.008 |
ig | -0.008 |
ash | -0.008 |
Token | see |
Token ID | 766 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
disl | +0.034 |
mm | +0.027 |
Gig | +0.027 |
endant | +0.026 |
Sorry | +0.025 |
Neg logit contributions | |
aid | -0.033 |
' | -0.032 |
ches | -0.032 |
chair | -0.031 |
inn | -0.031 |
Token | cars |
Token ID | 5006 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
disl | +0.036 |
Sorry | +0.029 |
Thank | +0.029 |
endant | +0.029 |
killed | +0.028 |
Neg logit contributions | |
inn | -0.024 |
kernel | -0.022 |
icky | -0.021 |
ches | -0.021 |
aid | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
disl | +0.085 |
Gig | +0.069 |
Sorry | +0.069 |
killed | +0.069 |
endant | +0.069 |
Neg logit contributions | |
inn | -0.042 |
ches | -0.037 |
icky | -0.036 |
kernel | -0.035 |
aid | -0.034 |
Token | trees |
Token ID | 7150 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
disl | +0.050 |
endant | +0.042 |
mm | +0.041 |
Gig | +0.041 |
Sorry | +0.041 |
Neg logit contributions | |
chair | -0.034 |
mat | -0.034 |
kernel | -0.033 |
inn | -0.032 |
aid | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
disl | +0.088 |
killed | +0.072 |
Gig | +0.071 |
Thank | +0.071 |
endant | +0.070 |
Neg logit contributions | |
inn | -0.051 |
ches | -0.044 |
icky | -0.044 |
kernel | -0.042 |
nie | -0.042 |
Token | shops |
Token ID | 12437 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
disl | +0.074 |
endant | +0.061 |
mm | +0.060 |
Sorry | +0.060 |
Gig | +0.058 |
Neg logit contributions | |
chair | -0.049 |
corner | -0.048 |
ches | -0.047 |
kernel | -0.047 |
nie | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
disl | +0.185 |
Sorry | +0.152 |
Gig | +0.149 |
killed | +0.149 |
Thank | +0.148 |
Neg logit contributions | |
inn | -0.068 |
aid | -0.061 |
kernel | -0.059 |
ches | -0.059 |
chair | -0.058 |
Token | people |
Token ID | 661 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
disl | +0.070 |
mm | +0.059 |
endant | +0.059 |
Sorry | +0.057 |
Gig | +0.056 |
Neg logit contributions | |
corner | -0.045 |
chair | -0.045 |
aid | -0.044 |
kernel | -0.043 |
mat | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
disl | +0.111 |
Sorry | +0.090 |
Gig | +0.090 |
killed | +0.089 |
Thank | +0.089 |
Neg logit contributions | |
inn | -0.060 |
ches | -0.053 |
icky | -0.052 |
kernel | -0.051 |
aid | -0.051 |
Token | They |
Token ID | 1119 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
disl | +0.061 |
killed | +0.048 |
endant | +0.048 |
jewels | +0.046 |
Sorry | +0.046 |
Neg logit contributions | |
inn | -0.053 |
icky | -0.048 |
aid | -0.047 |
ches | -0.045 |
kernel | -0.045 |
Token | are |
Token ID | 389 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
disl | +0.037 |
mm | +0.031 |
Gig | +0.031 |
endant | +0.030 |
Sorry | +0.029 |
Neg logit contributions | |
aid | -0.033 |
' | -0.033 |
chair | -0.033 |
inn | -0.032 |
scrub | -0.032 |
Token | disappointment |
Token ID | 18641 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
inn | +0.001 |
ches | +0.001 |
icky | +0.001 |
nie | +0.001 |
kernel | +0.001 |
Neg logit contributions | |
disl | -0.001 |
killed | -0.001 |
Thank | -0.001 |
Gig | -0.001 |
Sorry | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
disl | +0.046 |
killed | +0.037 |
jewels | +0.036 |
statues | +0.036 |
Thank | +0.036 |
Neg logit contributions | |
inn | -0.043 |
icky | -0.038 |
ches | -0.037 |
kernel | -0.037 |
nie | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
inn | +0.036 |
ches | +0.033 |
kernel | +0.032 |
icky | +0.031 |
nie | +0.031 |
Neg logit contributions | |
disl | -0.039 |
Gig | -0.031 |
Sorry | -0.030 |
Thank | -0.030 |
killed | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
inn | +0.029 |
kernel | +0.028 |
ches | +0.027 |
nie | +0.026 |
ler | +0.026 |
Neg logit contributions | |
disl | -0.032 |
Gig | -0.025 |
Thank | -0.025 |
killed | -0.024 |
Tri | -0.024 |
Token | M |
Token ID | 44 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
inn | +0.009 |
ches | +0.009 |
kernel | +0.009 |
icky | +0.008 |
nie | +0.008 |
Neg logit contributions | |
disl | -0.010 |
Thank | -0.008 |
Gig | -0.008 |
Sorry | -0.008 |
killed | -0.008 |
Token | arl |
Token ID | 7063 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
inn | +0.014 |
ches | +0.012 |
icky | +0.011 |
kernel | +0.011 |
nie | +0.011 |
Neg logit contributions | |
disl | -0.025 |
killed | -0.020 |
Gig | -0.020 |
Sorry | -0.020 |
endant | -0.020 |
Token | on |
Token ID | 261 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
disl | +0.115 |
killed | +0.090 |
Thank | +0.089 |
bows | +0.088 |
Gig | +0.087 |
Neg logit contributions | |
inn | -0.133 |
ches | -0.121 |
icky | -0.120 |
nie | -0.119 |
kernel | -0.118 |
Token | 's |
Token ID | 338 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
inn | +0.028 |
ash | +0.024 |
mat | +0.024 |
icky | +0.024 |
ud | +0.024 |
Neg logit contributions | |
disl | -0.025 |
killed | -0.021 |
endant | -0.019 |
Thank | -0.019 |
jewels | -0.019 |
Token | mum |
Token ID | 25682 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
inn | +0.026 |
ches | +0.023 |
icky | +0.022 |
kernel | +0.022 |
ide | +0.022 |
Neg logit contributions | |
disl | -0.026 |
killed | -0.021 |
jewels | -0.020 |
endant | -0.020 |
Gig | -0.020 |
Token | hugged |
Token ID | 41130 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
disl | +0.017 |
killed | +0.014 |
Thank | +0.013 |
Gig | +0.013 |
endant | +0.013 |
Neg logit contributions | |
inn | -0.022 |
icky | -0.019 |
kernel | -0.019 |
ches | -0.018 |
mat | -0.018 |
Token | him |
Token ID | 683 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
disl | +0.022 |
Gig | +0.019 |
Thank | +0.018 |
Tri | +0.018 |
Sorry | +0.017 |
Neg logit contributions | |
inn | -0.026 |
icky | -0.023 |
ches | -0.023 |
kernel | -0.023 |
aid | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
disl | +0.046 |
Gig | +0.038 |
Sorry | +0.038 |
killed | +0.038 |
Thank | +0.037 |
Neg logit contributions | |
inn | -0.021 |
ches | -0.018 |
icky | -0.017 |
kernel | -0.017 |
aid | -0.017 |
Token | bridges |
Token ID | 19432 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
disl | +0.078 |
Gig | +0.066 |
Sorry | +0.064 |
mm | +0.063 |
endant | +0.063 |
Neg logit contributions | |
inn | -0.044 |
chair | -0.044 |
aid | -0.043 |
kernel | -0.043 |
scrub | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
disl | +0.085 |
Gig | +0.071 |
Sorry | +0.071 |
killed | +0.070 |
endant | +0.069 |
Neg logit contributions | |
inn | -0.037 |
ches | -0.031 |
icky | -0.031 |
aid | -0.030 |
kernel | -0.030 |
Token | parks |
Token ID | 14860 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
disl | +0.105 |
Gig | +0.087 |
Sorry | +0.085 |
mm | +0.084 |
endant | +0.084 |
Neg logit contributions | |
inn | -0.059 |
aid | -0.059 |
chair | -0.058 |
corner | -0.058 |
kernel | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
disl | +0.061 |
statues | +0.050 |
killed | +0.050 |
bows | +0.049 |
jewels | +0.049 |
Neg logit contributions | |
inn | -0.049 |
icky | -0.043 |
ches | -0.042 |
nie | -0.042 |
kernel | -0.040 |
Token | shops |
Token ID | 12437 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
disl | +0.099 |
Gig | +0.081 |
mm | +0.081 |
endant | +0.079 |
Sorry | +0.078 |
Neg logit contributions | |
corner | -0.058 |
aid | -0.058 |
chair | -0.057 |
again | -0.056 |
inn | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
disl | +0.186 |
Sorry | +0.155 |
Gig | +0.152 |
mm | +0.149 |
Thank | +0.149 |
Neg logit contributions | |
inn | -0.064 |
aid | -0.059 |
again | -0.057 |
chair | -0.057 |
ches | -0.056 |
Token | schools |
Token ID | 4266 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
disl | +0.087 |
mm | +0.073 |
Gig | +0.072 |
endant | +0.072 |
Sorry | +0.072 |
Neg logit contributions | |
aid | -0.051 |
corner | -0.051 |
chair | -0.050 |
again | -0.050 |
scrub | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
disl | +0.108 |
Sorry | +0.088 |
Gig | +0.088 |
killed | +0.087 |
endant | +0.087 |
Neg logit contributions | |
inn | -0.054 |
ches | -0.047 |
icky | -0.045 |
aid | -0.045 |
kernel | -0.045 |
Token | hospitals |
Token ID | 11301 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
disl | +0.072 |
mm | +0.061 |
Gig | +0.061 |
Sorry | +0.059 |
endant | +0.059 |
Neg logit contributions | |
corner | -0.043 |
chair | -0.042 |
aid | -0.042 |
again | -0.041 |
scrub | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
disl | +0.062 |
killed | +0.050 |
Sorry | +0.050 |
Gig | +0.050 |
endant | +0.050 |
Neg logit contributions | |
inn | -0.040 |
ches | -0.035 |
icky | -0.035 |
kernel | -0.034 |
nie | -0.033 |
Token | It |
Token ID | 632 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
disl | +0.006 |
killed | +0.005 |
endant | +0.005 |
Gig | +0.005 |
bows | +0.005 |
Neg logit contributions | |
inn | -0.004 |
icky | -0.004 |
ches | -0.004 |
aid | -0.004 |
nie | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
disl | +0.030 |
killed | +0.025 |
Thank | +0.024 |
endant | +0.024 |
Tri | +0.024 |
Neg logit contributions | |
inn | -0.020 |
icky | -0.018 |
ches | -0.017 |
kernel | -0.017 |
aid | -0.017 |
Token | fixed |
Token ID | 5969 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
inn | +0.010 |
ches | +0.008 |
icky | +0.008 |
kernel | +0.008 |
nie | +0.008 |
Neg logit contributions | |
disl | -0.011 |
Sorry | -0.009 |
bows | -0.009 |
killed | -0.008 |
endant | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
inn | +0.006 |
icky | +0.005 |
kernel | +0.005 |
ches | +0.005 |
aid | +0.005 |
Neg logit contributions | |
disl | -0.007 |
killed | -0.006 |
bows | -0.005 |
jewels | -0.005 |
statues | -0.005 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
disl | +0.012 |
bows | +0.009 |
Sorry | +0.009 |
endant | +0.009 |
Gig | +0.009 |
Neg logit contributions | |
inn | -0.009 |
ches | -0.007 |
nie | -0.007 |
kernel | -0.007 |
chair | -0.007 |
Token | brand |
Token ID | 4508 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
disl | +0.059 |
bows | +0.047 |
Sorry | +0.047 |
Gig | +0.046 |
mm | +0.046 |
Neg logit contributions | |
inn | -0.040 |
again | -0.037 |
ches | -0.037 |
nie | -0.034 |
scrub | -0.032 |
Token | new |
Token ID | 649 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
disl | +0.138 |
killed | +0.109 |
Gig | +0.107 |
Sorry | +0.107 |
Thank | +0.107 |
Neg logit contributions | |
inn | -0.115 |
ches | -0.102 |
icky | -0.101 |
kernel | -0.098 |
nie | -0.098 |
Token | ! |
Token ID | 0 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
disl | +0.024 |
killed | +0.019 |
Sorry | +0.019 |
Gig | +0.019 |
Thank | +0.019 |
Neg logit contributions | |
inn | -0.014 |
ches | -0.012 |
icky | -0.012 |
kernel | -0.012 |
nie | -0.012 |
Token | Tim |
Token ID | 5045 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
inn | +0.012 |
icky | +0.010 |
ches | +0.010 |
nie | +0.010 |
aid | +0.010 |
Neg logit contributions | |
disl | -0.016 |
killed | -0.013 |
endant | -0.013 |
bows | -0.013 |
jewels | -0.012 |
Token | my |
Token ID | 1820 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
inn | +0.018 |
kernel | +0.015 |
icky | +0.015 |
ches | +0.015 |
aid | +0.015 |
Neg logit contributions | |
disl | -0.020 |
killed | -0.016 |
Thank | -0.016 |
endant | -0.016 |
bows | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
inn | +0.010 |
ches | +0.009 |
icky | +0.009 |
kernel | +0.008 |
nie | +0.008 |
Neg logit contributions | |
disl | -0.014 |
killed | -0.011 |
Gig | -0.011 |
Sorry | -0.011 |
endant | -0.011 |
Token | famous |
Token ID | 5863 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
disl | +0.024 |
Sorry | +0.019 |
bows | +0.018 |
endant | +0.018 |
Gig | +0.018 |
Neg logit contributions | |
inn | -0.022 |
ches | -0.019 |
icky | -0.019 |
kernel | -0.019 |
aid | -0.019 |
Token | ! |
Token ID | 0 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
disl | +0.009 |
Sorry | +0.008 |
Gig | +0.007 |
killed | +0.007 |
Thank | +0.007 |
Neg logit contributions | |
inn | -0.006 |
ches | -0.005 |
icky | -0.005 |
aid | -0.005 |
nie | -0.005 |
Token | And |
Token ID | 843 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
inn | +0.032 |
ches | +0.029 |
kernel | +0.029 |
icky | +0.028 |
nie | +0.028 |
Neg logit contributions | |
disl | -0.033 |
Gig | -0.025 |
Sorry | -0.025 |
Thank | -0.025 |
killed | -0.025 |
Token | when |
Token ID | 618 |
Feature activation | -9.03e-02 |
Pos logit contributions | |
disl | +0.028 |
endant | +0.023 |
killed | +0.023 |
bows | +0.022 |
Gig | +0.022 |
Neg logit contributions | |
inn | -0.019 |
nie | -0.017 |
icky | -0.017 |
kernel | -0.017 |
Alex | -0.017 |
Token | his |
Token ID | 465 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
inn | +0.002 |
icky | +0.002 |
Alex | +0.002 |
nie | +0.002 |
kernel | +0.002 |
Neg logit contributions | |
disl | -0.003 |
endant | -0.002 |
bows | -0.002 |
Thank | -0.002 |
killed | -0.002 |
Token | story |
Token ID | 1621 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
inn | +0.001 |
aid | +0.001 |
icky | +0.001 |
kernel | +0.001 |
ches | +0.001 |
Neg logit contributions | |
disl | -0.001 |
Thank | -0.001 |
Gig | -0.001 |
killed | -0.001 |
bows | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
disl | +0.140 |
Gig | +0.113 |
endant | +0.111 |
killed | +0.108 |
Tri | +0.108 |
Neg logit contributions | |
inn | -0.107 |
ches | -0.097 |
icky | -0.095 |
nie | -0.091 |
kernel | -0.090 |
Token | told |
Token ID | 1297 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
disl | +0.016 |
Sorry | +0.012 |
Gig | +0.012 |
killed | +0.012 |
endant | +0.012 |
Neg logit contributions | |
inn | -0.017 |
ches | -0.015 |
icky | -0.015 |
nie | -0.015 |
kernel | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
disl | +0.055 |
endant | +0.046 |
Thank | +0.045 |
killed | +0.044 |
bows | +0.044 |
Neg logit contributions | |
inn | -0.036 |
ches | -0.033 |
icky | -0.032 |
nie | -0.031 |
aid | -0.031 |
Token | everyone |
Token ID | 2506 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
inn | +0.013 |
ches | +0.011 |
icky | +0.011 |
kernel | +0.011 |
nie | +0.011 |
Neg logit contributions | |
disl | -0.018 |
endant | -0.015 |
killed | -0.014 |
bows | -0.014 |
Thank | -0.014 |
Token | who |
Token ID | 508 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
disl | +0.030 |
killed | +0.024 |
Sorry | +0.023 |
Gig | +0.023 |
Thank | +0.023 |
Neg logit contributions | |
inn | -0.026 |
ches | -0.023 |
icky | -0.023 |
kernel | -0.022 |
aid | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
inn | +0.017 |
ches | +0.015 |
nie | +0.014 |
icky | +0.014 |
kernel | +0.014 |
Neg logit contributions | |
disl | -0.031 |
killed | -0.026 |
Gig | -0.025 |
Thank | -0.025 |
bows | -0.024 |
Token | grow |
Token ID | 1663 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
disl | +0.015 |
endant | +0.013 |
mm | +0.012 |
Sorry | +0.012 |
killed | +0.012 |
Neg logit contributions | |
inn | -0.014 |
ches | -0.014 |
aid | -0.014 |
icky | -0.013 |
kernel | -0.013 |
Token | l |
Token ID | 75 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
disl | +0.036 |
killed | +0.029 |
Gig | +0.029 |
Thank | +0.028 |
endant | +0.028 |
Neg logit contributions | |
inn | -0.024 |
ches | -0.021 |
icky | -0.021 |
kernel | -0.020 |
nie | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
disl | +0.014 |
bows | +0.013 |
killed | +0.012 |
endant | +0.012 |
statues | +0.011 |
Neg logit contributions | |
inn | -0.013 |
kernel | -0.011 |
nie | -0.011 |
strand | -0.011 |
aid | -0.011 |
Token | sn |
Token ID | 3013 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
disl | +0.008 |
mm | +0.007 |
endant | +0.007 |
bows | +0.006 |
Thank | +0.006 |
Neg logit contributions | |
inn | -0.008 |
ches | -0.007 |
aid | -0.007 |
kernel | -0.007 |
icky | -0.007 |
Token | arl |
Token ID | 7063 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
disl | +0.042 |
statues | +0.034 |
jewels | +0.034 |
killed | +0.033 |
Sorry | +0.032 |
Neg logit contributions | |
inn | -0.034 |
ches | -0.030 |
icky | -0.028 |
ash | -0.027 |
kernel | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
disl | +0.151 |
killed | +0.124 |
Gig | +0.122 |
bows | +0.122 |
Sorry | +0.121 |
Neg logit contributions | |
inn | -0.095 |
ches | -0.082 |
icky | -0.081 |
kernel | -0.080 |
nie | -0.079 |
Token | try |
Token ID | 1949 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
disl | +0.024 |
endant | +0.020 |
killed | +0.019 |
Sorry | +0.019 |
mm | +0.019 |
Neg logit contributions | |
inn | -0.020 |
ches | -0.019 |
aid | -0.019 |
icky | -0.018 |
kernel | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
inn | +0.021 |
nie | +0.018 |
kernel | +0.018 |
icky | +0.017 |
ud | +0.017 |
Neg logit contributions | |
disl | -0.028 |
Gig | -0.023 |
statues | -0.022 |
bows | -0.022 |
killed | -0.022 |
Token | scare |
Token ID | 19437 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
disl | +0.017 |
endant | +0.014 |
mm | +0.014 |
bows | +0.013 |
Gig | +0.013 |
Neg logit contributions | |
inn | -0.014 |
aid | -0.014 |
ches | -0.014 |
kernel | -0.013 |
icky | -0.013 |
Token | her |
Token ID | 607 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
inn | +0.005 |
ches | +0.004 |
icky | +0.004 |
kernel | +0.004 |
nie | +0.004 |
Neg logit contributions | |
disl | -0.007 |
killed | -0.006 |
Gig | -0.006 |
Sorry | -0.006 |
Thank | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
disl | +0.045 |
killed | +0.036 |
Sorry | +0.036 |
Gig | +0.036 |
endant | +0.036 |
Neg logit contributions | |
inn | -0.028 |
ches | -0.024 |
icky | -0.024 |
kernel | -0.023 |
nie | -0.023 |
Token | cozy |
Token ID | 37438 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
disl | +0.017 |
statues | +0.015 |
bows | +0.015 |
endant | +0.015 |
Gig | +0.014 |
Neg logit contributions | |
scrub | -0.015 |
's | -0.014 |
ches | -0.014 |
' | -0.014 |
nie | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
disl | +0.051 |
killed | +0.041 |
Sorry | +0.041 |
Gig | +0.041 |
endant | +0.041 |
Neg logit contributions | |
inn | -0.033 |
ches | -0.029 |
icky | -0.028 |
kernel | -0.028 |
nie | -0.027 |
Token | her |
Token ID | 607 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
disl | +0.050 |
killed | +0.040 |
endant | +0.040 |
Sorry | +0.040 |
bows | +0.039 |
Neg logit contributions | |
inn | -0.034 |
ches | -0.029 |
icky | -0.029 |
kernel | -0.028 |
aid | -0.028 |
Token | p |
Token ID | 279 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
disl | +0.032 |
killed | +0.026 |
Gig | +0.025 |
Sorry | +0.025 |
Thank | +0.025 |
Neg logit contributions | |
inn | -0.025 |
ches | -0.022 |
icky | -0.021 |
kernel | -0.021 |
nie | -0.021 |
Token | aj |
Token ID | 1228 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
disl | +0.057 |
Thank | +0.047 |
Gig | +0.046 |
killed | +0.045 |
Sorry | +0.045 |
Neg logit contributions | |
inn | -0.053 |
ches | -0.048 |
icky | -0.047 |
aid | -0.045 |
ash | -0.045 |
Token | amas |
Token ID | 17485 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
disl | +0.171 |
killed | +0.143 |
Gig | +0.140 |
Sorry | +0.140 |
Thank | +0.140 |
Neg logit contributions | |
inn | -0.077 |
ches | -0.065 |
icky | -0.065 |
nie | -0.061 |
kernel | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
disl | +0.060 |
killed | +0.049 |
Thank | +0.048 |
Gig | +0.048 |
Sorry | +0.048 |
Neg logit contributions | |
inn | -0.041 |
ches | -0.036 |
icky | -0.035 |
kernel | -0.034 |
nie | -0.034 |
Token | even |
Token ID | 772 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
inn | +0.006 |
ches | +0.005 |
icky | +0.005 |
kernel | +0.005 |
nie | +0.005 |
Neg logit contributions | |
disl | -0.006 |
killed | -0.004 |
Gig | -0.004 |
Thank | -0.004 |
Sorry | -0.004 |
Token | though |
Token ID | 996 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
inn | +0.001 |
icky | +0.001 |
ches | +0.001 |
kernel | +0.001 |
ud | +0.001 |
Neg logit contributions | |
disl | -0.001 |
Thank | -0.001 |
killed | -0.001 |
jewels | -0.001 |
Gig | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
inn | +0.011 |
ches | +0.010 |
icky | +0.009 |
nie | +0.009 |
ash | +0.009 |
Neg logit contributions | |
disl | -0.008 |
Gig | -0.006 |
killed | -0.006 |
jewels | -0.006 |
statues | -0.006 |
Token | Spot |
Token ID | 32565 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
disl | +0.012 |
Thank | +0.010 |
killed | +0.009 |
Gig | +0.009 |
Sorry | +0.009 |
Neg logit contributions | |
inn | -0.013 |
icky | -0.012 |
ches | -0.012 |
kernel | -0.012 |
nie | -0.012 |
Token | grow |
Token ID | 1663 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
disl | +0.021 |
killed | +0.016 |
Thank | +0.015 |
Sorry | +0.015 |
bows | +0.015 |
Neg logit contributions | |
inn | -0.025 |
icky | -0.022 |
ches | -0.022 |
nie | -0.022 |
kernel | -0.022 |
Token | ls |
Token ID | 7278 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
disl | +0.051 |
killed | +0.043 |
statues | +0.041 |
jewels | +0.040 |
bows | +0.039 |
Neg logit contributions | |
inn | -0.066 |
aid | -0.060 |
nie | -0.060 |
pron | -0.060 |
kernel | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
inn | +0.009 |
nie | +0.008 |
icky | +0.008 |
kernel | +0.008 |
ches | +0.008 |
Neg logit contributions | |
disl | -0.013 |
killed | -0.011 |
Thank | -0.011 |
Gig | -0.011 |
jewels | -0.011 |
Token | sn |
Token ID | 3013 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
disl | +0.019 |
killed | +0.015 |
endant | +0.015 |
Gig | +0.015 |
Thank | +0.015 |
Neg logit contributions | |
inn | -0.019 |
ches | -0.018 |
icky | -0.017 |
kernel | -0.017 |
aid | -0.017 |
Token | arl |
Token ID | 7063 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
disl | +0.025 |
killed | +0.020 |
Thank | +0.020 |
Sorry | +0.020 |
Gig | +0.019 |
Neg logit contributions | |
inn | -0.020 |
ches | -0.018 |
icky | -0.018 |
kernel | -0.017 |
nie | -0.017 |
Token | s |
Token ID | 82 |
Feature activation | +2.93e-04 |
Pos logit contributions | |
disl | +0.148 |
killed | +0.122 |
Sorry | +0.120 |
Gig | +0.119 |
bows | +0.119 |
Neg logit contributions | |
inn | -0.096 |
ches | -0.084 |
nie | -0.082 |
icky | -0.081 |
kernel | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
disl | +0.000 |
killed | +0.000 |
Thank | +0.000 |
jewels | +0.000 |
Gig | +0.000 |
Neg logit contributions | |
inn | -0.000 |
nie | -0.000 |
icky | -0.000 |
ash | -0.000 |
oby | -0.000 |
Token | He |
Token ID | 679 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
disl | +0.025 |
Gig | +0.020 |
killed | +0.019 |
Thank | +0.019 |
Sorry | +0.019 |
Neg logit contributions | |
inn | -0.029 |
ches | -0.027 |
nie | -0.027 |
kernel | -0.026 |
icky | -0.026 |
Token | tries |
Token ID | 8404 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
disl | +0.005 |
killed | +0.004 |
Gig | +0.004 |
Sorry | +0.004 |
Thank | +0.004 |
Neg logit contributions | |
inn | -0.005 |
ches | -0.005 |
icky | -0.005 |
kernel | -0.005 |
nie | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
inn | +0.029 |
nie | +0.027 |
kernel | +0.026 |
ler | +0.026 |
ches | +0.026 |
Neg logit contributions | |
disl | -0.034 |
killed | -0.029 |
Gig | -0.028 |
Thank | -0.027 |
Gold | -0.027 |
Token | took |
Token ID | 1718 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
disl | +0.030 |
Sorry | +0.022 |
endant | +0.021 |
bows | +0.021 |
statues | +0.021 |
Neg logit contributions | |
inn | -0.027 |
ches | -0.025 |
nie | -0.024 |
' | -0.024 |
kernel | -0.024 |
Token | their |
Token ID | 511 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
inn | +0.020 |
pron | +0.017 |
nie | +0.017 |
icky | +0.017 |
kernel | +0.017 |
Neg logit contributions | |
disl | -0.025 |
killed | -0.021 |
Gig | -0.021 |
Tri | -0.021 |
jewels | -0.021 |
Token | hats |
Token ID | 23910 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
disl | +0.031 |
Thank | +0.026 |
Sorry | +0.025 |
bows | +0.025 |
mm | +0.025 |
Neg logit contributions | |
inn | -0.023 |
aid | -0.022 |
ches | -0.022 |
chair | -0.021 |
kernel | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
disl | +0.029 |
killed | +0.024 |
Gig | +0.024 |
bows | +0.024 |
endant | +0.024 |
Neg logit contributions | |
inn | -0.019 |
icky | -0.017 |
ches | -0.016 |
nie | -0.016 |
kernel | -0.016 |
Token | bin |
Token ID | 9874 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
disl | +0.038 |
Sorry | +0.031 |
bows | +0.031 |
endant | +0.030 |
mm | +0.030 |
Neg logit contributions | |
inn | -0.027 |
ches | -0.026 |
aid | -0.025 |
kernel | -0.024 |
chair | -0.024 |
Token | ocular |
Token ID | 37320 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
disl | +0.059 |
Sorry | +0.042 |
killed | +0.041 |
Thank | +0.041 |
Gig | +0.040 |
Neg logit contributions | |
inn | -0.082 |
ches | -0.075 |
icky | -0.073 |
kernel | -0.073 |
aid | -0.073 |
Token | s |
Token ID | 82 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
disl | +0.176 |
Thank | +0.144 |
Sorry | +0.144 |
killed | +0.143 |
Gig | +0.142 |
Neg logit contributions | |
inn | -0.072 |
ches | -0.066 |
icky | -0.056 |
kernel | -0.056 |
nie | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
disl | +0.027 |
Sorry | +0.022 |
Thank | +0.022 |
killed | +0.022 |
Gig | +0.022 |
Neg logit contributions | |
inn | -0.011 |
ches | -0.010 |
aid | -0.009 |
icky | -0.009 |
kernel | -0.009 |
Token | stuffed |
Token ID | 22259 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
disl | +0.039 |
Sorry | +0.034 |
mm | +0.033 |
endant | +0.031 |
bows | +0.031 |
Neg logit contributions | |
aid | -0.024 |
ches | -0.024 |
chair | -0.024 |
inn | -0.024 |
scrub | -0.024 |
Token | animals |
Token ID | 4695 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
disl | +0.011 |
Sorry | +0.009 |
endant | +0.008 |
Thank | +0.008 |
killed | +0.008 |
Neg logit contributions | |
inn | -0.008 |
ches | -0.008 |
icky | -0.007 |
kernel | -0.007 |
nie | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
disl | +0.051 |
killed | +0.042 |
jewels | +0.041 |
endant | +0.040 |
Gig | +0.040 |
Neg logit contributions | |
inn | -0.043 |
icky | -0.038 |
nie | -0.037 |
ches | -0.036 |
kernel | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
inn | +0.011 |
ches | +0.010 |
ool | +0.010 |
icky | +0.009 |
nie | +0.009 |
Neg logit contributions | |
disl | -0.008 |
Gig | -0.007 |
Thank | -0.007 |
statues | -0.007 |
jewels | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
disl | +0.021 |
endant | +0.017 |
killed | +0.016 |
Sorry | +0.016 |
bows | +0.016 |
Neg logit contributions | |
inn | -0.018 |
ches | -0.016 |
icky | -0.016 |
kernel | -0.016 |
nie | -0.016 |
Token | noticed |
Token ID | 6810 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
inn | +0.020 |
icky | +0.018 |
kernel | +0.017 |
ches | +0.017 |
aid | +0.017 |
Neg logit contributions | |
disl | -0.014 |
killed | -0.012 |
Thank | -0.011 |
statues | -0.010 |
Gig | -0.010 |
Token | something |
Token ID | 1223 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
disl | +0.012 |
killed | +0.009 |
Gig | +0.009 |
statues | +0.009 |
endant | +0.009 |
Neg logit contributions | |
inn | -0.014 |
ches | -0.012 |
icky | -0.012 |
nie | -0.012 |
kernel | -0.012 |
Token | shiny |
Token ID | 22441 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
disl | +0.023 |
killed | +0.017 |
statues | +0.016 |
jewels | +0.016 |
Tri | +0.016 |
Neg logit contributions | |
inn | -0.037 |
nie | -0.035 |
icky | -0.034 |
ud | -0.034 |
ches | -0.034 |
Token | wed |
Token ID | 29445 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
inn | +0.015 |
icky | +0.013 |
ches | +0.013 |
aid | +0.013 |
nie | +0.013 |
Neg logit contributions | |
disl | -0.023 |
killed | -0.019 |
endant | -0.019 |
jewels | -0.019 |
bows | -0.019 |
Token | ged |
Token ID | 2004 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
crib | +0.164 |
mat | +0.162 |
aid | +0.162 |
icky | +0.159 |
chair | +0.157 |
Neg logit contributions | |
disl | -0.125 |
killed | -0.110 |
Gig | -0.104 |
Tri | -0.102 |
jewels | -0.101 |
Token | between |
Token ID | 1022 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
inn | +0.067 |
ches | +0.059 |
kernel | +0.059 |
icky | +0.059 |
aid | +0.058 |
Neg logit contributions | |
disl | -0.110 |
killed | -0.093 |
jewels | -0.093 |
Gig | -0.092 |
Tri | -0.092 |
Token | some |
Token ID | 617 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
inn | +0.065 |
ches | +0.061 |
nie | +0.059 |
kernel | +0.057 |
pron | +0.055 |
Neg logit contributions | |
disl | -0.086 |
jewels | -0.072 |
Gig | -0.072 |
Tri | -0.072 |
killed | -0.071 |
Token | branches |
Token ID | 13737 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
inn | +0.011 |
ches | +0.010 |
icky | +0.010 |
nie | +0.010 |
kernel | +0.010 |
Neg logit contributions | |
disl | -0.010 |
killed | -0.008 |
jewels | -0.008 |
statues | -0.008 |
endant | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
inn | +0.039 |
nie | +0.036 |
Alex | +0.035 |
icky | +0.034 |
aid | +0.034 |
Neg logit contributions | |
disl | -0.037 |
killed | -0.031 |
endant | -0.030 |
bows | -0.030 |
Gig | -0.029 |
Token | so |
Token ID | 523 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
inn | +0.019 |
ches | +0.017 |
icky | +0.017 |
kernel | +0.016 |
nie | +0.016 |
Neg logit contributions | |
disl | -0.022 |
killed | -0.018 |
Thank | -0.017 |
Gig | -0.017 |
Sorry | -0.017 |
Token | he |
Token ID | 339 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
disl | +0.003 |
bows | +0.003 |
endant | +0.003 |
Sorry | +0.003 |
Thank | +0.003 |
Neg logit contributions | |
inn | -0.002 |
kernel | -0.002 |
icky | -0.002 |
ches | -0.002 |
aid | -0.002 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
inn | +0.031 |
icky | +0.029 |
ches | +0.028 |
kernel | +0.028 |
aid | +0.027 |
Neg logit contributions | |
disl | -0.020 |
killed | -0.015 |
Thank | -0.015 |
Gig | -0.015 |
Sorry | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
inn | +0.004 |
kernel | +0.003 |
ches | +0.003 |
ud | +0.003 |
icky | +0.003 |
Neg logit contributions | |
disl | -0.004 |
Gig | -0.003 |
jewels | -0.003 |
Tri | -0.003 |
statues | -0.003 |
Token | ch |
Token ID | 442 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
inn | +0.009 |
icky | +0.008 |
aid | +0.008 |
ches | +0.008 |
kernel | +0.008 |
Neg logit contributions | |
disl | -0.012 |
endant | -0.010 |
killed | -0.010 |
Sorry | -0.010 |
Gig | -0.010 |
Token | ame |
Token ID | 480 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
inn | +0.014 |
ches | +0.013 |
kernel | +0.013 |
nie | +0.012 |
aid | +0.012 |
Neg logit contributions | |
disl | -0.019 |
killed | -0.015 |
endant | -0.015 |
Tri | -0.014 |
Gig | -0.014 |
Token | leon |
Token ID | 38970 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
inn | +0.112 |
ud | +0.101 |
mat | +0.095 |
ches | +0.095 |
nie | +0.094 |
Neg logit contributions | |
disl | -0.176 |
Tri | -0.151 |
Gig | -0.151 |
lucky | -0.146 |
jewels | -0.145 |
Token | to |
Token ID | 284 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
inn | +0.040 |
ches | +0.034 |
icky | +0.033 |
kernel | +0.033 |
nie | +0.033 |
Neg logit contributions | |
disl | -0.060 |
killed | -0.049 |
Gig | -0.049 |
endant | -0.048 |
bows | -0.048 |
Token | play |
Token ID | 711 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
inn | +0.006 |
ches | +0.006 |
aid | +0.006 |
kernel | +0.006 |
icky | +0.006 |
Neg logit contributions | |
disl | -0.006 |
endant | -0.005 |
killed | -0.004 |
bows | -0.004 |
Gig | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
inn | +0.007 |
nie | +0.007 |
ud | +0.007 |
icky | +0.007 |
ches | +0.007 |
Neg logit contributions | |
disl | -0.007 |
Thank | -0.006 |
killed | -0.005 |
jewels | -0.005 |
statues | -0.005 |
Token | him |
Token ID | 683 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
inn | +0.018 |
ches | +0.016 |
icky | +0.016 |
kernel | +0.015 |
nie | +0.015 |
Neg logit contributions | |
disl | -0.025 |
killed | -0.021 |
Gig | -0.020 |
Thank | -0.020 |
statues | -0.020 |
Token | Emma |
Token ID | 18966 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
disl | +0.014 |
killed | +0.011 |
Gig | +0.011 |
Sorry | +0.011 |
Thank | +0.011 |
Neg logit contributions | |
inn | -0.010 |
ches | -0.009 |
icky | -0.008 |
kernel | -0.008 |
nie | -0.008 |
Token | could |
Token ID | 714 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
inn | +0.001 |
ches | +0.001 |
aid | +0.001 |
icky | +0.001 |
nie | +0.001 |
Neg logit contributions | |
disl | -0.002 |
Sorry | -0.002 |
Gig | -0.001 |
killed | -0.001 |
endant | -0.001 |
Token | hear |
Token ID | 3285 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
inn | +0.034 |
aid | +0.032 |
ches | +0.031 |
icky | +0.031 |
kernel | +0.031 |
Neg logit contributions | |
disl | -0.023 |
Gig | -0.016 |
Sorry | -0.016 |
endant | -0.016 |
mm | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
disl | +0.032 |
Sorry | +0.027 |
endant | +0.026 |
mm | +0.026 |
Thank | +0.026 |
Neg logit contributions | |
inn | -0.017 |
aid | -0.016 |
ches | -0.016 |
icky | -0.016 |
Alex | -0.015 |
Token | wh |
Token ID | 348 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
disl | +0.002 |
killed | +0.001 |
endant | +0.001 |
Gig | +0.001 |
bows | +0.001 |
Neg logit contributions | |
inn | -0.002 |
ches | -0.001 |
icky | -0.001 |
kernel | -0.001 |
aid | -0.001 |
Token | inn |
Token ID | 3732 |
Feature activation | -5.61e+00 |
Pos logit contributions | |
disl | +0.017 |
killed | +0.013 |
endant | +0.013 |
mm | +0.012 |
vell | +0.012 |
Neg logit contributions | |
chair | -0.015 |
ches | -0.014 |
mat | -0.014 |
aid | -0.014 |
kernel | -0.014 |
Token | ying |
Token ID | 1112 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
inn | +0.107 |
crib | +0.094 |
Alex | +0.091 |
ud | +0.088 |
DVD | +0.088 |
Neg logit contributions | |
disl | -0.166 |
bows | -0.149 |
statues | -0.146 |
Tri | -0.140 |
jewels | -0.137 |
Token | sound |
Token ID | 2128 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
inn | +0.055 |
icky | +0.047 |
ches | +0.045 |
ud | +0.045 |
nie | +0.045 |
Neg logit contributions | |
disl | -0.053 |
statues | -0.048 |
jewels | -0.047 |
bows | -0.047 |
Tri | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
inn | +0.002 |
ches | +0.002 |
icky | +0.002 |
kernel | +0.002 |
nie | +0.002 |
Neg logit contributions | |
disl | -0.003 |
killed | -0.003 |
Thank | -0.003 |
bows | -0.003 |
Gig | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
inn | +0.020 |
ches | +0.018 |
kernel | +0.018 |
icky | +0.018 |
nie | +0.017 |
Neg logit contributions | |
disl | -0.015 |
Thank | -0.011 |
Gig | -0.011 |
Sorry | -0.011 |
Thank | -0.011 |
Token | stepped |
Token ID | 10764 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
disl | +0.002 |
Gig | +0.002 |
Sorry | +0.002 |
killed | +0.002 |
endant | +0.002 |
Neg logit contributions | |
inn | -0.002 |
ches | -0.002 |
icky | -0.001 |
nie | -0.001 |
kernel | -0.001 |
Token | tried |
Token ID | 3088 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
disl | +0.005 |
Gig | +0.004 |
endant | +0.004 |
Sorry | +0.004 |
Tri | +0.004 |
Neg logit contributions | |
inn | -0.006 |
ches | -0.005 |
icky | -0.005 |
kernel | -0.005 |
nie | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
inn | +0.057 |
kernel | +0.049 |
ches | +0.046 |
nie | +0.045 |
pron | +0.045 |
Neg logit contributions | |
disl | -0.075 |
killed | -0.064 |
bows | -0.058 |
Gig | -0.057 |
Sorry | -0.057 |
Token | catch |
Token ID | 4929 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
disl | +0.009 |
endant | +0.008 |
Gig | +0.007 |
statues | +0.007 |
Tri | +0.007 |
Neg logit contributions | |
inn | -0.008 |
aid | -0.008 |
ches | -0.008 |
icky | -0.007 |
kernel | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
inn | +0.062 |
pron | +0.055 |
nie | +0.054 |
kernel | +0.054 |
aid | +0.053 |
Neg logit contributions | |
disl | -0.038 |
killed | -0.029 |
Gig | -0.027 |
Sorry | -0.026 |
Thank | -0.026 |
Token | k |
Token ID | 479 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
inn | +0.045 |
icky | +0.039 |
ches | +0.038 |
aid | +0.037 |
nie | +0.037 |
Neg logit contributions | |
disl | -0.037 |
killed | -0.032 |
Thank | -0.031 |
Gig | -0.031 |
lucky | -0.030 |
Token | ang |
Token ID | 648 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
inn | +0.046 |
nie | +0.045 |
aid | +0.045 |
icky | +0.043 |
pron | +0.043 |
Neg logit contributions | |
disl | -0.031 |
killed | -0.030 |
Thank | -0.029 |
Sorry | -0.027 |
tou | -0.026 |
Token | aroo |
Token ID | 38049 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
inn | +0.172 |
pron | +0.167 |
oby | +0.166 |
aid | +0.165 |
icky | +0.165 |
Neg logit contributions | |
disl | -0.087 |
killed | -0.076 |
Gig | -0.074 |
Sorry | -0.068 |
Tri | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
inn | +0.066 |
icky | +0.056 |
Alex | +0.055 |
pron | +0.055 |
kernel | +0.055 |
Neg logit contributions | |
disl | -0.050 |
killed | -0.040 |
Gig | -0.038 |
bows | -0.037 |
lucky | -0.037 |
Token | It |
Token ID | 632 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
disl | +0.016 |
bows | +0.013 |
endant | +0.013 |
statues | +0.013 |
killed | +0.013 |
Neg logit contributions | |
inn | -0.011 |
icky | -0.010 |
aid | -0.009 |
ches | -0.009 |
Alex | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
disl | +0.006 |
Gig | +0.005 |
endant | +0.005 |
Sorry | +0.005 |
Thank | +0.005 |
Neg logit contributions | |
inn | -0.004 |
ches | -0.003 |
icky | -0.003 |
nie | -0.003 |
kernel | -0.003 |
Token | not |
Token ID | 407 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
inn | +0.011 |
icky | +0.010 |
ches | +0.010 |
kernel | +0.010 |
aid | +0.009 |
Neg logit contributions | |
disl | -0.009 |
killed | -0.007 |
Thank | -0.006 |
Gig | -0.006 |
endant | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
inn | +0.008 |
ches | +0.007 |
icky | +0.007 |
kernel | +0.007 |
aid | +0.007 |
Neg logit contributions | |
disl | -0.013 |
killed | -0.011 |
Gig | -0.010 |
Thank | -0.010 |
bows | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
disl | +0.004 |
killed | +0.003 |
Sorry | +0.003 |
Thank | +0.003 |
Gig | +0.003 |
Neg logit contributions | |
inn | -0.004 |
ches | -0.004 |
icky | -0.004 |
aid | -0.004 |
kernel | -0.004 |
Token | picture |
Token ID | 4286 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
inn | +0.002 |
aid | +0.002 |
ches | +0.002 |
kernel | +0.002 |
nie | +0.002 |
Neg logit contributions | |
disl | -0.004 |
Gig | -0.003 |
Sorry | -0.003 |
endant | -0.003 |
killed | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
disl | +0.030 |
killed | +0.027 |
bows | +0.025 |
Thank | +0.024 |
Sorry | +0.024 |
Neg logit contributions | |
inn | -0.038 |
icky | -0.032 |
aid | -0.032 |
nie | -0.032 |
kernel | -0.031 |
Token | sm |
Token ID | 895 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
inn | +0.026 |
icky | +0.024 |
ches | +0.024 |
aid | +0.024 |
nie | +0.024 |
Neg logit contributions | |
disl | -0.019 |
killed | -0.016 |
endant | -0.015 |
jewels | -0.015 |
Thank | -0.015 |
Token | ud |
Token ID | 463 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
disl | +0.005 |
killed | +0.004 |
Thank | +0.004 |
Gig | +0.004 |
endant | +0.004 |
Neg logit contributions | |
inn | -0.004 |
ches | -0.003 |
icky | -0.003 |
kernel | -0.003 |
aid | -0.003 |
Token | gy |
Token ID | 1360 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
inn | +0.124 |
aid | +0.115 |
Alex | +0.107 |
icky | +0.105 |
kernel | +0.104 |
Neg logit contributions | |
disl | -0.151 |
killed | -0.128 |
bows | -0.126 |
Gig | -0.122 |
jewels | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
disl | +0.003 |
Thank | +0.002 |
killed | +0.002 |
Sorry | +0.002 |
Gig | +0.002 |
Neg logit contributions | |
inn | -0.002 |
ches | -0.002 |
icky | -0.001 |
kernel | -0.001 |
nie | -0.001 |
Token | Mom |
Token ID | 11254 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
disl | +0.002 |
killed | +0.001 |
endant | +0.001 |
Gig | +0.001 |
bows | +0.001 |
Neg logit contributions | |
inn | -0.001 |
ches | -0.001 |
icky | -0.001 |
nie | -0.001 |
kernel | -0.001 |
Token | my |
Token ID | 1820 |
Feature activation | +8.45e-02 |
Pos logit contributions | |
disl | +0.020 |
killed | +0.017 |
Thank | +0.017 |
endant | +0.016 |
Gig | +0.016 |
Neg logit contributions | |
inn | -0.025 |
aid | -0.022 |
kernel | -0.022 |
icky | -0.022 |
mat | -0.022 |
Token | said |
Token ID | 531 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
disl | +0.002 |
killed | +0.001 |
Thank | +0.001 |
Gig | +0.001 |
endant | +0.001 |
Neg logit contributions | |
inn | -0.003 |
icky | -0.003 |
kernel | -0.002 |
aid | -0.002 |
ches | -0.002 |
Token | house |
Token ID | 2156 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
disl | +0.009 |
mm | +0.008 |
endant | +0.008 |
bows | +0.008 |
Sorry | +0.008 |
Neg logit contributions | |
corner | -0.004 |
crib | -0.004 |
chair | -0.003 |
aid | -0.003 |
inn | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
disl | +0.076 |
killed | +0.066 |
statues | +0.063 |
Thank | +0.062 |
endant | +0.062 |
Neg logit contributions | |
inn | -0.063 |
ches | -0.055 |
icky | -0.055 |
nie | -0.053 |
kernel | -0.053 |
Token | a |
Token ID | 257 |
Feature activation | +8.92e-02 |
Pos logit contributions | |
inn | +0.007 |
icky | +0.007 |
ches | +0.007 |
aid | +0.007 |
kernel | +0.007 |
Neg logit contributions | |
disl | -0.008 |
Sorry | -0.006 |
mm | -0.006 |
endant | -0.006 |
Gig | -0.006 |
Token | tall |
Token ID | 7331 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
disl | +0.002 |
killed | +0.002 |
Thank | +0.002 |
Gig | +0.002 |
bows | +0.002 |
Neg logit contributions | |
inn | -0.002 |
ches | -0.002 |
icky | -0.002 |
kernel | -0.002 |
aid | -0.002 |
Token | cane |
Token ID | 33009 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
inn | +0.013 |
ches | +0.012 |
icky | +0.012 |
kernel | +0.011 |
nie | +0.011 |
Neg logit contributions | |
disl | -0.017 |
killed | -0.014 |
Gig | -0.014 |
Sorry | -0.014 |
Thank | -0.014 |
Token | leaning |
Token ID | 21804 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
inn | +0.018 |
icky | +0.015 |
ches | +0.015 |
nie | +0.015 |
kernel | +0.015 |
Neg logit contributions | |
disl | -0.021 |
killed | -0.018 |
endant | -0.017 |
Thank | -0.017 |
jewels | -0.017 |
Token | against |
Token ID | 1028 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
icky | +0.116 |
oons | +0.116 |
nie | +0.112 |
inn | +0.112 |
ud | +0.111 |
Neg logit contributions | |
Thank | -0.127 |
Tri | -0.127 |
ocular | -0.125 |
hy | -0.124 |
disl | -0.118 |
Token | its |
Token ID | 663 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
inn | +0.079 |
ches | +0.073 |
nie | +0.069 |
pron | +0.068 |
ash | +0.068 |
Neg logit contributions | |
disl | -0.074 |
Gig | -0.067 |
killed | -0.064 |
jewels | -0.062 |
statues | -0.062 |
Token | front |
Token ID | 2166 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
inn | +0.008 |
ches | +0.007 |
icky | +0.007 |
kernel | +0.007 |
nie | +0.007 |
Neg logit contributions | |
disl | -0.013 |
killed | -0.010 |
Gig | -0.010 |
Sorry | -0.010 |
Thank | -0.010 |
Token | door |
Token ID | 3420 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
inn | +0.010 |
ches | +0.009 |
icky | +0.009 |
kernel | +0.008 |
nie | +0.008 |
Neg logit contributions | |
disl | -0.011 |
statues | -0.009 |
endant | -0.009 |
killed | -0.009 |
bows | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
disl | +0.016 |
killed | +0.013 |
endant | +0.013 |
bows | +0.012 |
Gig | +0.012 |
Neg logit contributions | |
inn | -0.011 |
ches | -0.010 |
icky | -0.010 |
kernel | -0.010 |
nie | -0.010 |
Token | forgive |
Token ID | 20927 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
disl | +0.010 |
endant | +0.009 |
statues | +0.009 |
killed | +0.008 |
bows | +0.008 |
Neg logit contributions | |
inn | -0.010 |
ches | -0.009 |
aid | -0.009 |
icky | -0.009 |
nie | -0.008 |
Token | than |
Token ID | 621 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
disl | +0.012 |
killed | +0.010 |
Thank | +0.010 |
Gig | +0.010 |
Sorry | +0.010 |
Neg logit contributions | |
inn | -0.008 |
ches | -0.007 |
icky | -0.007 |
kernel | -0.007 |
nie | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
disl | +0.017 |
endant | +0.013 |
Sorry | +0.013 |
Gig | +0.013 |
mm | +0.013 |
Neg logit contributions | |
inn | -0.011 |
ches | -0.010 |
icky | -0.009 |
nie | -0.009 |
aid | -0.009 |
Token | hold |
Token ID | 1745 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
disl | +0.037 |
endant | +0.031 |
killed | +0.030 |
Gig | +0.029 |
Tri | +0.029 |
Neg logit contributions | |
inn | -0.036 |
ches | -0.033 |
icky | -0.032 |
aid | -0.032 |
nie | -0.032 |
Token | gr |
Token ID | 1036 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
inn | +0.077 |
kernel | +0.068 |
icky | +0.068 |
ches | +0.067 |
aid | +0.066 |
Neg logit contributions | |
disl | -0.078 |
killed | -0.060 |
Gig | -0.059 |
jewels | -0.058 |
Thank | -0.058 |
Token | ud |
Token ID | 463 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
disl | +0.042 |
killed | +0.033 |
Gig | +0.032 |
Sorry | +0.032 |
Thank | +0.032 |
Neg logit contributions | |
inn | -0.041 |
ches | -0.037 |
icky | -0.037 |
nie | -0.036 |
kernel | -0.036 |
Token | ges |
Token ID | 3212 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
inn | +0.123 |
kernel | +0.108 |
icky | +0.104 |
aid | +0.104 |
mat | +0.103 |
Neg logit contributions | |
disl | -0.161 |
Gig | -0.125 |
killed | -0.125 |
Tri | -0.121 |
bows | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
inn | +0.045 |
icky | +0.038 |
ches | +0.038 |
kernel | +0.038 |
nie | +0.037 |
Neg logit contributions | |
disl | -0.070 |
killed | -0.057 |
Thank | -0.056 |
Gig | -0.056 |
bows | -0.056 |
Token | |
Token ID | 220 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
inn | +0.021 |
icky | +0.019 |
ches | +0.018 |
aid | +0.018 |
nie | +0.017 |
Neg logit contributions | |
disl | -0.030 |
killed | -0.025 |
statues | -0.024 |
endant | -0.024 |
jewels | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
disl | +0.017 |
killed | +0.014 |
jewels | +0.014 |
statues | +0.013 |
endant | +0.013 |
Neg logit contributions | |
inn | -0.012 |
icky | -0.011 |
ches | -0.010 |
aid | -0.010 |
nie | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
inn | +0.026 |
ches | +0.023 |
icky | +0.023 |
kernel | +0.023 |
nie | +0.022 |
Neg logit contributions | |
disl | -0.032 |
killed | -0.025 |
Thank | -0.025 |
Gig | -0.025 |
Sorry | -0.024 |
Token | there |
Token ID | 612 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
inn | +0.051 |
ches | +0.043 |
icky | +0.043 |
nie | +0.041 |
ud | +0.041 |
Neg logit contributions | |
disl | -0.052 |
killed | -0.041 |
Sorry | -0.040 |
Gig | -0.040 |
statues | -0.039 |
Token | 's |
Token ID | 338 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
inn | +0.040 |
ches | +0.034 |
icky | +0.034 |
kernel | +0.033 |
nie | +0.033 |
Neg logit contributions | |
disl | -0.049 |
killed | -0.039 |
Sorry | -0.038 |
Gig | -0.038 |
Thank | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
inn | +0.000 |
ches | +0.000 |
icky | +0.000 |
aid | +0.000 |
kernel | +0.000 |
Neg logit contributions | |
disl | -0.000 |
Sorry | -0.000 |
endant | -0.000 |
bows | -0.000 |
Thank | -0.000 |
Token | light |
Token ID | 1657 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
inn | +0.023 |
ches | +0.021 |
icky | +0.021 |
kernel | +0.021 |
aid | +0.020 |
Neg logit contributions | |
disl | -0.022 |
killed | -0.017 |
endant | -0.016 |
Thank | -0.016 |
Gig | -0.016 |
Token | up |
Token ID | 510 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
inn | +0.043 |
icky | +0.037 |
ches | +0.035 |
ud | +0.035 |
nie | +0.035 |
Neg logit contributions | |
disl | -0.042 |
killed | -0.035 |
Sorry | -0.034 |
bows | -0.034 |
statues | -0.033 |
Token | ahead |
Token ID | 4058 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
inn | +0.071 |
icky | +0.063 |
ches | +0.063 |
kernel | +0.061 |
nie | +0.059 |
Neg logit contributions | |
disl | -0.073 |
killed | -0.060 |
Gig | -0.059 |
Thank | -0.058 |
jewels | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
inn | +0.167 |
kernel | +0.146 |
aid | +0.145 |
Alex | +0.144 |
ches | +0.143 |
Neg logit contributions | |
disl | -0.097 |
Thank | -0.080 |
Gig | -0.080 |
killed | -0.078 |
Sorry | -0.077 |
Token | We |
Token ID | 775 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
inn | +0.014 |
ches | +0.012 |
icky | +0.012 |
aid | +0.012 |
nie | +0.012 |
Neg logit contributions | |
disl | -0.016 |
killed | -0.012 |
endant | -0.012 |
bows | -0.012 |
jewels | -0.012 |
Token | just |
Token ID | 655 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
inn | +0.046 |
ches | +0.046 |
' | +0.043 |
nie | +0.041 |
kernel | +0.040 |
Neg logit contributions | |
disl | -0.053 |
mm | -0.043 |
statues | -0.041 |
endant | -0.041 |
Gig | -0.041 |
Token | need |
Token ID | 761 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
inn | +0.000 |
ches | +0.000 |
nie | +0.000 |
aid | +0.000 |
' | +0.000 |
Neg logit contributions | |
disl | -0.000 |
mm | -0.000 |
bows | -0.000 |
Gig | -0.000 |
endant | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
inn | +0.031 |
ches | +0.027 |
icky | +0.027 |
kernel | +0.026 |
aid | +0.025 |
Neg logit contributions | |
disl | -0.056 |
killed | -0.045 |
Sorry | -0.045 |
Thank | -0.045 |
endant | -0.045 |
Token | her |
Token ID | 607 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
disl | +0.012 |
endant | +0.009 |
Thank | +0.009 |
Gig | +0.009 |
killed | +0.009 |
Neg logit contributions | |
inn | -0.010 |
ches | -0.009 |
icky | -0.009 |
nie | -0.009 |
aid | -0.009 |
Token | drawings |
Token ID | 23388 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
disl | +0.009 |
Gig | +0.007 |
killed | +0.007 |
Sorry | +0.007 |
Thank | +0.007 |
Neg logit contributions | |
inn | -0.007 |
ches | -0.006 |
icky | -0.006 |
aid | -0.006 |
nie | -0.006 |
Token | would |
Token ID | 561 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
disl | +0.085 |
Gig | +0.074 |
Sorry | +0.068 |
Thank | +0.067 |
mm | +0.067 |
Neg logit contributions | |
ches | -0.060 |
inn | -0.060 |
ide | -0.055 |
' | -0.054 |
icky | -0.053 |
Token | get |
Token ID | 651 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
disl | +0.021 |
Gig | +0.017 |
endant | +0.017 |
Sorry | +0.017 |
killed | +0.017 |
Neg logit contributions | |
inn | -0.016 |
ches | -0.015 |
icky | -0.014 |
aid | -0.014 |
kernel | -0.014 |
Token | sm |
Token ID | 895 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
inn | +0.006 |
ches | +0.006 |
icky | +0.006 |
nie | +0.005 |
kernel | +0.005 |
Neg logit contributions | |
disl | -0.008 |
mm | -0.007 |
Sorry | -0.007 |
Gig | -0.006 |
Thank | -0.006 |
Token | ud |
Token ID | 463 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
inn | +0.011 |
ches | +0.010 |
icky | +0.010 |
kernel | +0.010 |
nie | +0.009 |
Neg logit contributions | |
disl | -0.014 |
killed | -0.011 |
Thank | -0.011 |
Gig | -0.011 |
Sorry | -0.011 |
Token | ged |
Token ID | 2004 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
inn | +0.076 |
aid | +0.064 |
kernel | +0.059 |
Alex | +0.055 |
mat | +0.053 |
Neg logit contributions | |
disl | -0.204 |
bows | -0.179 |
killed | -0.169 |
Gig | -0.166 |
jewels | -0.166 |
Token | because |
Token ID | 780 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
inn | +0.046 |
ches | +0.040 |
icky | +0.039 |
nie | +0.038 |
kernel | +0.037 |
Neg logit contributions | |
disl | -0.079 |
killed | -0.064 |
Sorry | -0.064 |
Thank | -0.063 |
Gig | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
disl | +0.010 |
killed | +0.007 |
statues | +0.007 |
jewels | +0.007 |
Sorry | +0.007 |
Neg logit contributions | |
inn | -0.012 |
ches | -0.011 |
aid | -0.011 |
kernel | -0.011 |
nie | -0.011 |
Token | paper |
Token ID | 3348 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
inn | +0.010 |
ches | +0.009 |
kernel | +0.009 |
aid | +0.009 |
nie | +0.009 |
Neg logit contributions | |
disl | -0.012 |
Gig | -0.010 |
killed | -0.010 |
Sorry | -0.010 |
endant | -0.009 |
Token | wasn |
Token ID | 2492 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
disl | +0.004 |
Gig | +0.003 |
killed | +0.003 |
Thank | +0.003 |
Sorry | +0.003 |
Neg logit contributions | |
inn | -0.002 |
ches | -0.002 |
icky | -0.002 |
kernel | -0.002 |
nie | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
disl | +0.008 |
bows | +0.006 |
endant | +0.006 |
Gig | +0.006 |
jewels | +0.006 |
Neg logit contributions | |
inn | -0.007 |
ches | -0.006 |
kernel | -0.006 |
icky | -0.006 |
nie | -0.006 |
Token | waiting |
Token ID | 4953 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
inn | +0.046 |
ches | +0.041 |
kernel | +0.040 |
icky | +0.040 |
aid | +0.040 |
Neg logit contributions | |
disl | -0.055 |
killed | -0.044 |
Sorry | -0.043 |
endant | -0.043 |
bows | -0.043 |
Token | for |
Token ID | 329 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
inn | +0.008 |
ches | +0.007 |
icky | +0.007 |
kernel | +0.007 |
nie | +0.007 |
Neg logit contributions | |
disl | -0.017 |
killed | -0.014 |
Gig | -0.014 |
endant | -0.014 |
Thank | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
inn | +0.009 |
ches | +0.008 |
icky | +0.008 |
kernel | +0.008 |
aid | +0.008 |
Neg logit contributions | |
disl | -0.013 |
killed | -0.010 |
endant | -0.010 |
Sorry | -0.010 |
bows | -0.010 |
Token | k |
Token ID | 479 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
inn | +0.029 |
ches | +0.026 |
icky | +0.026 |
kernel | +0.025 |
nie | +0.025 |
Neg logit contributions | |
disl | -0.036 |
killed | -0.029 |
Gig | -0.028 |
Thank | -0.028 |
Sorry | -0.028 |
Token | ang |
Token ID | 648 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
inn | +0.038 |
nie | +0.037 |
aid | +0.036 |
icky | +0.036 |
oby | +0.035 |
Neg logit contributions | |
disl | -0.031 |
killed | -0.030 |
Thank | -0.029 |
endant | -0.028 |
Gig | -0.028 |
Token | aroo |
Token ID | 38049 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
inn | +0.153 |
icky | +0.151 |
oby | +0.149 |
studio | +0.145 |
aid | +0.144 |
Neg logit contributions | |
disl | -0.093 |
Gig | -0.089 |
killed | -0.084 |
tou | -0.077 |
Twe | -0.074 |
Token | to |
Token ID | 284 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
inn | +0.044 |
icky | +0.037 |
ches | +0.037 |
kernel | +0.036 |
nie | +0.036 |
Neg logit contributions | |
disl | -0.062 |
killed | -0.050 |
Gig | -0.050 |
endant | -0.049 |
jewels | -0.049 |
Token | move |
Token ID | 1445 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
inn | +0.002 |
ches | +0.002 |
aid | +0.002 |
kernel | +0.002 |
icky | +0.002 |
Neg logit contributions | |
disl | -0.002 |
endant | -0.001 |
bows | -0.001 |
Sorry | -0.001 |
killed | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
inn | +0.063 |
pron | +0.057 |
icky | +0.056 |
kernel | +0.056 |
ches | +0.056 |
Neg logit contributions | |
disl | -0.067 |
Gig | -0.056 |
jewels | -0.055 |
killed | -0.055 |
Tri | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
inn | +0.019 |
ches | +0.017 |
icky | +0.016 |
kernel | +0.016 |
nie | +0.016 |
Neg logit contributions | |
disl | -0.023 |
killed | -0.018 |
Sorry | -0.018 |
endant | -0.018 |
Gig | -0.018 |
Token | he |
Token ID | 339 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
inn | +0.029 |
ches | +0.027 |
nie | +0.026 |
aid | +0.026 |
ash | +0.026 |
Neg logit contributions | |
disl | -0.023 |
killed | -0.018 |
Gig | -0.018 |
Sorry | -0.017 |
Tri | -0.017 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
inn | +0.022 |
ches | +0.020 |
icky | +0.020 |
kernel | +0.019 |
aid | +0.019 |
Neg logit contributions | |
disl | -0.022 |
Sorry | -0.016 |
killed | -0.016 |
endant | -0.016 |
Gig | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
disl | +0.017 |
killed | +0.013 |
Sorry | +0.013 |
endant | +0.013 |
Thank | +0.013 |
Neg logit contributions | |
inn | -0.015 |
ches | -0.013 |
icky | -0.013 |
kernel | -0.013 |
aid | -0.012 |
Token | big |
Token ID | 1263 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
inn | +0.009 |
ches | +0.008 |
icky | +0.008 |
kernel | +0.008 |
nie | +0.008 |
Neg logit contributions | |
disl | -0.008 |
killed | -0.006 |
Gig | -0.006 |
Sorry | -0.006 |
endant | -0.006 |
Token | staff |
Token ID | 3085 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
inn | +0.004 |
ches | +0.004 |
icky | +0.004 |
nie | +0.004 |
aid | +0.004 |
Neg logit contributions | |
disl | -0.004 |
Gig | -0.003 |
killed | -0.003 |
jewels | -0.003 |
Sorry | -0.003 |
Token | leaning |
Token ID | 21804 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
inn | +0.005 |
nie | +0.005 |
icky | +0.005 |
ches | +0.005 |
kernel | +0.004 |
Neg logit contributions | |
disl | -0.005 |
killed | -0.005 |
statues | -0.005 |
endant | -0.005 |
Tri | -0.004 |
Token | against |
Token ID | 1028 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
oons | +0.128 |
nie | +0.121 |
mat | +0.115 |
panc | +0.114 |
inn | +0.112 |
Neg logit contributions | |
Thank | -0.107 |
hy | -0.105 |
tou | -0.101 |
Tri | -0.099 |
ocular | -0.098 |
Token | a |
Token ID | 257 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
inn | +0.095 |
pron | +0.086 |
nie | +0.086 |
ches | +0.085 |
ash | +0.084 |
Neg logit contributions | |
disl | -0.069 |
Gig | -0.060 |
jewels | -0.059 |
Tri | -0.058 |
killed | -0.057 |
Token | tree |
Token ID | 5509 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
inn | +0.009 |
icky | +0.008 |
ud | +0.008 |
ash | +0.008 |
nie | +0.008 |
Neg logit contributions | |
disl | -0.007 |
Gig | -0.006 |
statues | -0.006 |
jewels | -0.006 |
tou | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
inn | +0.019 |
nie | +0.017 |
Alex | +0.017 |
icky | +0.017 |
oby | +0.016 |
Neg logit contributions | |
disl | -0.015 |
killed | -0.012 |
endant | -0.012 |
bows | -0.012 |
Thank | -0.012 |
Token | |
Token ID | 220 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
inn | +0.016 |
kernel | +0.015 |
nie | +0.015 |
aid | +0.015 |
icky | +0.015 |
Neg logit contributions | |
disl | -0.014 |
Gig | -0.011 |
Thank | -0.011 |
Tri | -0.011 |
Sorry | -0.011 |
Token | there |
Token ID | 612 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
disl | +0.004 |
Gig | +0.003 |
Thank | +0.003 |
killed | +0.003 |
lucky | +0.003 |
Neg logit contributions | |
inn | -0.008 |
ches | -0.007 |
nie | -0.007 |
ash | -0.007 |
ud | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
disl | +0.006 |
killed | +0.006 |
statues | +0.006 |
Gig | +0.006 |
Thank | +0.006 |
Neg logit contributions | |
inn | -0.009 |
nie | -0.008 |
ash | -0.008 |
ches | -0.008 |
icky | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
inn | +0.006 |
ches | +0.005 |
icky | +0.005 |
nie | +0.005 |
kernel | +0.005 |
Neg logit contributions | |
disl | -0.006 |
killed | -0.005 |
Gig | -0.005 |
Thank | -0.004 |
endant | -0.004 |
Token | big |
Token ID | 1263 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
inn | +0.014 |
ches | +0.012 |
icky | +0.012 |
nie | +0.012 |
kernel | +0.012 |
Neg logit contributions | |
disl | -0.011 |
killed | -0.009 |
Sorry | -0.008 |
Thank | -0.008 |
Gig | -0.008 |
Token | th |
Token ID | 294 |
Feature activation | +3.32e-03 |
Pos logit contributions | |
inn | +0.004 |
ches | +0.004 |
icky | +0.004 |
nie | +0.004 |
ide | +0.004 |
Neg logit contributions | |
disl | -0.004 |
killed | -0.003 |
jewels | -0.003 |
Thank | -0.003 |
statues | -0.003 |
Token | ud |
Token ID | 463 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
disl | +0.000 |
killed | +0.000 |
Thank | +0.000 |
bows | +0.000 |
endant | +0.000 |
Neg logit contributions | |
inn | -0.000 |
nie | -0.000 |
ches | -0.000 |
aid | -0.000 |
kernel | -0.000 |
Token | as |
Token ID | 355 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
inn | +0.119 |
icky | +0.111 |
aid | +0.110 |
crib | +0.109 |
rey | +0.107 |
Neg logit contributions | |
disl | -0.126 |
killed | -0.110 |
drops | -0.103 |
bows | -0.102 |
Gig | -0.102 |
Token | the |
Token ID | 262 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
inn | +0.095 |
ches | +0.085 |
icky | +0.084 |
kernel | +0.083 |
nie | +0.082 |
Neg logit contributions | |
disl | -0.100 |
killed | -0.077 |
Sorry | -0.076 |
endant | -0.076 |
Gig | -0.076 |
Token | blocks |
Token ID | 7021 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
inn | +0.011 |
ches | +0.010 |
icky | +0.010 |
kernel | +0.010 |
nie | +0.010 |
Neg logit contributions | |
disl | -0.014 |
killed | -0.011 |
Gig | -0.011 |
Sorry | -0.011 |
endant | -0.011 |
Token | started |
Token ID | 2067 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
inn | +0.006 |
icky | +0.006 |
ches | +0.006 |
nie | +0.006 |
kernel | +0.005 |
Neg logit contributions | |
disl | -0.006 |
killed | -0.005 |
endant | -0.004 |
Thank | -0.004 |
bows | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
inn | +0.044 |
ches | +0.038 |
nie | +0.038 |
kernel | +0.037 |
icky | +0.036 |
Neg logit contributions | |
disl | -0.073 |
killed | -0.062 |
bows | -0.060 |
Gig | -0.060 |
Tri | -0.059 |
Token | he |
Token ID | 339 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
disl | +0.028 |
killed | +0.021 |
Gig | +0.021 |
Sorry | +0.021 |
Thank | +0.021 |
Neg logit contributions | |
inn | -0.027 |
ches | -0.024 |
icky | -0.024 |
kernel | -0.024 |
nie | -0.023 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
inn | +0.028 |
ches | +0.025 |
icky | +0.025 |
aid | +0.024 |
kernel | +0.024 |
Neg logit contributions | |
disl | -0.031 |
bows | -0.024 |
Sorry | -0.023 |
Gig | -0.023 |
killed | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
disl | +0.019 |
Sorry | +0.015 |
killed | +0.015 |
Thank | +0.015 |
endant | +0.015 |
Neg logit contributions | |
inn | -0.016 |
icky | -0.014 |
ches | -0.014 |
kernel | -0.014 |
aid | -0.013 |
Token | big |
Token ID | 1263 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
inn | +0.013 |
ches | +0.011 |
icky | +0.011 |
nie | +0.011 |
kernel | +0.011 |
Neg logit contributions | |
disl | -0.011 |
killed | -0.009 |
Gig | -0.009 |
statues | -0.009 |
endant | -0.009 |
Token | ladder |
Token ID | 18002 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
inn | +0.003 |
ches | +0.003 |
icky | +0.003 |
nie | +0.003 |
ash | +0.003 |
Neg logit contributions | |
disl | -0.003 |
jewels | -0.002 |
statues | -0.002 |
killed | -0.002 |
Gig | -0.002 |
Token | leaning |
Token ID | 21804 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
inn | +0.029 |
icky | +0.027 |
nie | +0.026 |
ches | +0.025 |
Alex | +0.025 |
Neg logit contributions | |
disl | -0.023 |
killed | -0.020 |
Thank | -0.020 |
hy | -0.020 |
bows | -0.019 |
Token | against |
Token ID | 1028 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
oons | +0.116 |
icky | +0.115 |
nie | +0.113 |
ches | +0.111 |
mat | +0.111 |
Neg logit contributions | |
Thank | -0.118 |
hy | -0.110 |
Tri | -0.109 |
ocular | -0.108 |
Twe | -0.102 |
Token | the |
Token ID | 262 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
inn | +0.076 |
ches | +0.074 |
icky | +0.071 |
nie | +0.069 |
ash | +0.067 |
Neg logit contributions | |
disl | -0.071 |
Gig | -0.062 |
Tri | -0.061 |
jewels | -0.060 |
killed | -0.060 |
Token | fence |
Token ID | 13990 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
inn | +0.013 |
ches | +0.011 |
icky | +0.011 |
ash | +0.011 |
kernel | +0.010 |
Neg logit contributions | |
disl | -0.013 |
statues | -0.011 |
killed | -0.011 |
Gig | -0.011 |
Thank | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
inn | +0.017 |
nie | +0.015 |
icky | +0.015 |
ches | +0.015 |
Alex | +0.015 |
Neg logit contributions | |
disl | -0.011 |
ocular | -0.009 |
statues | -0.009 |
bows | -0.009 |
Thank | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
inn | +0.008 |
ches | +0.008 |
icky | +0.008 |
kernel | +0.007 |
nie | +0.007 |
Neg logit contributions | |
disl | -0.009 |
killed | -0.007 |
Gig | -0.007 |
Thank | -0.007 |
Sorry | -0.006 |
Token | stick |
Token ID | 4859 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
disl | +0.001 |
killed | +0.001 |
know | +0.001 |
Gig | +0.001 |
bows | +0.001 |
Neg logit contributions | |
inn | -0.001 |
ud | -0.001 |
kernel | -0.001 |
icky | -0.001 |
nie | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
inn | +0.019 |
nie | +0.018 |
ud | +0.017 |
icky | +0.017 |
kernel | +0.017 |
Neg logit contributions | |
disl | -0.023 |
jewels | -0.019 |
Gig | -0.019 |
killed | -0.019 |
Tri | -0.018 |
Token | mustache |
Token ID | 49303 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
inn | +0.022 |
icky | +0.019 |
ches | +0.018 |
ud | +0.018 |
ide | +0.017 |
Neg logit contributions | |
disl | -0.025 |
jewels | -0.021 |
killed | -0.020 |
endant | -0.020 |
bows | -0.020 |
Token | on |
Token ID | 319 |
Feature activation | +9.02e-03 |
Pos logit contributions | |
disl | +0.014 |
bows | +0.012 |
killed | +0.012 |
endant | +0.011 |
Thank | +0.011 |
Neg logit contributions | |
inn | -0.011 |
icky | -0.010 |
nie | -0.009 |
ud | -0.009 |
ches | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
disl | +0.000 |
Gig | +0.000 |
Thank | +0.000 |
Tri | +0.000 |
Gold | +0.000 |
Neg logit contributions | |
inn | -0.000 |
nie | -0.000 |
kernel | -0.000 |
ches | -0.000 |
ash | -0.000 |
Token | upper |
Token ID | 6727 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
inn | +0.002 |
ud | +0.001 |
icky | +0.001 |
ash | +0.001 |
ches | +0.001 |
Neg logit contributions | |
disl | -0.002 |
jewels | -0.002 |
endant | -0.002 |
killed | -0.001 |
statues | -0.001 |
Token | lip |
Token ID | 10645 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
inn | +0.124 |
ches | +0.110 |
nie | +0.104 |
kernel | +0.102 |
Alex | +0.101 |
Neg logit contributions | |
disl | -0.152 |
endant | -0.117 |
Gig | -0.117 |
mm | -0.116 |
killed | -0.116 |
Token | with |
Token ID | 351 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
disl | +0.009 |
bows | +0.008 |
killed | +0.008 |
endant | +0.007 |
jewels | +0.007 |
Neg logit contributions | |
inn | -0.008 |
icky | -0.007 |
ches | -0.007 |
kernel | -0.007 |
nie | -0.007 |
Token | some |
Token ID | 617 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
disl | +0.000 |
bows | +0.000 |
killed | +0.000 |
endant | +0.000 |
Sorry | +0.000 |
Neg logit contributions | |
inn | -0.000 |
icky | -0.000 |
ches | -0.000 |
kernel | -0.000 |
aid | -0.000 |
Token | tape |
Token ID | 9154 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
inn | +0.016 |
ches | +0.014 |
icky | +0.014 |
kernel | +0.014 |
nie | +0.014 |
Neg logit contributions | |
disl | -0.015 |
killed | -0.012 |
Gig | -0.011 |
Sorry | -0.011 |
Thank | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
inn | +0.046 |
icky | +0.040 |
nie | +0.039 |
ches | +0.038 |
kernel | +0.038 |
Neg logit contributions | |
disl | -0.052 |
bows | -0.042 |
endant | -0.041 |
jewels | -0.041 |
killed | -0.041 |
Token | wanted |
Token ID | 2227 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
disl | +0.027 |
Gig | +0.020 |
bows | +0.020 |
endant | +0.020 |
Thank | +0.020 |
Neg logit contributions | |
inn | -0.026 |
ches | -0.024 |
icky | -0.023 |
kernel | -0.023 |
nie | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
inn | +0.013 |
ches | +0.011 |
icky | +0.011 |
kernel | +0.010 |
nie | +0.010 |
Neg logit contributions | |
disl | -0.026 |
killed | -0.022 |
Gig | -0.021 |
Thank | -0.021 |
Sorry | -0.021 |
Token | catch |
Token ID | 4929 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
disl | +0.018 |
endant | +0.016 |
mm | +0.015 |
bows | +0.015 |
statues | +0.015 |
Neg logit contributions | |
aid | -0.012 |
ches | -0.011 |
inn | -0.011 |
mate | -0.011 |
scrub | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
inn | +0.024 |
ches | +0.021 |
icky | +0.021 |
nie | +0.020 |
kernel | +0.020 |
Neg logit contributions | |
disl | -0.039 |
killed | -0.032 |
Gig | -0.032 |
Sorry | -0.031 |
Thank | -0.031 |
Token | k |
Token ID | 479 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
inn | +0.019 |
kernel | +0.018 |
ches | +0.018 |
aid | +0.017 |
icky | +0.017 |
Neg logit contributions | |
disl | -0.024 |
endant | -0.019 |
Sorry | -0.018 |
Tri | -0.018 |
mm | -0.018 |
Token | ang |
Token ID | 648 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
inn | +0.030 |
nie | +0.028 |
icky | +0.027 |
aid | +0.026 |
ches | +0.026 |
Neg logit contributions | |
disl | -0.032 |
killed | -0.029 |
Sorry | -0.027 |
Thank | -0.027 |
Tri | -0.026 |
Token | aro |
Token ID | 12022 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
inn | +0.143 |
pron | +0.134 |
icky | +0.134 |
nie | +0.133 |
ches | +0.132 |
Neg logit contributions | |
disl | -0.108 |
killed | -0.097 |
Gig | -0.092 |
Sorry | -0.090 |
Tri | -0.088 |
Token | os |
Token ID | 418 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
inn | +0.028 |
aid | +0.025 |
kernel | +0.025 |
nie | +0.024 |
icky | +0.024 |
Neg logit contributions | |
disl | -0.039 |
Gig | -0.032 |
Sorry | -0.031 |
killed | -0.031 |
bows | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
inn | +0.009 |
aid | +0.008 |
kernel | +0.008 |
ud | +0.008 |
pron | +0.008 |
Neg logit contributions | |
disl | -0.008 |
killed | -0.006 |
bows | -0.006 |
Gig | -0.006 |
Tri | -0.006 |
Token | take |
Token ID | 1011 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
disl | +0.012 |
endant | +0.011 |
mm | +0.011 |
bows | +0.010 |
Thank | +0.010 |
Neg logit contributions | |
ches | -0.009 |
aid | -0.009 |
kernel | -0.009 |
inn | -0.009 |
chair | -0.009 |
Token | them |
Token ID | 606 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
inn | +0.032 |
ches | +0.027 |
icky | +0.026 |
kernel | +0.025 |
aid | +0.025 |
Neg logit contributions | |
disl | -0.069 |
endant | -0.058 |
Thank | -0.057 |
bows | -0.056 |
Sorry | -0.056 |
Token | is |
Token ID | 318 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
inn | +0.005 |
icky | +0.004 |
kernel | +0.004 |
ches | +0.004 |
aid | +0.004 |
Neg logit contributions | |
disl | -0.005 |
killed | -0.004 |
Thank | -0.004 |
Sorry | -0.004 |
bows | -0.004 |
Token | normal |
Token ID | 3487 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
inn | +0.021 |
ches | +0.019 |
icky | +0.019 |
kernel | +0.019 |
nie | +0.019 |
Neg logit contributions | |
disl | -0.019 |
killed | -0.015 |
Thank | -0.014 |
Gig | -0.014 |
endant | -0.014 |
Token | for |
Token ID | 329 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
inn | +0.018 |
ches | +0.016 |
kernel | +0.015 |
icky | +0.015 |
nie | +0.015 |
Neg logit contributions | |
disl | -0.024 |
killed | -0.019 |
bows | -0.019 |
jewels | -0.019 |
endant | -0.018 |
Token | old |
Token ID | 1468 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
inn | +0.007 |
ches | +0.006 |
icky | +0.006 |
kernel | +0.006 |
nie | +0.006 |
Neg logit contributions | |
disl | -0.009 |
killed | -0.007 |
endant | -0.007 |
Thank | -0.007 |
Sorry | -0.007 |
Token | k |
Token ID | 479 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
inn | +0.017 |
ches | +0.015 |
icky | +0.015 |
kernel | +0.014 |
nie | +0.014 |
Neg logit contributions | |
disl | -0.018 |
killed | -0.013 |
bows | -0.013 |
statues | -0.013 |
Gig | -0.013 |
Token | ang |
Token ID | 648 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
inn | +0.052 |
aid | +0.048 |
kernel | +0.048 |
nie | +0.047 |
ches | +0.046 |
Neg logit contributions | |
disl | -0.040 |
endant | -0.035 |
killed | -0.035 |
bows | -0.032 |
Thank | -0.032 |
Token | aro |
Token ID | 12022 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
inn | +0.127 |
aid | +0.115 |
kernel | +0.108 |
pron | +0.107 |
icky | +0.106 |
Neg logit contributions | |
disl | -0.137 |
killed | -0.114 |
Gig | -0.109 |
Tri | -0.106 |
statues | -0.105 |
Token | os |
Token ID | 418 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
inn | +0.028 |
kernel | +0.024 |
aid | +0.024 |
icky | +0.024 |
ches | +0.024 |
Neg logit contributions | |
disl | -0.044 |
killed | -0.036 |
bows | -0.036 |
endant | -0.035 |
Gig | -0.035 |
Token | ." |
Token ID | 526 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
inn | +0.006 |
kernel | +0.005 |
icky | +0.005 |
aid | +0.005 |
nie | +0.005 |
Neg logit contributions | |
disl | -0.008 |
killed | -0.006 |
bows | -0.006 |
Sorry | -0.006 |
Gig | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
inn | +0.018 |
ches | +0.017 |
kernel | +0.016 |
icky | +0.016 |
nie | +0.016 |
Neg logit contributions | |
disl | -0.017 |
Gig | -0.014 |
Sorry | -0.013 |
Thank | -0.013 |
Tri | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
inn | +0.036 |
kernel | +0.035 |
ches | +0.034 |
nie | +0.034 |
ler | +0.033 |
Neg logit contributions | |
disl | -0.028 |
Gig | -0.022 |
Thank | -0.021 |
Tri | -0.020 |
killed | -0.019 |
Token | The |
Token ID | 383 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
inn | +0.007 |
icky | +0.007 |
aid | +0.007 |
nie | +0.006 |
ud | +0.006 |
Neg logit contributions | |
disl | -0.010 |
killed | -0.008 |
jewels | -0.008 |
vell | -0.008 |
endant | -0.008 |
Token | walls |
Token ID | 7714 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
disl | +0.020 |
Gig | +0.016 |
endant | +0.016 |
killed | +0.016 |
Sorry | +0.016 |
Neg logit contributions | |
inn | -0.013 |
icky | -0.011 |
aid | -0.011 |
chair | -0.011 |
mat | -0.011 |
Token | were |
Token ID | 547 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
disl | +0.045 |
killed | +0.038 |
bows | +0.035 |
endant | +0.035 |
Thank | +0.034 |
Neg logit contributions | |
inn | -0.057 |
icky | -0.052 |
nie | -0.051 |
aid | -0.051 |
ches | -0.050 |
Token | terribly |
Token ID | 22121 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
disl | +0.025 |
killed | +0.019 |
Thank | +0.019 |
endant | +0.019 |
Gig | +0.018 |
Neg logit contributions | |
inn | -0.028 |
ches | -0.025 |
icky | -0.025 |
kernel | -0.024 |
nie | -0.024 |
Token | sm |
Token ID | 895 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
inn | +0.002 |
ches | +0.002 |
icky | +0.002 |
kernel | +0.002 |
nie | +0.002 |
Neg logit contributions | |
disl | -0.002 |
Gig | -0.001 |
Sorry | -0.001 |
killed | -0.001 |
Thank | -0.001 |
Token | ud |
Token ID | 463 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
disl | +0.018 |
killed | +0.014 |
Sorry | +0.014 |
Gig | +0.014 |
Thank | +0.014 |
Neg logit contributions | |
inn | -0.013 |
ches | -0.011 |
icky | -0.011 |
kernel | -0.011 |
nie | -0.011 |
Token | ged |
Token ID | 2004 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
inn | +0.122 |
aid | +0.109 |
kernel | +0.106 |
icky | +0.105 |
Alex | +0.104 |
Neg logit contributions | |
disl | -0.139 |
Gig | -0.116 |
killed | -0.115 |
bows | -0.114 |
Tri | -0.110 |
Token | and |
Token ID | 290 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
inn | +0.040 |
ches | +0.034 |
icky | +0.034 |
nie | +0.032 |
kernel | +0.032 |
Neg logit contributions | |
disl | -0.070 |
Sorry | -0.057 |
killed | -0.056 |
Thank | -0.056 |
Gig | -0.056 |
Token | she |
Token ID | 673 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
inn | +0.001 |
ches | +0.001 |
kernel | +0.001 |
icky | +0.001 |
nie | +0.001 |
Neg logit contributions | |
disl | -0.002 |
Sorry | -0.002 |
endant | -0.002 |
bows | -0.002 |
Thank | -0.002 |
Token | could |
Token ID | 714 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
inn | +0.017 |
icky | +0.015 |
kernel | +0.015 |
aid | +0.015 |
ash | +0.015 |
Neg logit contributions | |
disl | -0.011 |
killed | -0.010 |
Thank | -0.008 |
wished | -0.008 |
endant | -0.008 |
Token | not |
Token ID | 407 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
inn | +0.023 |
ches | +0.021 |
icky | +0.021 |
aid | +0.021 |
kernel | +0.021 |
Neg logit contributions | |
disl | -0.019 |
Gig | -0.014 |
endant | -0.014 |
killed | -0.014 |
Thank | -0.014 |
Token | It |
Token ID | 632 |
Feature activation | +8.51e-02 |
Pos logit contributions | |
disl | +0.001 |
Sorry | +0.000 |
killed | +0.000 |
Gig | +0.000 |
Thank | +0.000 |
Neg logit contributions | |
inn | -0.001 |
ches | -0.001 |
icky | -0.001 |
kernel | -0.001 |
nie | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
disl | +0.003 |
killed | +0.002 |
Sorry | +0.002 |
endant | +0.002 |
bows | +0.002 |
Neg logit contributions | |
inn | -0.002 |
icky | -0.002 |
ches | -0.002 |
kernel | -0.002 |
aid | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
inn | +0.001 |
ches | +0.001 |
icky | +0.001 |
kernel | +0.001 |
aid | +0.001 |
Neg logit contributions | |
disl | -0.001 |
killed | -0.001 |
endant | -0.001 |
Gig | -0.001 |
Thank | -0.001 |
Token | best |
Token ID | 1266 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
inn | +0.027 |
ches | +0.024 |
icky | +0.024 |
kernel | +0.023 |
nie | +0.023 |
Neg logit contributions | |
disl | -0.021 |
killed | -0.016 |
Thank | -0.016 |
Gig | -0.016 |
jewels | -0.016 |
Token | tw |
Token ID | 665 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
inn | +0.051 |
ches | +0.047 |
icky | +0.045 |
kernel | +0.044 |
nie | +0.043 |
Neg logit contributions | |
disl | -0.051 |
jewels | -0.044 |
bows | -0.043 |
endant | -0.042 |
killed | -0.041 |
Token | ig |
Token ID | 328 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
inn | +0.024 |
aid | +0.023 |
kernel | +0.023 |
Alex | +0.021 |
nie | +0.021 |
Neg logit contributions | |
disl | -0.069 |
endant | -0.063 |
majesty | -0.060 |
mm | -0.060 |
bows | -0.060 |
Token | in |
Token ID | 287 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
inn | +0.127 |
ud | +0.111 |
icky | +0.108 |
kernel | +0.108 |
aid | +0.108 |
Neg logit contributions | |
disl | -0.142 |
bows | -0.117 |
endant | -0.114 |
killed | -0.112 |
jewels | -0.112 |
Token | the |
Token ID | 262 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
disl | +0.002 |
killed | +0.002 |
jewels | +0.002 |
Sorry | +0.002 |
Thank | +0.002 |
Neg logit contributions | |
inn | -0.002 |
ches | -0.002 |
nie | -0.002 |
ash | -0.002 |
kernel | -0.002 |
Token | world |
Token ID | 995 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
disl | +0.028 |
Thank | +0.022 |
killed | +0.022 |
Gig | +0.022 |
jewels | +0.022 |
Neg logit contributions | |
inn | -0.025 |
ches | -0.022 |
icky | -0.022 |
kernel | -0.021 |
nie | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
disl | +0.032 |
killed | +0.025 |
bows | +0.025 |
Thank | +0.024 |
Sorry | +0.024 |
Neg logit contributions | |
inn | -0.032 |
icky | -0.028 |
ches | -0.028 |
kernel | -0.028 |
aid | -0.027 |
Token | It |
Token ID | 632 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
disl | +0.003 |
killed | +0.002 |
endant | +0.002 |
bows | +0.002 |
Gig | +0.002 |
Neg logit contributions | |
inn | -0.003 |
ches | -0.003 |
icky | -0.003 |
aid | -0.002 |
kernel | -0.002 |
Token | 's |
Token ID | 338 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
inn | +0.059 |
ud | +0.043 |
icky | +0.043 |
kernel | +0.042 |
pron | +0.041 |
Neg logit contributions | |
disl | -0.101 |
killed | -0.087 |
Gig | -0.086 |
Sorry | -0.084 |
Thank | -0.083 |
Token | go |
Token ID | 467 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
disl | +0.010 |
endant | +0.008 |
bows | +0.008 |
killed | +0.008 |
Thank | +0.008 |
Neg logit contributions | |
inn | -0.007 |
ches | -0.007 |
aid | -0.007 |
kernel | -0.007 |
icky | -0.007 |
Token | catch |
Token ID | 4929 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
inn | +0.009 |
ches | +0.008 |
icky | +0.008 |
kernel | +0.008 |
nie | +0.008 |
Neg logit contributions | |
disl | -0.017 |
killed | -0.013 |
Sorry | -0.013 |
endant | -0.013 |
Thank | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
inn | +0.041 |
nie | +0.035 |
icky | +0.034 |
aid | +0.034 |
kernel | +0.033 |
Neg logit contributions | |
disl | -0.044 |
Gig | -0.035 |
killed | -0.035 |
statues | -0.033 |
Thank | -0.033 |
Token | k |
Token ID | 479 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
inn | +0.009 |
ches | +0.008 |
icky | +0.008 |
kernel | +0.007 |
nie | +0.007 |
Neg logit contributions | |
disl | -0.012 |
killed | -0.009 |
Gig | -0.009 |
Sorry | -0.009 |
Thank | -0.009 |
Token | ang |
Token ID | 648 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
inn | +0.027 |
aid | +0.026 |
nie | +0.025 |
icky | +0.025 |
kernel | +0.024 |
Neg logit contributions | |
disl | -0.022 |
killed | -0.020 |
Thank | -0.020 |
Sorry | -0.019 |
Tri | -0.019 |
Token | aroo |
Token ID | 38049 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
inn | +0.157 |
icky | +0.149 |
aid | +0.148 |
oby | +0.146 |
ud | +0.143 |
Neg logit contributions | |
disl | -0.088 |
Gig | -0.080 |
Sorry | -0.079 |
killed | -0.078 |
Tri | -0.075 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
inn | +0.049 |
icky | +0.043 |
kernel | +0.042 |
aid | +0.042 |
ches | +0.042 |
Neg logit contributions | |
disl | -0.031 |
Gig | -0.023 |
killed | -0.023 |
bows | -0.022 |
Sorry | -0.022 |
Token | Ben |
Token ID | 3932 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
inn | +0.004 |
ches | +0.003 |
ash | +0.003 |
icky | +0.003 |
mate | +0.003 |
Neg logit contributions | |
disl | -0.004 |
Gig | -0.004 |
Sorry | -0.004 |
killed | -0.004 |
Thank | -0.004 |
Token | says |
Token ID | 1139 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
inn | +0.033 |
kernel | +0.032 |
pron | +0.032 |
mate | +0.031 |
icky | +0.031 |
Neg logit contributions | |
disl | -0.012 |
killed | -0.006 |
bows | -0.006 |
Gig | -0.006 |
Tri | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
inn | +0.021 |
kernel | +0.020 |
ud | +0.020 |
nie | +0.019 |
pron | +0.019 |
Neg logit contributions | |
disl | -0.015 |
killed | -0.012 |
Tri | -0.012 |
bows | -0.011 |
Thank | -0.011 |
Token | conversation |
Token ID | 5273 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
disl | +0.047 |
endant | +0.037 |
killed | +0.037 |
Thank | +0.037 |
Sorry | +0.037 |
Neg logit contributions | |
inn | -0.037 |
ches | -0.034 |
icky | -0.033 |
aid | -0.033 |
nie | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
disl | +0.058 |
statues | +0.046 |
bows | +0.046 |
killed | +0.046 |
Thank | +0.046 |
Neg logit contributions | |
inn | -0.058 |
icky | -0.051 |
ches | -0.051 |
nie | -0.050 |
kernel | -0.050 |
Token | encouraged |
Token ID | 10085 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
inn | +0.017 |
kernel | +0.016 |
ches | +0.016 |
nie | +0.016 |
aid | +0.015 |
Neg logit contributions | |
disl | -0.018 |
endant | -0.014 |
bows | -0.013 |
mm | -0.013 |
killed | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
inn | +0.024 |
kernel | +0.022 |
icky | +0.021 |
pron | +0.021 |
aid | +0.021 |
Neg logit contributions | |
disl | -0.025 |
Gig | -0.021 |
Tri | -0.020 |
killed | -0.020 |
Thank | -0.019 |
Token | k |
Token ID | 479 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
inn | +0.019 |
nie | +0.019 |
kernel | +0.018 |
cable | +0.018 |
aid | +0.018 |
Neg logit contributions | |
disl | -0.030 |
endant | -0.025 |
mm | -0.024 |
Sorry | -0.024 |
killed | -0.023 |
Token | ang |
Token ID | 648 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
inn | +0.032 |
ches | +0.028 |
nie | +0.028 |
icky | +0.028 |
kernel | +0.028 |
Neg logit contributions | |
disl | -0.042 |
killed | -0.036 |
Gig | -0.035 |
endant | -0.035 |
Tri | -0.035 |
Token | aroo |
Token ID | 38049 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
inn | +0.145 |
icky | +0.133 |
mat | +0.132 |
pron | +0.131 |
ud | +0.131 |
Neg logit contributions | |
disl | -0.110 |
Gig | -0.095 |
Tri | -0.094 |
killed | -0.092 |
lucky | -0.085 |
Token | to |
Token ID | 284 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
inn | +0.055 |
icky | +0.046 |
kernel | +0.046 |
ches | +0.045 |
nie | +0.044 |
Neg logit contributions | |
disl | -0.082 |
killed | -0.066 |
Gig | -0.066 |
Tri | -0.064 |
bows | -0.064 |
Token | go |
Token ID | 467 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
disl | +0.004 |
endant | +0.003 |
killed | +0.003 |
bows | +0.003 |
Sorry | +0.003 |
Neg logit contributions | |
inn | -0.003 |
ches | -0.003 |
aid | -0.003 |
icky | -0.003 |
kernel | -0.003 |
Token | ahead |
Token ID | 4058 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
inn | +0.012 |
ches | +0.010 |
icky | +0.010 |
kernel | +0.010 |
nie | +0.010 |
Neg logit contributions | |
disl | -0.020 |
killed | -0.016 |
Sorry | -0.016 |
Gig | -0.016 |
Thank | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
inn | +0.106 |
ches | +0.102 |
kernel | +0.101 |
nie | +0.099 |
Alex | +0.099 |
Neg logit contributions | |
disl | -0.053 |
lucky | -0.046 |
Gig | -0.046 |
Thank | -0.045 |
Tri | -0.045 |
Token | help |
Token ID | 1037 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
disl | +0.008 |
endant | +0.006 |
Gig | +0.006 |
killed | +0.006 |
bows | +0.006 |
Neg logit contributions | |
inn | -0.008 |
ches | -0.007 |
kernel | -0.007 |
aid | -0.007 |
nie | -0.007 |
Token | each |
Token ID | 1123 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
inn | +0.035 |
kernel | +0.030 |
icky | +0.029 |
ud | +0.029 |
mat | +0.028 |
Neg logit contributions | |
disl | -0.031 |
killed | -0.024 |
Gig | -0.023 |
Sorry | -0.023 |
Tri | -0.023 |
Token | other |
Token ID | 584 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
inn | +0.072 |
icky | +0.061 |
ches | +0.060 |
ud | +0.057 |
Alex | +0.056 |
Neg logit contributions | |
disl | -0.049 |
lucky | -0.040 |
killed | -0.039 |
Gig | -0.038 |
Thank | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
disl | +0.027 |
bows | +0.021 |
killed | +0.021 |
lucky | +0.021 |
jewels | +0.021 |
Neg logit contributions | |
inn | -0.025 |
icky | -0.020 |
ud | -0.020 |
kernel | -0.020 |
ches | -0.020 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
inn | +0.024 |
ches | +0.022 |
kernel | +0.021 |
nie | +0.021 |
icky | +0.020 |
Neg logit contributions | |
disl | -0.021 |
Sorry | -0.016 |
Gig | -0.016 |
Thank | -0.016 |
Thank | -0.016 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
disl | +0.017 |
Thank | +0.015 |
Gig | +0.014 |
Tri | +0.014 |
killed | +0.014 |
Neg logit contributions | |
inn | -0.034 |
kernel | -0.032 |
nie | -0.032 |
ches | -0.032 |
ler | -0.030 |
Token | upon |
Token ID | 2402 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
disl | +0.070 |
lucky | +0.059 |
endant | +0.056 |
Gig | +0.055 |
Sorry | +0.053 |
Neg logit contributions | |
kernel | -0.086 |
inn | -0.084 |
ches | -0.083 |
aid | -0.082 |
nie | -0.078 |
Token | a |
Token ID | 257 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
inn | +0.014 |
ches | +0.013 |
kernel | +0.012 |
icky | +0.012 |
ash | +0.012 |
Neg logit contributions | |
disl | -0.011 |
killed | -0.008 |
Thank | -0.008 |
Gig | -0.008 |
statues | -0.008 |
Token | time |
Token ID | 640 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
inn | +0.034 |
kernel | +0.033 |
ware | +0.033 |
pan | +0.032 |
mate | +0.032 |
Neg logit contributions | |
disl | -0.041 |
lucky | -0.035 |
dear | -0.033 |
Thank | -0.033 |
fun | -0.033 |
Token | there |
Token ID | 612 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
disl | +0.009 |
killed | +0.007 |
Sorry | +0.006 |
Gig | +0.006 |
endant | +0.006 |
Neg logit contributions | |
inn | -0.009 |
ches | -0.008 |
kernel | -0.008 |
icky | -0.008 |
nie | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
disl | +0.013 |
killed | +0.010 |
Sorry | +0.010 |
Thank | +0.010 |
Gig | +0.010 |
Neg logit contributions | |
inn | -0.012 |
ches | -0.011 |
kernel | -0.010 |
nie | -0.010 |
aid | -0.010 |
Token | lake |
Token ID | 13546 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
disl | +0.008 |
killed | +0.006 |
Thank | +0.006 |
Gig | +0.006 |
Sorry | +0.006 |
Neg logit contributions | |
inn | -0.007 |
ches | -0.006 |
icky | -0.006 |
kernel | -0.006 |
nie | -0.006 |
Token | again |
Token ID | 757 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
inn | +0.022 |
icky | +0.019 |
ches | +0.019 |
ud | +0.018 |
Alex | +0.018 |
Neg logit contributions | |
disl | -0.023 |
Gig | -0.018 |
Thank | -0.018 |
statues | -0.018 |
killed | -0.018 |
Token | soon |
Token ID | 2582 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
disl | +0.019 |
killed | +0.015 |
Thank | +0.015 |
Gig | +0.015 |
Sorry | +0.014 |
Neg logit contributions | |
inn | -0.016 |
icky | -0.014 |
ches | -0.014 |
kernel | -0.014 |
nie | -0.013 |
Token | ! |
Token ID | 0 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
disl | +0.028 |
endant | +0.022 |
Sorry | +0.022 |
Gig | +0.022 |
killed | +0.022 |
Neg logit contributions | |
inn | -0.015 |
ches | -0.014 |
aid | -0.013 |
icky | -0.013 |
kernel | -0.013 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
inn | +0.035 |
ches | +0.033 |
kernel | +0.032 |
icky | +0.032 |
nie | +0.032 |
Neg logit contributions | |
disl | -0.035 |
Gig | -0.028 |
Sorry | -0.028 |
Thank | -0.027 |
Tri | -0.027 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
disl | +0.025 |
Thank | +0.020 |
Gig | +0.020 |
killed | +0.020 |
Tri | +0.019 |
Neg logit contributions | |
inn | -0.035 |
kernel | -0.032 |
ches | -0.032 |
nie | -0.032 |
aid | -0.031 |
Token | upon |
Token ID | 2402 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
disl | +0.066 |
lucky | +0.059 |
endant | +0.055 |
Gig | +0.054 |
glad | +0.052 |
Neg logit contributions | |
kernel | -0.093 |
ches | -0.088 |
inn | -0.088 |
aid | -0.087 |
panc | -0.086 |
Token | a |
Token ID | 257 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
inn | +0.001 |
ches | +0.001 |
icky | +0.001 |
kernel | +0.001 |
nie | +0.001 |
Neg logit contributions | |
disl | -0.001 |
killed | -0.001 |
Thank | -0.001 |
Gig | -0.001 |
endant | -0.001 |
Token | time |
Token ID | 640 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
inn | +0.028 |
kernel | +0.026 |
ware | +0.025 |
ches | +0.025 |
pan | +0.025 |
Neg logit contributions | |
disl | -0.040 |
lucky | -0.034 |
Thank | -0.034 |
dear | -0.033 |
Gig | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
disl | +0.017 |
killed | +0.014 |
Thank | +0.013 |
endant | +0.013 |
Sorry | +0.013 |
Neg logit contributions | |
inn | -0.015 |
icky | -0.013 |
ches | -0.013 |
nie | -0.012 |
kernel | -0.012 |
Token | there |
Token ID | 612 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
disl | +0.017 |
lucky | +0.016 |
Thank | +0.015 |
Gig | +0.015 |
killed | +0.014 |
Neg logit contributions | |
ches | -0.038 |
kernel | -0.037 |
inn | -0.037 |
ash | -0.037 |
aid | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
disl | +0.003 |
killed | +0.003 |
Sorry | +0.003 |
Thank | +0.003 |
endant | +0.003 |
Neg logit contributions | |
inn | -0.002 |
ches | -0.001 |
icky | -0.001 |
kernel | -0.001 |
aid | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
disl | +0.028 |
killed | +0.022 |
Thank | +0.022 |
Sorry | +0.022 |
endant | +0.022 |
Neg logit contributions | |
inn | -0.018 |
ches | -0.015 |
icky | -0.015 |
kernel | -0.015 |
aid | -0.015 |
Token | zoo |
Token ID | 26626 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
disl | +0.018 |
endant | +0.014 |
bows | +0.014 |
killed | +0.014 |
mm | +0.014 |
Neg logit contributions | |
aid | -0.012 |
inn | -0.012 |
corner | -0.012 |
chair | -0.012 |
kernel | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
disl | +0.049 |
killed | +0.040 |
statues | +0.039 |
bows | +0.039 |
Gig | +0.039 |
Neg logit contributions | |
inn | -0.042 |
icky | -0.036 |
ches | -0.036 |
kernel | -0.035 |
nie | -0.034 |
Token | The |
Token ID | 383 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
disl | +0.018 |
killed | +0.015 |
endant | +0.014 |
jewels | +0.014 |
bows | +0.014 |
Neg logit contributions | |
inn | -0.014 |
aid | -0.013 |
ches | -0.013 |
icky | -0.012 |
nie | -0.012 |
Token | zoo |
Token ID | 26626 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
disl | +0.010 |
endant | +0.009 |
bleed | +0.009 |
killed | +0.008 |
uts | +0.008 |
Neg logit contributions | |
cable | -0.004 |
corner | -0.004 |
rug | -0.004 |
tray | -0.004 |
player | -0.004 |
Token | has |
Token ID | 468 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
disl | +0.096 |
Gig | +0.077 |
Thank | +0.077 |
killed | +0.075 |
endant | +0.075 |
Neg logit contributions | |
inn | -0.056 |
ches | -0.054 |
icky | -0.051 |
nie | -0.050 |
kernel | -0.050 |
Token | many |
Token ID | 867 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
inn | +0.003 |
ches | +0.003 |
aid | +0.003 |
icky | +0.002 |
kernel | +0.002 |
Neg logit contributions | |
disl | -0.004 |
Sorry | -0.003 |
mm | -0.003 |
Thank | -0.003 |
endant | -0.003 |
Token | animals |
Token ID | 4695 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
disl | +0.054 |
Sorry | +0.049 |
Thank | +0.047 |
mm | +0.043 |
Gig | +0.042 |
Neg logit contributions | |
corner | -0.036 |
ches | -0.035 |
ide | -0.035 |
chair | -0.034 |
nie | -0.034 |
Token | from |
Token ID | 422 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
disl | +0.054 |
Sorry | +0.045 |
Thank | +0.045 |
mm | +0.044 |
Gig | +0.044 |
Neg logit contributions | |
inn | -0.025 |
ches | -0.024 |
' | -0.023 |
icky | -0.022 |
aid | -0.021 |
Token | different |
Token ID | 1180 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
disl | +0.031 |
killed | +0.025 |
Sorry | +0.024 |
endant | +0.024 |
Thank | +0.024 |
Neg logit contributions | |
inn | -0.020 |
ches | -0.018 |
icky | -0.018 |
kernel | -0.017 |
nie | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
inn | +0.021 |
nie | +0.020 |
kernel | +0.020 |
ches | +0.019 |
ler | +0.019 |
Neg logit contributions | |
disl | -0.019 |
Gig | -0.015 |
Thank | -0.015 |
killed | -0.014 |
Tri | -0.014 |
Token | The |
Token ID | 464 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
inn | +0.001 |
icky | +0.001 |
nie | +0.001 |
ash | +0.001 |
kernel | +0.001 |
Neg logit contributions | |
disl | -0.001 |
Thank | -0.001 |
killed | -0.001 |
Gig | -0.001 |
lucky | -0.001 |
Token | moral |
Token ID | 6573 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
disl | +0.005 |
endant | +0.004 |
bows | +0.004 |
Gig | +0.004 |
Sorry | +0.004 |
Neg logit contributions | |
inn | -0.004 |
ches | -0.003 |
icky | -0.003 |
aid | -0.003 |
kernel | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
disl | +0.049 |
killed | +0.043 |
Thank | +0.042 |
Gig | +0.042 |
Tri | +0.041 |
Neg logit contributions | |
inn | -0.029 |
ches | -0.024 |
kernel | -0.024 |
icky | -0.024 |
nie | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
inn | +0.034 |
about | +0.031 |
ud | +0.031 |
aid | +0.030 |
ash | +0.030 |
Neg logit contributions | |
disl | -0.021 |
Gig | -0.017 |
lucky | -0.016 |
Tri | -0.015 |
glad | -0.014 |
Token | story |
Token ID | 1621 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
inn | +0.007 |
ches | +0.006 |
icky | +0.006 |
kernel | +0.006 |
nie | +0.006 |
Neg logit contributions | |
disl | -0.013 |
killed | -0.010 |
Gig | -0.010 |
Thank | -0.010 |
Sorry | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
disl | +0.072 |
Sorry | +0.057 |
bows | +0.056 |
killed | +0.055 |
Thank | +0.054 |
Neg logit contributions | |
inn | -0.079 |
kernel | -0.071 |
ches | -0.069 |
nie | -0.067 |
icky | -0.067 |
Token | clear |
Token ID | 1598 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
disl | +0.014 |
killed | +0.011 |
Gig | +0.010 |
Thank | +0.010 |
Sorry | +0.010 |
Neg logit contributions | |
inn | -0.017 |
ches | -0.015 |
kernel | -0.015 |
icky | -0.015 |
aid | -0.015 |
Token | : |
Token ID | 25 |
Feature activation | -7.98e-02 |
Pos logit contributions | |
inn | +0.023 |
kernel | +0.020 |
icky | +0.020 |
nie | +0.019 |
aid | +0.019 |
Neg logit contributions | |
disl | -0.024 |
killed | -0.018 |
bows | -0.018 |
Sorry | -0.017 |
Thank | -0.017 |
Token | never |
Token ID | 1239 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
inn | +0.002 |
ches | +0.002 |
icky | +0.002 |
kernel | +0.002 |
nie | +0.002 |
Neg logit contributions | |
disl | -0.002 |
killed | -0.002 |
Thank | -0.002 |
Gig | -0.002 |
Sorry | -0.002 |
Token | face |
Token ID | 1986 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
disl | +0.036 |
endant | +0.029 |
mm | +0.029 |
Sorry | +0.028 |
Gig | +0.028 |
Neg logit contributions | |
inn | -0.035 |
ches | -0.033 |
nie | -0.033 |
aid | -0.032 |
icky | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
disl | +0.027 |
Sorry | +0.021 |
endant | +0.021 |
killed | +0.021 |
Gig | +0.020 |
Neg logit contributions | |
inn | -0.027 |
ches | -0.024 |
icky | -0.024 |
nie | -0.023 |
kernel | -0.023 |
Token | great |
Token ID | 1049 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
disl | +0.024 |
killed | +0.017 |
endant | +0.017 |
Gig | +0.017 |
Sorry | +0.016 |
Neg logit contributions | |
inn | -0.036 |
ches | -0.033 |
icky | -0.033 |
kernel | -0.032 |
nie | -0.032 |
Token | time |
Token ID | 640 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
disl | +0.042 |
bows | +0.035 |
Thank | +0.035 |
lucky | +0.034 |
Gig | +0.034 |
Neg logit contributions | |
inn | -0.025 |
ches | -0.023 |
icky | -0.022 |
kernel | -0.022 |
nie | -0.021 |
Token | ! |
Token ID | 0 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
inn | +0.017 |
ches | +0.015 |
icky | +0.014 |
kernel | +0.014 |
nie | +0.014 |
Neg logit contributions | |
disl | -0.024 |
killed | -0.019 |
Gig | -0.019 |
Thank | -0.019 |
Sorry | -0.019 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
inn | +0.016 |
icky | +0.015 |
ches | +0.014 |
aid | +0.014 |
nie | +0.014 |
Neg logit contributions | |
disl | -0.020 |
killed | -0.016 |
endant | -0.016 |
Sorry | -0.015 |
jewels | -0.015 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
disl | +0.027 |
Thank | +0.021 |
Gig | +0.021 |
killed | +0.020 |
Tri | +0.020 |
Neg logit contributions | |
inn | -0.041 |
kernel | -0.039 |
ches | -0.039 |
nie | -0.039 |
aid | -0.037 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
disl | +0.077 |
lucky | +0.065 |
endant | +0.062 |
Gig | +0.062 |
Tri | +0.059 |
Neg logit contributions | |
kernel | -0.088 |
inn | -0.087 |
ches | -0.086 |
aid | -0.082 |
nie | -0.081 |
Token | a |
Token ID | 257 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
inn | +0.004 |
ches | +0.003 |
kernel | +0.003 |
icky | +0.003 |
nie | +0.003 |
Neg logit contributions | |
disl | -0.003 |
killed | -0.002 |
Thank | -0.002 |
Gig | -0.002 |
statues | -0.002 |
Token | time |
Token ID | 640 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
inn | +0.027 |
kernel | +0.025 |
ches | +0.024 |
ware | +0.024 |
pan | +0.024 |
Neg logit contributions | |
disl | -0.039 |
lucky | -0.032 |
Thank | -0.032 |
Gig | -0.031 |
dear | -0.031 |
Token | there |
Token ID | 612 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
disl | +0.011 |
killed | +0.008 |
Gig | +0.008 |
Sorry | +0.008 |
Tri | +0.008 |
Neg logit contributions | |
inn | -0.011 |
ches | -0.010 |
kernel | -0.010 |
nie | -0.010 |
icky | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
disl | +0.016 |
killed | +0.013 |
Thank | +0.013 |
Sorry | +0.013 |
Gig | +0.013 |
Neg logit contributions | |
inn | -0.016 |
ches | -0.015 |
kernel | -0.014 |
nie | -0.014 |
aid | -0.014 |
Token | ! |
Token ID | 0 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
inn | +0.041 |
icky | +0.035 |
kernel | +0.034 |
ches | +0.034 |
aid | +0.033 |
Neg logit contributions | |
disl | -0.051 |
killed | -0.041 |
Gig | -0.040 |
bows | -0.040 |
Thank | -0.039 |
Token | We |
Token ID | 775 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
inn | +0.036 |
ches | +0.032 |
icky | +0.032 |
nie | +0.031 |
aid | +0.031 |
Neg logit contributions | |
disl | -0.035 |
killed | -0.027 |
endant | -0.027 |
Gig | -0.026 |
Thank | -0.026 |
Token | need |
Token ID | 761 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
inn | +0.038 |
ches | +0.037 |
' | +0.035 |
nie | +0.034 |
kernel | +0.033 |
Neg logit contributions | |
disl | -0.044 |
mm | -0.034 |
endant | -0.034 |
statues | -0.033 |
bows | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
inn | +0.016 |
ches | +0.014 |
icky | +0.014 |
kernel | +0.013 |
nie | +0.013 |
Neg logit contributions | |
disl | -0.035 |
killed | -0.029 |
Gig | -0.028 |
Sorry | -0.028 |
Thank | -0.028 |
Token | rush |
Token ID | 10484 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
disl | +0.021 |
endant | +0.017 |
bows | +0.017 |
Thank | +0.016 |
Sorry | +0.016 |
Neg logit contributions | |
inn | -0.016 |
aid | -0.016 |
ches | -0.015 |
icky | -0.015 |
kernel | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
inn | +0.015 |
ches | +0.013 |
icky | +0.013 |
kernel | +0.013 |
aid | +0.012 |
Neg logit contributions | |
disl | -0.028 |
killed | -0.023 |
Gig | -0.023 |
Thank | -0.023 |
Sorry | -0.023 |
Token | play |
Token ID | 711 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
disl | +0.014 |
endant | +0.011 |
bows | +0.011 |
killed | +0.011 |
Gig | +0.011 |
Neg logit contributions | |
inn | -0.012 |
ches | -0.011 |
aid | -0.011 |
kernel | -0.011 |
icky | -0.011 |
Token | together |
Token ID | 1978 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
disl | +0.014 |
killed | +0.011 |
Thank | +0.011 |
Sorry | +0.011 |
Gig | +0.011 |
Neg logit contributions | |
inn | -0.016 |
icky | -0.014 |
kernel | -0.014 |
nie | -0.014 |
ches | -0.014 |
Token | !" |
Token ID | 2474 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
inn | +0.008 |
kernel | +0.008 |
ches | +0.007 |
aid | +0.007 |
icky | +0.007 |
Neg logit contributions | |
disl | -0.004 |
bows | -0.003 |
Thank | -0.003 |
killed | -0.003 |
Gig | -0.003 |
Token | |
Token ID | 220 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
inn | +0.011 |
ches | +0.011 |
' | +0.011 |
ide | +0.010 |
again | +0.010 |
Neg logit contributions | |
disl | -0.030 |
endant | -0.027 |
majesty | -0.026 |
killed | -0.026 |
statues | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
disl | +0.009 |
killed | +0.006 |
Gig | +0.006 |
Sorry | +0.006 |
Tri | +0.006 |
Neg logit contributions | |
inn | -0.009 |
kernel | -0.009 |
nie | -0.009 |
ches | -0.008 |
strand | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
disl | +0.000 |
killed | +0.000 |
Gig | +0.000 |
Tri | +0.000 |
jewels | +0.000 |
Neg logit contributions | |
inn | -0.000 |
ches | -0.000 |
kernel | -0.000 |
icky | -0.000 |
nie | -0.000 |
Token | cr |
Token ID | 1067 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
disl | +0.053 |
Gig | +0.046 |
Sorry | +0.044 |
Thank | +0.041 |
endant | +0.041 |
Neg logit contributions | |
nie | -0.028 |
inn | -0.027 |
icky | -0.027 |
chair | -0.027 |
sheet | -0.027 |
Token | ay |
Token ID | 323 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
disl | +0.028 |
Gig | +0.023 |
Sorry | +0.022 |
killed | +0.022 |
Thank | +0.022 |
Neg logit contributions | |
inn | -0.017 |
icky | -0.015 |
ches | -0.015 |
ud | -0.013 |
ide | -0.013 |
Token | ons |
Token ID | 684 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
disl | +0.017 |
Gig | +0.014 |
Sorry | +0.014 |
Thank | +0.014 |
killed | +0.014 |
Neg logit contributions | |
inn | -0.013 |
icky | -0.011 |
ches | -0.011 |
kernel | -0.011 |
nie | -0.010 |
Token | started |
Token ID | 2067 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
disl | +0.020 |
Gig | +0.015 |
Sorry | +0.015 |
Thank | +0.015 |
mm | +0.015 |
Neg logit contributions | |
inn | -0.019 |
ches | -0.018 |
kernel | -0.017 |
icky | -0.017 |
aid | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
inn | +0.026 |
icky | +0.022 |
ches | +0.022 |
kernel | +0.021 |
aid | +0.020 |
Neg logit contributions | |
disl | -0.052 |
Sorry | -0.043 |
Thank | -0.043 |
Gig | -0.043 |
killed | -0.043 |
Token | move |
Token ID | 1445 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
disl | +0.002 |
endant | +0.001 |
Gig | +0.001 |
mm | +0.001 |
Sorry | +0.001 |
Neg logit contributions | |
inn | -0.001 |
ches | -0.001 |
icky | -0.001 |
aid | -0.001 |
kernel | -0.001 |
Token | around |
Token ID | 1088 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
inn | +0.042 |
kernel | +0.036 |
icky | +0.036 |
ches | +0.036 |
nie | +0.035 |
Neg logit contributions | |
disl | -0.059 |
killed | -0.049 |
bows | -0.048 |
statues | -0.048 |
Tri | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
inn | +0.023 |
ches | +0.020 |
kernel | +0.019 |
icky | +0.019 |
nie | +0.019 |
Neg logit contributions | |
disl | -0.028 |
killed | -0.022 |
Thank | -0.022 |
statues | -0.022 |
Gig | -0.022 |
Token | paper |
Token ID | 3348 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
disl | +0.028 |
Gig | +0.024 |
killed | +0.023 |
Sorry | +0.023 |
endant | +0.023 |
Neg logit contributions | |
inn | -0.010 |
icky | -0.008 |
aid | -0.008 |
nie | -0.008 |
ches | -0.008 |
Token | ! |
Token ID | 0 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
inn | +0.016 |
ches | +0.014 |
icky | +0.014 |
nie | +0.013 |
kernel | +0.013 |
Neg logit contributions | |
disl | -0.021 |
killed | -0.017 |
bows | -0.017 |
endant | -0.017 |
statues | -0.017 |
Token | you |
Token ID | 345 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
ches | +0.004 |
inn | +0.004 |
nie | +0.004 |
icky | +0.004 |
chair | +0.004 |
Neg logit contributions | |
disl | -0.006 |
bows | -0.005 |
endant | -0.005 |
killed | -0.005 |
vell | -0.005 |
Token | can |
Token ID | 460 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
inn | +0.011 |
ches | +0.011 |
icky | +0.010 |
nie | +0.010 |
kernel | +0.010 |
Neg logit contributions | |
disl | -0.014 |
Thank | -0.011 |
Gig | -0.011 |
bows | -0.010 |
statues | -0.010 |
Token | build |
Token ID | 1382 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
inn | +0.007 |
ches | +0.006 |
icky | +0.006 |
kernel | +0.006 |
aid | +0.006 |
Neg logit contributions | |
disl | -0.008 |
killed | -0.006 |
Gig | -0.006 |
endant | -0.006 |
Thank | -0.006 |
Token | your |
Token ID | 534 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
inn | +0.017 |
icky | +0.016 |
ches | +0.016 |
aid | +0.015 |
kernel | +0.014 |
Neg logit contributions | |
disl | -0.028 |
Thank | -0.024 |
Sorry | -0.023 |
bows | -0.023 |
Gig | -0.022 |
Token | nest |
Token ID | 16343 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
disl | +0.010 |
Sorry | +0.008 |
Thank | +0.008 |
bows | +0.008 |
killed | +0.008 |
Neg logit contributions | |
inn | -0.006 |
aid | -0.005 |
ches | -0.005 |
icky | -0.005 |
kernel | -0.005 |
Token | here |
Token ID | 994 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
disl | +0.005 |
bows | +0.004 |
killed | +0.004 |
endant | +0.004 |
jewels | +0.004 |
Neg logit contributions | |
inn | -0.004 |
icky | -0.004 |
ches | -0.004 |
kernel | -0.004 |
aid | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
disl | +0.003 |
killed | +0.002 |
bows | +0.002 |
jewels | +0.002 |
Gig | +0.002 |
Neg logit contributions | |
inn | -0.003 |
ches | -0.003 |
icky | -0.003 |
kernel | -0.003 |
nie | -0.003 |
Token | But |
Token ID | 887 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
inn | +0.008 |
ches | +0.007 |
icky | +0.007 |
aid | +0.007 |
nie | +0.007 |
Neg logit contributions | |
disl | -0.009 |
killed | -0.007 |
endant | -0.007 |
bows | -0.007 |
statues | -0.007 |
Token | please |
Token ID | 3387 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
inn | +0.032 |
ches | +0.029 |
icky | +0.029 |
kernel | +0.028 |
nie | +0.028 |
Neg logit contributions | |
disl | -0.029 |
killed | -0.022 |
endant | -0.021 |
Gig | -0.021 |
Thank | -0.021 |
Token | don |
Token ID | 836 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
disl | +0.032 |
endant | +0.026 |
statues | +0.026 |
Gig | +0.025 |
Thank | +0.025 |
Neg logit contributions | |
inn | -0.024 |
ches | -0.024 |
aid | -0.022 |
' | -0.022 |
nie | -0.022 |
Token | 't |
Token ID | 470 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
inn | +0.003 |
nie | +0.003 |
kernel | +0.003 |
ches | +0.002 |
aid | +0.002 |
Neg logit contributions | |
disl | -0.002 |
killed | -0.002 |
Sorry | -0.002 |
Gig | -0.002 |
Thank | -0.002 |
Token | down |
Token ID | 866 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
inn | +0.011 |
kernel | +0.009 |
ches | +0.009 |
icky | +0.009 |
nie | +0.009 |
Neg logit contributions | |
disl | -0.016 |
killed | -0.014 |
Gig | -0.013 |
endant | -0.013 |
jewels | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
inn | +0.045 |
ches | +0.043 |
nie | +0.041 |
kernel | +0.041 |
icky | +0.040 |
Neg logit contributions | |
disl | -0.047 |
killed | -0.039 |
Gig | -0.038 |
jewels | -0.038 |
Tri | -0.038 |
Token | They |
Token ID | 1119 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
disl | +0.011 |
bows | +0.009 |
killed | +0.009 |
statues | +0.009 |
endant | +0.009 |
Neg logit contributions | |
inn | -0.008 |
icky | -0.007 |
aid | -0.007 |
chair | -0.006 |
ches | -0.006 |
Token | opened |
Token ID | 4721 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
disl | +0.024 |
Sorry | +0.018 |
bows | +0.018 |
killed | +0.018 |
endant | +0.018 |
Neg logit contributions | |
inn | -0.026 |
ches | -0.023 |
kernel | -0.023 |
icky | -0.023 |
nie | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
disl | +0.018 |
Gig | +0.015 |
jewels | +0.015 |
statues | +0.015 |
killed | +0.015 |
Neg logit contributions | |
inn | -0.017 |
ches | -0.015 |
nie | -0.015 |
icky | -0.015 |
ash | -0.014 |
Token | jar |
Token ID | 17379 |
Feature activation | -7.19e-03 |
Pos logit contributions | |
disl | +0.012 |
jewels | +0.011 |
endant | +0.011 |
killed | +0.011 |
statues | +0.010 |
Neg logit contributions | |
inn | -0.010 |
ide | -0.009 |
nie | -0.008 |
ches | -0.008 |
icky | -0.008 |
Token | together |
Token ID | 1978 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
inn | +0.000 |
nie | +0.000 |
kernel | +0.000 |
ches | +0.000 |
icky | +0.000 |
Neg logit contributions | |
disl | -0.000 |
ocular | -0.000 |
endant | -0.000 |
bows | -0.000 |
jewels | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
disl | +0.004 |
statues | +0.003 |
jewels | +0.003 |
endant | +0.003 |
lucky | +0.003 |
Neg logit contributions | |
inn | -0.006 |
nie | -0.006 |
ches | -0.006 |
icky | -0.005 |
pron | -0.005 |
Token | shared |
Token ID | 4888 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
disl | +0.021 |
killed | +0.016 |
endant | +0.015 |
Sorry | +0.015 |
Gig | +0.015 |
Neg logit contributions | |
inn | -0.022 |
ches | -0.020 |
icky | -0.019 |
kernel | -0.019 |
nie | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
disl | +0.027 |
killed | +0.022 |
Sorry | +0.022 |
Thank | +0.022 |
bows | +0.022 |
Neg logit contributions | |
inn | -0.013 |
icky | -0.011 |
kernel | -0.010 |
ches | -0.010 |
aid | -0.010 |
Token | y |
Token ID | 331 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
inn | +0.002 |
ches | +0.002 |
icky | +0.002 |
kernel | +0.002 |
nie | +0.002 |
Neg logit contributions | |
disl | -0.003 |
killed | -0.002 |
Sorry | -0.002 |
Gig | -0.002 |
Thank | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
disl | +0.032 |
Gig | +0.026 |
Sorry | +0.026 |
Thank | +0.025 |
endant | +0.025 |
Neg logit contributions | |
inn | -0.019 |
ches | -0.016 |
icky | -0.016 |
kernel | -0.015 |
aid | -0.015 |
Token | fit |
Token ID | 4197 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
disl | +0.027 |
killed | +0.021 |
Sorry | +0.020 |
Thank | +0.020 |
bows | +0.020 |
Neg logit contributions | |
inn | -0.026 |
ches | -0.024 |
icky | -0.024 |
kernel | -0.023 |
nie | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
inn | +0.041 |
ches | +0.037 |
kernel | +0.036 |
aid | +0.036 |
icky | +0.036 |
Neg logit contributions | |
disl | -0.060 |
killed | -0.049 |
jewels | -0.049 |
statues | -0.049 |
bows | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
inn | +0.023 |
ches | +0.021 |
nie | +0.020 |
kernel | +0.019 |
ash | +0.019 |
Neg logit contributions | |
disl | -0.026 |
statues | -0.022 |
jewels | -0.021 |
killed | -0.020 |
Gig | -0.020 |
Token | top |
Token ID | 1353 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
disl | +0.011 |
statues | +0.009 |
jewels | +0.009 |
endant | +0.009 |
killed | +0.009 |
Neg logit contributions | |
inn | -0.008 |
ches | -0.007 |
icky | -0.007 |
kernel | -0.006 |
ud | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
inn | +0.044 |
ches | +0.041 |
Alex | +0.040 |
nie | +0.040 |
kernel | +0.039 |
Neg logit contributions | |
disl | -0.039 |
bows | -0.037 |
statues | -0.037 |
ocular | -0.036 |
endant | -0.035 |
Token | The |
Token ID | 383 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
disl | +0.027 |
killed | +0.021 |
endant | +0.021 |
Gig | +0.021 |
bows | +0.020 |
Neg logit contributions | |
inn | -0.025 |
icky | -0.022 |
ches | -0.021 |
aid | -0.021 |
kernel | -0.021 |
Token | tower |
Token ID | 10580 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
disl | +0.021 |
killed | +0.017 |
Thank | +0.017 |
statues | +0.017 |
endant | +0.017 |
Neg logit contributions | |
inn | -0.015 |
ches | -0.013 |
icky | -0.013 |
kernel | -0.012 |
nie | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
disl | +0.046 |
killed | +0.042 |
endant | +0.038 |
statues | +0.038 |
Thank | +0.038 |
Neg logit contributions | |
inn | -0.046 |
icky | -0.041 |
nie | -0.040 |
ches | -0.040 |
aid | -0.039 |
Token | not |
Token ID | 407 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
inn | +0.012 |
ches | +0.012 |
icky | +0.011 |
aid | +0.011 |
nie | +0.011 |
Neg logit contributions | |
disl | -0.010 |
killed | -0.009 |
jewels | -0.008 |
endant | -0.008 |
Thank | -0.008 |
Token | finished |
Token ID | 5201 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
inn | +0.005 |
ches | +0.004 |
icky | +0.004 |
kernel | +0.004 |
nie | +0.004 |
Neg logit contributions | |
disl | -0.004 |
killed | -0.003 |
Sorry | -0.003 |
Gig | -0.003 |
Thank | -0.003 |
Token | angry |
Token ID | 7954 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
disl | +0.046 |
bows | +0.042 |
mm | +0.040 |
Thank | +0.038 |
killed | +0.038 |
Neg logit contributions | |
inn | -0.048 |
icky | -0.042 |
nie | -0.040 |
ches | -0.040 |
nervously | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
disl | +0.057 |
killed | +0.047 |
Gig | +0.046 |
Thank | +0.046 |
Sorry | +0.046 |
Neg logit contributions | |
inn | -0.033 |
ches | -0.029 |
icky | -0.028 |
kernel | -0.027 |
nie | -0.027 |
Token | said |
Token ID | 531 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
disl | +0.001 |
endant | +0.001 |
bows | +0.001 |
mm | +0.001 |
Gig | +0.001 |
Neg logit contributions | |
inn | -0.001 |
ches | -0.001 |
nie | -0.001 |
kernel | -0.001 |
Alex | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
disl | +0.031 |
Gig | +0.024 |
killed | +0.024 |
Sorry | +0.023 |
Tri | +0.023 |
Neg logit contributions | |
inn | -0.034 |
ches | -0.031 |
kernel | -0.030 |
nie | -0.030 |
icky | -0.030 |
Token | " |
Token ID | 366 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
inn | +0.031 |
ches | +0.027 |
icky | +0.027 |
kernel | +0.026 |
nie | +0.025 |
Neg logit contributions | |
disl | -0.046 |
Gig | -0.038 |
Thank | -0.038 |
killed | -0.037 |
Sorry | -0.037 |
Token | This |
Token ID | 1212 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
disl | +0.012 |
killed | +0.009 |
Thank | +0.009 |
Gig | +0.009 |
Sorry | +0.009 |
Neg logit contributions | |
inn | -0.012 |
ches | -0.011 |
icky | -0.011 |
kernel | -0.011 |
nie | -0.011 |
Token | coin |
Token ID | 10752 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
inn | +0.039 |
ches | +0.035 |
icky | +0.034 |
kernel | +0.034 |
nie | +0.033 |
Neg logit contributions | |
disl | -0.054 |
killed | -0.043 |
Gig | -0.042 |
Sorry | -0.042 |
Thank | -0.042 |
Token | belongs |
Token ID | 14448 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
inn | +0.010 |
ches | +0.009 |
icky | +0.009 |
kernel | +0.008 |
nie | +0.008 |
Neg logit contributions | |
disl | -0.012 |
killed | -0.010 |
Gig | -0.010 |
Thank | -0.010 |
Sorry | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
inn | +0.015 |
icky | +0.012 |
kernel | +0.012 |
ches | +0.012 |
aid | +0.011 |
Neg logit contributions | |
disl | -0.027 |
killed | -0.023 |
endant | -0.022 |
Gig | -0.022 |
jewels | -0.022 |
Token | me |
Token ID | 502 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
disl | +0.005 |
endant | +0.004 |
bows | +0.004 |
killed | +0.004 |
Thank | +0.004 |
Neg logit contributions | |
inn | -0.004 |
ches | -0.003 |
icky | -0.003 |
aid | -0.003 |
kernel | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
inn | +0.016 |
ches | +0.014 |
icky | +0.014 |
kernel | +0.014 |
nie | +0.013 |
Neg logit contributions | |
disl | -0.015 |
killed | -0.012 |
Gig | -0.012 |
Sorry | -0.012 |
endant | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
disl | +0.009 |
Sorry | +0.008 |
killed | +0.008 |
endant | +0.007 |
Tri | +0.007 |
Neg logit contributions | |
inn | -0.004 |
ches | -0.003 |
kernel | -0.003 |
icky | -0.003 |
nie | -0.003 |
Token | tasty |
Token ID | 25103 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
disl | +0.020 |
killed | +0.015 |
endant | +0.015 |
bows | +0.014 |
majesty | +0.014 |
Neg logit contributions | |
inn | -0.021 |
nie | -0.020 |
kernel | -0.019 |
ches | -0.019 |
chair | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
inn | +0.001 |
ches | +0.001 |
icky | +0.001 |
kernel | +0.001 |
nie | +0.001 |
Neg logit contributions | |
disl | -0.001 |
killed | -0.001 |
Sorry | -0.001 |
endant | -0.001 |
Thank | -0.001 |
Token | so |
Token ID | 523 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
inn | +0.002 |
kernel | +0.002 |
chair | +0.002 |
nie | +0.002 |
mat | +0.001 |
Neg logit contributions | |
disl | -0.004 |
Sorry | -0.004 |
endant | -0.004 |
killed | -0.004 |
majesty | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
disl | +0.016 |
killed | +0.013 |
majesty | +0.013 |
endant | +0.013 |
bleed | +0.012 |
Neg logit contributions | |
inn | -0.007 |
again | -0.007 |
particular | -0.006 |
of | -0.006 |
one | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
inn | +0.012 |
icky | +0.011 |
ches | +0.011 |
aid | +0.011 |
kernel | +0.010 |
Neg logit contributions | |
disl | -0.010 |
killed | -0.008 |
Thank | -0.008 |
Gig | -0.008 |
Sorry | -0.008 |
Token | hard |
Token ID | 1327 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
inn | +0.012 |
ches | +0.011 |
icky | +0.010 |
kernel | +0.010 |
nie | +0.010 |
Neg logit contributions | |
disl | -0.011 |
killed | -0.009 |
Sorry | -0.009 |
endant | -0.009 |
Gig | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
inn | +0.032 |
ches | +0.027 |
icky | +0.027 |
nie | +0.026 |
kernel | +0.026 |
Neg logit contributions | |
disl | -0.067 |
Sorry | -0.056 |
Gig | -0.055 |
killed | -0.055 |
Thank | -0.055 |
Token | decide |
Token ID | 5409 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
disl | +0.014 |
endant | +0.011 |
Sorry | +0.011 |
bows | +0.011 |
killed | +0.011 |
Neg logit contributions | |
inn | -0.012 |
ches | -0.011 |
kernel | -0.011 |
aid | -0.010 |
icky | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
disl | +0.025 |
killed | +0.020 |
Gig | +0.020 |
endant | +0.020 |
Thank | +0.020 |
Neg logit contributions | |
inn | -0.019 |
ches | -0.016 |
icky | -0.016 |
kernel | -0.016 |
nie | -0.016 |
Token | In |
Token ID | 554 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
inn | +0.009 |
corner | +0.007 |
aid | +0.007 |
' | +0.007 |
ide | +0.007 |
Neg logit contributions | |
disl | -0.025 |
killed | -0.021 |
jewels | -0.020 |
majesty | -0.020 |
vell | -0.019 |
Token | mine |
Token ID | 6164 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
inn | +0.008 |
ches | +0.007 |
icky | +0.007 |
kernel | +0.007 |
nie | +0.007 |
Neg logit contributions | |
disl | -0.007 |
killed | -0.006 |
Gig | -0.006 |
Sorry | -0.006 |
endant | -0.006 |
Token | ! |
Token ID | 0 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
disl | +0.010 |
killed | +0.008 |
endant | +0.008 |
statues | +0.008 |
jewels | +0.007 |
Neg logit contributions | |
inn | -0.012 |
ches | -0.011 |
icky | -0.010 |
nie | -0.010 |
kernel | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
inn | +0.028 |
ches | +0.027 |
nie | +0.027 |
kernel | +0.026 |
ide | +0.025 |
Neg logit contributions | |
disl | -0.028 |
Gig | -0.022 |
Tri | -0.022 |
Sorry | -0.022 |
Thank | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
nie | +0.025 |
inn | +0.025 |
kernel | +0.025 |
ches | +0.024 |
ler | +0.024 |
Neg logit contributions | |
disl | -0.018 |
Gig | -0.013 |
Tri | -0.013 |
Thank | -0.012 |
killed | -0.012 |
Token | M |
Token ID | 44 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
disl | +0.008 |
Thank | +0.007 |
killed | +0.006 |
Tri | +0.006 |
Sorry | +0.006 |
Neg logit contributions | |
inn | -0.006 |
ches | -0.006 |
nie | -0.006 |
kernel | -0.006 |
crib | -0.006 |
Token | andy |
Token ID | 10757 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
inn | +0.008 |
icky | +0.006 |
ud | +0.005 |
ches | +0.005 |
ash | +0.004 |
Neg logit contributions | |
disl | -0.026 |
Thank | -0.023 |
bows | -0.022 |
killed | -0.022 |
Sorry | -0.022 |
Token | quickly |
Token ID | 2952 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
inn | +0.036 |
icky | +0.031 |
kernel | +0.031 |
ches | +0.030 |
nie | +0.029 |
Neg logit contributions | |
disl | -0.043 |
killed | -0.035 |
endant | -0.034 |
Gig | -0.034 |
Thank | -0.034 |
Token | raced |
Token ID | 32897 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
disl | +0.033 |
Sorry | +0.028 |
mm | +0.028 |
bows | +0.027 |
Thank | +0.025 |
Neg logit contributions | |
inn | -0.024 |
ches | -0.023 |
aid | -0.021 |
' | -0.021 |
kernel | -0.020 |
Token | over |
Token ID | 625 |
Feature activation | +9.61e-02 |
Pos logit contributions | |
inn | +0.005 |
icky | +0.005 |
ches | +0.005 |
kernel | +0.004 |
ud | +0.004 |
Neg logit contributions | |
disl | -0.008 |
Gig | -0.007 |
Tri | -0.007 |
Thank | -0.007 |
killed | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
disl | +0.003 |
Gig | +0.002 |
statues | +0.002 |
jewels | +0.002 |
Tri | +0.002 |
Neg logit contributions | |
inn | -0.002 |
nie | -0.002 |
ches | -0.002 |
kernel | -0.002 |
pron | -0.002 |
Token | picked |
Token ID | 6497 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
inn | +0.006 |
ches | +0.006 |
kernel | +0.005 |
nie | +0.005 |
icky | +0.005 |
Neg logit contributions | |
disl | -0.008 |
bows | -0.006 |
mm | -0.006 |
endant | -0.006 |
Sorry | -0.006 |
Token | if |
Token ID | 611 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
inn | +0.046 |
ches | +0.040 |
ash | +0.038 |
kernel | +0.037 |
icky | +0.037 |
Neg logit contributions | |
disl | -0.037 |
Thank | -0.029 |
Sorry | -0.028 |
killed | -0.028 |
lucky | -0.028 |
Token | you |
Token ID | 345 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
inn | +0.016 |
ches | +0.015 |
icky | +0.015 |
kernel | +0.015 |
nie | +0.015 |
Neg logit contributions | |
disl | -0.011 |
killed | -0.008 |
endant | -0.007 |
Gig | -0.007 |
Thank | -0.007 |
Token | want |
Token ID | 765 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
disl | +0.017 |
Gig | +0.013 |
killed | +0.013 |
endant | +0.012 |
Sorry | +0.012 |
Neg logit contributions | |
inn | -0.020 |
ches | -0.019 |
icky | -0.018 |
kernel | -0.018 |
nie | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
inn | +0.015 |
ches | +0.012 |
icky | +0.012 |
kernel | +0.012 |
nie | +0.012 |
Neg logit contributions | |
disl | -0.022 |
killed | -0.018 |
Thank | -0.018 |
Sorry | -0.018 |
Gig | -0.018 |
Token | be |
Token ID | 307 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
disl | +0.031 |
killed | +0.023 |
endant | +0.023 |
Gig | +0.023 |
Sorry | +0.023 |
Neg logit contributions | |
inn | -0.034 |
ches | -0.030 |
icky | -0.030 |
kernel | -0.030 |
aid | -0.029 |
Token | clever |
Token ID | 14169 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
disl | +0.010 |
killed | +0.008 |
Sorry | +0.007 |
endant | +0.007 |
Gig | +0.007 |
Neg logit contributions | |
inn | -0.012 |
ches | -0.011 |
icky | -0.011 |
kernel | -0.011 |
nie | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
inn | +0.031 |
kernel | +0.027 |
ches | +0.027 |
icky | +0.027 |
aid | +0.025 |
Neg logit contributions | |
disl | -0.034 |
killed | -0.027 |
jewels | -0.027 |
Thank | -0.027 |
bows | -0.026 |
Token | you |
Token ID | 345 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
inn | +0.017 |
ches | +0.015 |
icky | +0.015 |
kernel | +0.015 |
nie | +0.015 |
Neg logit contributions | |
disl | -0.012 |
killed | -0.009 |
Gig | -0.009 |
Thank | -0.009 |
Sorry | -0.009 |
Token | must |
Token ID | 1276 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
disl | +0.001 |
killed | +0.001 |
Gig | +0.001 |
endant | +0.001 |
Thank | +0.001 |
Neg logit contributions | |
inn | -0.002 |
ches | -0.001 |
icky | -0.001 |
kernel | -0.001 |
nie | -0.001 |
Token | write |
Token ID | 3551 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
disl | +0.027 |
killed | +0.020 |
Thank | +0.020 |
Gig | +0.020 |
Sorry | +0.020 |
Neg logit contributions | |
inn | -0.032 |
ches | -0.029 |
icky | -0.029 |
kernel | -0.029 |
nie | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
disl | +0.010 |
killed | +0.008 |
Gig | +0.008 |
endant | +0.008 |
Sorry | +0.008 |
Neg logit contributions | |
inn | -0.008 |
ches | -0.007 |
icky | -0.007 |
nie | -0.007 |
kernel | -0.007 |
Token | whenever |
Token ID | 8797 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
inn | +0.002 |
ches | +0.002 |
icky | +0.002 |
kernel | +0.002 |
nie | +0.002 |
Neg logit contributions | |
disl | -0.003 |
killed | -0.002 |
Gig | -0.002 |
Thank | -0.002 |
Sorry | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
disl | +0.033 |
endant | +0.027 |
killed | +0.026 |
bows | +0.026 |
Thank | +0.025 |
Neg logit contributions | |
inn | -0.022 |
icky | -0.019 |
nie | -0.019 |
aid | -0.019 |
kernel | -0.019 |
Token | felt |
Token ID | 2936 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
disl | +0.002 |
Gig | +0.002 |
Sorry | +0.002 |
endant | +0.002 |
killed | +0.002 |
Neg logit contributions | |
inn | -0.002 |
ches | -0.002 |
icky | -0.002 |
nie | -0.002 |
aid | -0.002 |
Token | sad |
Token ID | 6507 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
disl | +0.022 |
killed | +0.016 |
Gig | +0.015 |
Thank | +0.015 |
Sorry | +0.015 |
Neg logit contributions | |
inn | -0.030 |
ches | -0.028 |
icky | -0.028 |
kernel | -0.027 |
nie | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
disl | +0.082 |
killed | +0.065 |
endant | +0.065 |
Gig | +0.064 |
Thank | +0.064 |
Neg logit contributions | |
inn | -0.061 |
ches | -0.054 |
icky | -0.053 |
aid | -0.052 |
nie | -0.052 |
Token | she |
Token ID | 673 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
inn | +0.013 |
ches | +0.012 |
icky | +0.012 |
kernel | +0.012 |
aid | +0.011 |
Neg logit contributions | |
disl | -0.012 |
endant | -0.009 |
killed | -0.009 |
Sorry | -0.009 |
Thank | -0.009 |
Token | would |
Token ID | 561 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
inn | +0.011 |
ches | +0.010 |
icky | +0.010 |
kernel | +0.009 |
nie | +0.009 |
Neg logit contributions | |
disl | -0.015 |
killed | -0.012 |
Gig | -0.012 |
Sorry | -0.012 |
endant | -0.012 |
Token | remember |
Token ID | 3505 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
inn | +0.003 |
ches | +0.003 |
icky | +0.003 |
kernel | +0.003 |
nie | +0.003 |
Neg logit contributions | |
disl | -0.003 |
killed | -0.003 |
Gig | -0.002 |
Sorry | -0.002 |
Thank | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
disl | +0.013 |
killed | +0.010 |
Gig | +0.010 |
Thank | +0.010 |
statues | +0.010 |
Neg logit contributions | |
inn | -0.012 |
icky | -0.010 |
ches | -0.010 |
kernel | -0.010 |
nie | -0.010 |
Token | piano |
Token ID | 19132 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
inn | +0.004 |
icky | +0.004 |
ches | +0.004 |
ud | +0.003 |
ide | +0.003 |
Neg logit contributions | |
disl | -0.004 |
Thank | -0.003 |
lucky | -0.003 |
bows | -0.003 |
killed | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
disl | +0.021 |
killed | +0.016 |
bows | +0.016 |
Thank | +0.016 |
Sorry | +0.016 |
Neg logit contributions | |
inn | -0.016 |
icky | -0.014 |
ches | -0.014 |
kernel | -0.013 |
nie | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
inn | +0.043 |
nie | +0.038 |
ches | +0.037 |
icky | +0.037 |
kernel | +0.036 |
Neg logit contributions | |
disl | -0.062 |
killed | -0.050 |
endant | -0.050 |
jewels | -0.050 |
bows | -0.050 |
Token | hold |
Token ID | 1745 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
inn | +0.002 |
icky | +0.002 |
ches | +0.002 |
nie | +0.002 |
kernel | +0.002 |
Neg logit contributions | |
disl | -0.002 |
killed | -0.001 |
Gig | -0.001 |
Thank | -0.001 |
Tri | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
aid | +0.087 |
ide | +0.087 |
nie | +0.086 |
inn | +0.083 |
ches | +0.083 |
Neg logit contributions | |
disl | -0.079 |
jewels | -0.071 |
Tri | -0.071 |
Gig | -0.069 |
gold | -0.068 |
Token | f |
Token ID | 277 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
inn | +0.018 |
kernel | +0.016 |
icky | +0.016 |
aid | +0.016 |
ches | +0.016 |
Neg logit contributions | |
disl | -0.023 |
Gig | -0.018 |
Sorry | -0.018 |
bows | -0.018 |
endant | -0.018 |
Token | auc |
Token ID | 14272 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
inn | +0.022 |
ches | +0.019 |
icky | +0.019 |
kernel | +0.018 |
nie | +0.018 |
Neg logit contributions | |
disl | -0.050 |
killed | -0.041 |
endant | -0.041 |
Sorry | -0.041 |
Gig | -0.041 |
Token | et |
Token ID | 316 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
inn | +0.027 |
icky | +0.023 |
aid | +0.022 |
kernel | +0.022 |
ches | +0.022 |
Neg logit contributions | |
disl | -0.063 |
killed | -0.052 |
bows | -0.051 |
Thank | -0.051 |
Gig | -0.051 |
Token | up |
Token ID | 510 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
inn | +0.087 |
nie | +0.081 |
ud | +0.079 |
Alex | +0.079 |
aid | +0.079 |
Neg logit contributions | |
disl | -0.094 |
Tri | -0.079 |
ocular | -0.078 |
Gig | -0.076 |
bows | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
inn | +0.069 |
ches | +0.067 |
nie | +0.065 |
icky | +0.064 |
kernel | +0.063 |
Neg logit contributions | |
disl | -0.085 |
jewels | -0.075 |
Tri | -0.073 |
killed | -0.073 |
Gig | -0.072 |
Token | support |
Token ID | 1104 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
inn | +0.012 |
icky | +0.010 |
ches | +0.010 |
nie | +0.010 |
kernel | +0.010 |
Neg logit contributions | |
disl | -0.014 |
killed | -0.011 |
Thank | -0.011 |
Sorry | -0.011 |
Gig | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
inn | +0.016 |
ches | +0.014 |
icky | +0.013 |
nie | +0.013 |
aid | +0.013 |
Neg logit contributions | |
disl | -0.017 |
killed | -0.014 |
jewels | -0.013 |
Tri | -0.013 |
Thank | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
inn | +0.009 |
ches | +0.008 |
icky | +0.008 |
kernel | +0.007 |
nie | +0.007 |
Neg logit contributions | |
disl | -0.013 |
killed | -0.011 |
Thank | -0.010 |
Sorry | -0.010 |
Gig | -0.010 |
Token | sharing |
Token ID | 7373 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
disl | +0.011 |
Gig | +0.009 |
endant | +0.009 |
bows | +0.009 |
statues | +0.009 |
Neg logit contributions | |
inn | -0.010 |
player | -0.009 |
nie | -0.009 |
scrub | -0.009 |
pron | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
disl | +0.032 |
killed | +0.025 |
Thank | +0.025 |
bows | +0.025 |
Sorry | +0.025 |
Neg logit contributions | |
inn | -0.023 |
ches | -0.020 |
icky | -0.019 |
kernel | -0.019 |
nie | -0.019 |
Token | She |
Token ID | 1375 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
disl | +0.019 |
vell | +0.017 |
killed | +0.017 |
jewels | +0.016 |
endant | +0.016 |
Neg logit contributions | |
inn | -0.011 |
aid | -0.009 |
icky | -0.009 |
Alex | -0.009 |
corner | -0.009 |
Token | gave |
Token ID | 2921 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
disl | +0.025 |
Sorry | +0.019 |
Gig | +0.019 |
bows | +0.019 |
Tri | +0.018 |
Neg logit contributions | |
inn | -0.025 |
ches | -0.023 |
nie | -0.022 |
kernel | -0.022 |
aid | -0.022 |
Token | them |
Token ID | 606 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
disl | +0.014 |
killed | +0.012 |
Sorry | +0.011 |
endant | +0.011 |
Thank | +0.011 |
Neg logit contributions | |
inn | -0.006 |
ches | -0.005 |
icky | -0.005 |
kernel | -0.005 |
nie | -0.005 |
Token | each |
Token ID | 1123 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
inn | +0.001 |
ches | +0.001 |
icky | +0.001 |
kernel | +0.001 |
nie | +0.001 |
Neg logit contributions | |
disl | -0.002 |
killed | -0.001 |
Gig | -0.001 |
Sorry | -0.001 |
Thank | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
inn | +0.119 |
icky | +0.106 |
ches | +0.106 |
ide | +0.105 |
aid | +0.104 |
Neg logit contributions | |
disl | -0.083 |
Gig | -0.068 |
Thank | -0.068 |
jewels | -0.065 |
killed | -0.065 |
Token | hug |
Token ID | 16225 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
inn | +0.011 |
ches | +0.010 |
icky | +0.010 |
nie | +0.010 |
kernel | +0.010 |
Neg logit contributions | |
disl | -0.011 |
killed | -0.009 |
endant | -0.009 |
Thank | -0.009 |
Sorry | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
inn | +0.014 |
icky | +0.012 |
ches | +0.012 |
kernel | +0.011 |
nie | +0.011 |
Neg logit contributions | |
disl | -0.018 |
bows | -0.015 |
Thank | -0.015 |
killed | -0.015 |
Gig | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
inn | +0.002 |
kernel | +0.002 |
ches | +0.002 |
aid | +0.002 |
scrub | +0.002 |
Neg logit contributions | |
disl | -0.003 |
endant | -0.002 |
Sorry | -0.002 |
Gig | -0.002 |
Tri | -0.002 |
Token | kiss |
Token ID | 9245 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
inn | +0.004 |
ches | +0.003 |
icky | +0.003 |
kernel | +0.003 |
aid | +0.003 |
Neg logit contributions | |
disl | -0.004 |
killed | -0.003 |
Gig | -0.003 |
Sorry | -0.003 |
endant | -0.003 |
Token | can |
Token ID | 460 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
inn | +0.054 |
ches | +0.051 |
' | +0.047 |
nie | +0.047 |
icky | +0.046 |
Neg logit contributions | |
disl | -0.060 |
Gig | -0.047 |
mm | -0.047 |
endant | -0.045 |
statues | -0.045 |
Token | use |
Token ID | 779 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
inn | +0.018 |
ches | +0.017 |
icky | +0.016 |
kernel | +0.016 |
aid | +0.016 |
Neg logit contributions | |
disl | -0.020 |
killed | -0.015 |
Gig | -0.015 |
endant | -0.015 |
Thank | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
inn | +0.052 |
icky | +0.045 |
nie | +0.045 |
kernel | +0.044 |
ches | +0.044 |
Neg logit contributions | |
disl | -0.059 |
killed | -0.047 |
jewels | -0.047 |
endant | -0.045 |
Tri | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
inn | +0.021 |
ches | +0.018 |
icky | +0.018 |
nie | +0.017 |
kernel | +0.016 |
Neg logit contributions | |
disl | -0.041 |
killed | -0.034 |
Sorry | -0.034 |
Thank | -0.034 |
Gig | -0.033 |
Token | spray |
Token ID | 11662 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
disl | +0.008 |
killed | +0.006 |
Gig | +0.006 |
Sorry | +0.006 |
endant | +0.006 |
Neg logit contributions | |
inn | -0.007 |
ches | -0.006 |
icky | -0.006 |
kernel | -0.006 |
aid | -0.006 |
Token | each |
Token ID | 1123 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
inn | +0.025 |
nie | +0.022 |
icky | +0.022 |
aid | +0.021 |
kernel | +0.021 |
Neg logit contributions | |
disl | -0.029 |
killed | -0.022 |
Gig | -0.022 |
jewels | -0.022 |
Sorry | -0.022 |
Token | other |
Token ID | 584 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
inn | +0.114 |
aid | +0.099 |
pron | +0.097 |
icky | +0.096 |
nie | +0.096 |
Neg logit contributions | |
disl | -0.082 |
killed | -0.065 |
lucky | -0.064 |
Thank | -0.062 |
love | -0.059 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
inn | +0.001 |
ud | +0.001 |
kernel | +0.001 |
icky | +0.001 |
ches | +0.001 |
Neg logit contributions | |
disl | -0.001 |
bows | -0.001 |
jewels | -0.001 |
statues | -0.001 |
killed | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
inn | +0.030 |
ches | +0.027 |
icky | +0.026 |
kernel | +0.026 |
nie | +0.026 |
Neg logit contributions | |
disl | -0.031 |
Gig | -0.024 |
Thank | -0.024 |
killed | -0.024 |
Sorry | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
inn | +0.023 |
nie | +0.021 |
kernel | +0.021 |
ches | +0.020 |
ash | +0.020 |
Neg logit contributions | |
disl | -0.023 |
Gig | -0.018 |
Thank | -0.018 |
killed | -0.018 |
Tri | -0.017 |
Token | The |
Token ID | 464 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
inn | +0.003 |
ches | +0.002 |
icky | +0.002 |
nie | +0.002 |
kernel | +0.002 |
Neg logit contributions | |
disl | -0.003 |
Thank | -0.002 |
killed | -0.002 |
Sorry | -0.002 |
Gig | -0.002 |
Token | my |
Token ID | 1820 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
disl | +0.036 |
Gig | +0.029 |
Thank | +0.029 |
bows | +0.029 |
Tri | +0.028 |
Neg logit contributions | |
inn | -0.032 |
ches | -0.028 |
kernel | -0.028 |
icky | -0.027 |
aid | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
disl | +0.004 |
Gig | +0.003 |
jewels | +0.003 |
statues | +0.003 |
bows | +0.003 |
Neg logit contributions | |
inn | -0.004 |
kernel | -0.004 |
ches | -0.004 |
ud | -0.004 |
icky | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
inn | +0.059 |
ches | +0.057 |
ud | +0.054 |
ler | +0.053 |
kernel | +0.053 |
Neg logit contributions | |
disl | -0.057 |
Gig | -0.049 |
Thank | -0.048 |
Tri | -0.047 |
lucky | -0.047 |
Token | Can |
Token ID | 6090 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
disl | +0.014 |
Thank | +0.012 |
Gig | +0.011 |
Sorry | +0.011 |
killed | +0.011 |
Neg logit contributions | |
inn | -0.016 |
ches | -0.014 |
icky | -0.014 |
kernel | -0.013 |
nie | -0.013 |
Token | I |
Token ID | 314 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
inn | +0.005 |
ches | +0.005 |
icky | +0.005 |
kernel | +0.005 |
nie | +0.005 |
Neg logit contributions | |
disl | -0.003 |
killed | -0.002 |
Sorry | -0.002 |
Thank | -0.002 |
Gig | -0.002 |
Token | let |
Token ID | 1309 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
inn | +0.039 |
' | +0.035 |
ches | +0.034 |
aid | +0.033 |
kernel | +0.032 |
Neg logit contributions | |
disl | -0.048 |
bows | -0.038 |
statues | -0.036 |
killed | -0.036 |
endant | -0.036 |
Token | my |
Token ID | 616 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
inn | +0.116 |
ud | +0.099 |
kernel | +0.099 |
icky | +0.098 |
aid | +0.098 |
Neg logit contributions | |
disl | -0.082 |
Sorry | -0.062 |
Gig | -0.061 |
killed | -0.061 |
Tri | -0.059 |
Token | wallet |
Token ID | 13008 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
disl | +0.023 |
bows | +0.019 |
killed | +0.018 |
Thank | +0.017 |
vell | +0.017 |
Neg logit contributions | |
chair | -0.011 |
aid | -0.011 |
hand | -0.011 |
plate | -0.011 |
' | -0.011 |
Token | outside |
Token ID | 2354 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
disl | +0.038 |
Gig | +0.030 |
Thank | +0.029 |
killed | +0.029 |
endant | +0.029 |
Neg logit contributions | |
inn | -0.021 |
ches | -0.019 |
icky | -0.018 |
kernel | -0.018 |
aid | -0.018 |
Token | ?" |
Token ID | 1701 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
inn | +0.041 |
ches | +0.036 |
icky | +0.035 |
ud | +0.035 |
kernel | +0.034 |
Neg logit contributions | |
disl | -0.030 |
Sorry | -0.024 |
killed | -0.022 |
Thank | -0.022 |
Gig | -0.022 |
Token | Her |
Token ID | 2332 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
inn | +0.024 |
kernel | +0.022 |
ches | +0.022 |
nie | +0.021 |
ud | +0.021 |
Neg logit contributions | |
disl | -0.015 |
Sorry | -0.012 |
Tri | -0.011 |
Thank | -0.011 |
Gig | -0.011 |
Token | much |
Token ID | 881 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
disl | +0.003 |
killed | +0.002 |
Sorry | +0.002 |
endant | +0.002 |
Thank | +0.002 |
Neg logit contributions | |
inn | -0.004 |
icky | -0.004 |
ches | -0.004 |
kernel | -0.003 |
nie | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
disl | +0.026 |
Sorry | +0.021 |
killed | +0.020 |
endant | +0.020 |
Thank | +0.020 |
Neg logit contributions | |
inn | -0.018 |
ches | -0.016 |
icky | -0.016 |
kernel | -0.015 |
aid | -0.015 |
Token | she |
Token ID | 673 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
inn | +0.029 |
icky | +0.026 |
ches | +0.026 |
kernel | +0.026 |
nie | +0.026 |
Neg logit contributions | |
disl | -0.024 |
killed | -0.017 |
endant | -0.017 |
bows | -0.017 |
Sorry | -0.017 |
Token | ate |
Token ID | 15063 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
inn | +0.007 |
icky | +0.006 |
aid | +0.006 |
ches | +0.006 |
kernel | +0.006 |
Neg logit contributions | |
disl | -0.004 |
killed | -0.003 |
Thank | -0.003 |
Gig | -0.003 |
Sorry | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
disl | +0.019 |
Gig | +0.016 |
jewels | +0.016 |
Thank | +0.016 |
statues | +0.016 |
Neg logit contributions | |
inn | -0.017 |
ches | -0.015 |
aid | -0.015 |
nie | -0.015 |
icky | -0.014 |
Token | every |
Token ID | 790 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
inn | +0.008 |
aid | +0.007 |
icky | +0.007 |
ches | +0.007 |
kernel | +0.007 |
Neg logit contributions | |
disl | -0.009 |
bows | -0.007 |
Thank | -0.007 |
Gig | -0.007 |
jewels | -0.007 |
Token | single |
Token ID | 2060 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
inn | +0.111 |
ches | +0.108 |
uart | +0.105 |
icky | +0.101 |
ide | +0.101 |
Neg logit contributions | |
disl | -0.073 |
Thank | -0.070 |
lucky | -0.069 |
Sorry | -0.066 |
Gig | -0.063 |
Token | day |
Token ID | 1110 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
inn | +0.035 |
ches | +0.034 |
icky | +0.032 |
uart | +0.031 |
ide | +0.030 |
Neg logit contributions | |
disl | -0.038 |
Thank | -0.032 |
killed | -0.031 |
jewels | -0.031 |
Thank | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
inn | +0.052 |
ches | +0.047 |
icky | +0.047 |
Alex | +0.046 |
nie | +0.045 |
Neg logit contributions | |
disl | -0.045 |
Gig | -0.039 |
Thank | -0.038 |
bows | -0.037 |
statues | -0.037 |
Token | One |
Token ID | 1881 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
disl | +0.008 |
Gig | +0.007 |
Thank | +0.006 |
bows | +0.006 |
Sorry | +0.006 |
Neg logit contributions | |
inn | -0.008 |
ches | -0.008 |
kernel | -0.008 |
icky | -0.007 |
nie | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
ches | +0.020 |
inn | +0.019 |
pan | +0.018 |
uart | +0.018 |
Alex | +0.018 |
Neg logit contributions | |
disl | -0.015 |
lucky | -0.014 |
Thank | -0.013 |
Gig | -0.013 |
dear | -0.012 |