Token | air |
Token ID | 1633 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
quest | +0.077 |
ement | +0.072 |
site | +0.070 |
ently | +0.069 |
ths | +0.068 |
Neg logit contributions | |
burn | -0.024 |
their | -0.022 |
y | -0.021 |
Woo | -0.021 |
Sara | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
burn | +0.046 |
Woo | +0.042 |
their | +0.040 |
y | +0.040 |
ety | +0.040 |
Neg logit contributions | |
quest | -0.069 |
ement | -0.065 |
site | -0.063 |
ently | -0.062 |
exhibit | -0.059 |
Token | He |
Token ID | 679 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
burn | +0.006 |
y | +0.006 |
their | +0.006 |
Woo | +0.005 |
ety | +0.005 |
Neg logit contributions | |
quest | -0.011 |
ement | -0.010 |
site | -0.010 |
ently | -0.010 |
exhibit | -0.010 |
Token | watched |
Token ID | 7342 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
quest | +0.006 |
ement | +0.006 |
ently | +0.006 |
site | +0.006 |
ths | +0.005 |
Neg logit contributions | |
their | -0.003 |
burn | -0.003 |
y | -0.003 |
Sara | -0.003 |
Woo | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
quest | +0.015 |
ement | +0.014 |
site | +0.013 |
ently | +0.013 |
ths | +0.013 |
Neg logit contributions | |
burn | -0.007 |
their | -0.006 |
y | -0.006 |
Woo | -0.006 |
Sara | -0.005 |
Token | amaz |
Token ID | 40642 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
their | +0.009 |
her | +0.008 |
Sara | +0.007 |
burn | +0.006 |
Woo | +0.006 |
Neg logit contributions | |
quest | -0.026 |
ently | -0.026 |
ement | -0.025 |
site | -0.025 |
ths | -0.025 |
Token | ement |
Token ID | 972 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
quest | +0.064 |
exhibit | +0.033 |
trek | +0.029 |
site | +0.028 |
boulder | +0.028 |
Neg logit contributions | |
their | -0.261 |
y | -0.259 |
her | -0.252 |
burn | -0.248 |
ful | -0.244 |
Token | as |
Token ID | 355 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
quest | +0.014 |
ement | +0.013 |
site | +0.013 |
ently | +0.013 |
ths | +0.013 |
Neg logit contributions | |
burn | -0.009 |
their | -0.008 |
y | -0.008 |
Woo | -0.008 |
Sara | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
burn | +0.016 |
their | +0.016 |
y | +0.015 |
Woo | +0.015 |
Sara | +0.014 |
Neg logit contributions | |
quest | -0.027 |
ement | -0.025 |
site | -0.024 |
ently | -0.024 |
ths | -0.023 |
Token | z |
Token ID | 1976 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
quest | +0.021 |
ement | +0.020 |
ently | +0.019 |
site | +0.019 |
ths | +0.019 |
Neg logit contributions | |
burn | -0.014 |
their | -0.013 |
y | -0.013 |
Sara | -0.013 |
Woo | -0.013 |
Token | ig |
Token ID | 328 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
quest | +0.072 |
site | +0.059 |
ement | +0.055 |
lair | +0.055 |
exhibit | +0.054 |
Neg logit contributions | |
burn | -0.110 |
ot | -0.104 |
y | -0.103 |
their | -0.097 |
Sara | -0.096 |
Token | could |
Token ID | 714 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
quest | +0.050 |
ement | +0.046 |
site | +0.045 |
ently | +0.044 |
ths | +0.044 |
Neg logit contributions | |
y | -0.025 |
burn | -0.025 |
their | -0.025 |
her | -0.022 |
ot | -0.022 |
Token | see |
Token ID | 766 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
their | +0.003 |
burn | +0.003 |
her | +0.003 |
ot | +0.003 |
y | +0.003 |
Neg logit contributions | |
quest | -0.007 |
ement | -0.007 |
site | -0.006 |
ths | -0.006 |
ently | -0.006 |
Token | lots |
Token ID | 6041 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
quest | +0.061 |
ement | +0.055 |
site | +0.054 |
renches | +0.053 |
ths | +0.053 |
Neg logit contributions | |
their | -0.024 |
y | -0.023 |
burn | -0.022 |
her | -0.022 |
Sara | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
y | +0.002 |
their | +0.002 |
her | +0.002 |
burn | +0.002 |
like | +0.002 |
Neg logit contributions | |
quest | -0.003 |
site | -0.003 |
ths | -0.003 |
ement | -0.003 |
renches | -0.003 |
Token | av |
Token ID | 1196 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
quest | +0.028 |
site | +0.025 |
exhibit | +0.025 |
ths | +0.025 |
ement | +0.025 |
Neg logit contributions | |
their | -0.015 |
her | -0.015 |
y | -0.015 |
like | -0.014 |
your | -0.013 |
Token | oc |
Token ID | 420 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
quest | +0.020 |
ement | +0.019 |
site | +0.018 |
ently | +0.017 |
ths | +0.016 |
Neg logit contributions | |
y | -0.033 |
burn | -0.032 |
ety | -0.030 |
their | -0.030 |
Woo | -0.029 |
Token | ados |
Token ID | 22484 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
quest | +0.174 |
mission | +0.147 |
site | +0.140 |
passage | +0.138 |
trek | +0.133 |
Neg logit contributions | |
y | -0.133 |
burn | -0.133 |
ety | -0.128 |
C | -0.125 |
her | -0.124 |
Token | that |
Token ID | 326 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
quest | +0.018 |
ement | +0.017 |
site | +0.017 |
renches | +0.017 |
ently | +0.016 |
Neg logit contributions | |
y | -0.008 |
burn | -0.008 |
their | -0.008 |
her | -0.007 |
like | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
burn | +0.017 |
Woo | +0.015 |
y | +0.015 |
their | +0.014 |
ety | +0.014 |
Neg logit contributions | |
quest | -0.026 |
ement | -0.024 |
site | -0.023 |
ths | -0.022 |
ently | -0.022 |
Token | supplier |
Token ID | 22693 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
their | +0.001 |
her | +0.001 |
burn | +0.001 |
Sara | +0.001 |
y | +0.001 |
Neg logit contributions | |
quest | -0.001 |
ement | -0.001 |
ently | -0.001 |
site | -0.001 |
exhibit | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
y | +0.011 |
burn | +0.010 |
their | +0.010 |
her | +0.009 |
ot | +0.009 |
Neg logit contributions | |
quest | -0.023 |
ement | -0.021 |
site | -0.021 |
renches | -0.021 |
ths | -0.021 |
Token | couldn |
Token ID | 3521 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
burn | +0.011 |
their | +0.010 |
y | +0.010 |
Woo | +0.010 |
Sara | +0.009 |
Neg logit contributions | |
quest | -0.018 |
ement | -0.017 |
site | -0.016 |
ently | -0.016 |
ths | -0.016 |
Token | 't |
Token ID | 470 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
quest | +0.030 |
ement | +0.028 |
site | +0.027 |
ently | +0.027 |
ths | +0.026 |
Neg logit contributions | |
burn | -0.024 |
y | -0.022 |
their | -0.021 |
groom | -0.021 |
Woo | -0.021 |
Token | find |
Token ID | 1064 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
their | +0.009 |
her | +0.009 |
burn | +0.009 |
Sara | +0.009 |
like | +0.009 |
Neg logit contributions | |
ement | -0.014 |
quest | -0.013 |
ths | -0.013 |
site | -0.012 |
ently | -0.012 |
Token | any |
Token ID | 597 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
quest | +0.035 |
ement | +0.033 |
site | +0.033 |
ently | +0.032 |
ths | +0.032 |
Neg logit contributions | |
their | -0.010 |
burn | -0.009 |
her | -0.009 |
Sara | -0.009 |
Woo | -0.008 |
Token | av |
Token ID | 1196 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
quest | +0.038 |
ths | +0.038 |
renches | +0.037 |
ently | +0.037 |
ement | +0.036 |
Neg logit contributions | |
like | -0.020 |
their | -0.020 |
y | -0.020 |
her | -0.020 |
Sara | -0.019 |
Token | oc |
Token ID | 420 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
quest | +0.016 |
ement | +0.014 |
site | +0.014 |
ently | +0.013 |
ths | +0.013 |
Neg logit contributions | |
y | -0.025 |
burn | -0.024 |
ety | -0.023 |
their | -0.022 |
Woo | -0.022 |
Token | ados |
Token ID | 22484 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
quest | +0.159 |
passage | +0.129 |
mission | +0.129 |
trek | +0.127 |
site | +0.127 |
Neg logit contributions | |
burn | -0.148 |
y | -0.142 |
ety | -0.133 |
C | -0.131 |
your | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
quest | +0.038 |
ement | +0.036 |
site | +0.034 |
ths | +0.034 |
renches | +0.034 |
Neg logit contributions | |
y | -0.016 |
burn | -0.016 |
their | -0.015 |
her | -0.014 |
Woo | -0.014 |
Token | Finally |
Token ID | 9461 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
quest | +0.005 |
ement | +0.005 |
site | +0.005 |
ently | +0.005 |
ths | +0.005 |
Neg logit contributions | |
burn | -0.003 |
their | -0.003 |
Woo | -0.003 |
y | -0.003 |
Sara | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
quest | +0.038 |
ement | +0.036 |
site | +0.035 |
lair | +0.035 |
ently | +0.034 |
Neg logit contributions | |
their | -0.019 |
her | -0.018 |
Sara | -0.017 |
burn | -0.017 |
Woo | -0.016 |
Token | she |
Token ID | 673 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
quest | +0.009 |
ths | +0.008 |
ement | +0.008 |
site | +0.008 |
exhibit | +0.008 |
Neg logit contributions | |
burn | -0.005 |
y | -0.005 |
ot | -0.005 |
ety | -0.004 |
Woo | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
quest | +0.016 |
ement | +0.015 |
site | +0.015 |
renches | +0.015 |
ently | +0.014 |
Neg logit contributions | |
their | -0.008 |
y | -0.008 |
burn | -0.007 |
her | -0.007 |
ful | -0.007 |
Token | filled |
Token ID | 5901 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
quest | +0.003 |
ement | +0.003 |
site | +0.003 |
ths | +0.003 |
ently | +0.003 |
Neg logit contributions | |
burn | -0.002 |
Woo | -0.002 |
y | -0.002 |
ety | -0.001 |
ot | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
burn | +0.053 |
Woo | +0.045 |
ety | +0.045 |
y | +0.043 |
groom | +0.042 |
Neg logit contributions | |
quest | -0.075 |
ement | -0.070 |
site | -0.069 |
ently | -0.066 |
exhibit | -0.066 |
Token | wonder |
Token ID | 4240 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
quest | +0.004 |
ement | +0.004 |
site | +0.004 |
ently | +0.004 |
ths | +0.004 |
Neg logit contributions | |
their | -0.003 |
burn | -0.003 |
y | -0.002 |
her | -0.002 |
Woo | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
quest | +0.049 |
ement | +0.045 |
site | +0.044 |
ths | +0.043 |
ently | +0.042 |
Neg logit contributions | |
burn | -0.027 |
their | -0.027 |
y | -0.026 |
Woo | -0.024 |
her | -0.024 |
Token | amaz |
Token ID | 40642 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
quest | +0.022 |
ement | +0.021 |
site | +0.020 |
ently | +0.020 |
ths | +0.019 |
Neg logit contributions | |
burn | -0.015 |
y | -0.014 |
their | -0.014 |
Woo | -0.014 |
ety | -0.013 |
Token | ement |
Token ID | 972 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
quest | +0.063 |
exhibit | +0.040 |
boulder | +0.033 |
trek | +0.031 |
lair | +0.029 |
Neg logit contributions | |
their | -0.249 |
y | -0.242 |
her | -0.238 |
ful | -0.230 |
burn | -0.229 |
Token | . |
Token ID | 13 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
quest | +0.033 |
ement | +0.032 |
ently | +0.030 |
site | +0.030 |
ths | +0.029 |
Neg logit contributions | |
burn | -0.026 |
Woo | -0.024 |
their | -0.022 |
y | -0.022 |
ety | -0.022 |
Token | They |
Token ID | 1119 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
quest | +0.013 |
ement | +0.012 |
ently | +0.011 |
ths | +0.011 |
site | +0.011 |
Neg logit contributions | |
their | -0.006 |
Sara | -0.005 |
C | -0.005 |
Woo | -0.005 |
y | -0.005 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
burn | +0.005 |
their | +0.005 |
y | +0.005 |
Woo | +0.005 |
her | +0.004 |
Neg logit contributions | |
quest | -0.009 |
ement | -0.009 |
site | -0.008 |
ently | -0.008 |
ths | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
burn | +0.002 |
y | +0.002 |
ety | +0.002 |
Woo | +0.002 |
ot | +0.002 |
Neg logit contributions | |
quest | -0.006 |
ement | -0.005 |
site | -0.005 |
ently | -0.005 |
exhibit | -0.005 |
Token | I |
Token ID | 40 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
burn | +0.016 |
their | +0.014 |
y | +0.014 |
ot | +0.013 |
Woo | +0.013 |
Neg logit contributions | |
quest | -0.024 |
ths | -0.023 |
ement | -0.023 |
site | -0.022 |
exhibit | -0.021 |
Token | will |
Token ID | 481 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
quest | +0.002 |
ement | +0.002 |
site | +0.002 |
exhibit | +0.002 |
ently | +0.002 |
Neg logit contributions | |
burn | -0.001 |
their | -0.001 |
Woo | -0.001 |
y | -0.001 |
ot | -0.001 |
Token | buy |
Token ID | 2822 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
burn | +0.035 |
y | +0.031 |
their | +0.031 |
Woo | +0.031 |
ety | +0.029 |
Neg logit contributions | |
quest | -0.052 |
ement | -0.049 |
site | -0.047 |
ently | -0.046 |
ths | -0.045 |
Token | more |
Token ID | 517 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
burn | +0.004 |
y | +0.003 |
their | +0.003 |
Woo | +0.003 |
ot | +0.003 |
Neg logit contributions | |
quest | -0.008 |
ement | -0.007 |
site | -0.007 |
ently | -0.007 |
ths | -0.007 |
Token | av |
Token ID | 1196 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
their | +0.005 |
Sara | +0.005 |
burn | +0.005 |
her | +0.005 |
your | +0.005 |
Neg logit contributions | |
quest | -0.007 |
ement | -0.007 |
ths | -0.006 |
ently | -0.006 |
site | -0.006 |
Token | oc |
Token ID | 420 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
quest | +0.013 |
ement | +0.011 |
site | +0.011 |
ently | +0.010 |
ths | +0.010 |
Neg logit contributions | |
burn | -0.025 |
y | -0.024 |
their | -0.023 |
Woo | -0.023 |
ety | -0.023 |
Token | ados |
Token ID | 22484 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
quest | +0.147 |
mission | +0.116 |
site | +0.116 |
trek | +0.113 |
passage | +0.113 |
Neg logit contributions | |
burn | -0.153 |
y | -0.145 |
C | -0.140 |
your | -0.138 |
ful | -0.138 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
quest | +0.025 |
ement | +0.024 |
site | +0.023 |
ently | +0.023 |
ths | +0.022 |
Neg logit contributions | |
burn | -0.015 |
their | -0.013 |
y | -0.013 |
Woo | -0.013 |
ot | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
burn | +0.042 |
Woo | +0.037 |
their | +0.037 |
y | +0.036 |
ety | +0.034 |
Neg logit contributions | |
quest | -0.069 |
ement | -0.064 |
site | -0.062 |
ently | -0.061 |
exhibit | -0.060 |
Token | You |
Token ID | 921 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
quest | +0.015 |
ement | +0.014 |
site | +0.014 |
exhibit | +0.013 |
ently | +0.013 |
Neg logit contributions | |
burn | -0.013 |
y | -0.012 |
their | -0.012 |
Woo | -0.011 |
ot | -0.011 |
Token | can |
Token ID | 460 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
quest | +0.004 |
ement | +0.004 |
ently | +0.004 |
site | +0.004 |
ths | +0.004 |
Neg logit contributions | |
burn | -0.001 |
y | -0.001 |
their | -0.001 |
Woo | -0.001 |
C | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
quest | +0.004 |
ement | +0.004 |
site | +0.004 |
exhibit | +0.004 |
ently | +0.004 |
Neg logit contributions | |
burn | -0.002 |
their | -0.001 |
y | -0.001 |
groom | -0.001 |
Woo | -0.001 |
Token | loved |
Token ID | 6151 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
burn | +0.009 |
Woo | +0.007 |
y | +0.007 |
their | +0.007 |
Sara | +0.007 |
Neg logit contributions | |
quest | -0.013 |
ement | -0.011 |
site | -0.011 |
ths | -0.011 |
ently | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
quest | +0.011 |
ths | +0.010 |
site | +0.010 |
exhibit | +0.010 |
ement | +0.010 |
Neg logit contributions | |
burn | -0.006 |
y | -0.005 |
Woo | -0.005 |
a | -0.005 |
ot | -0.005 |
Token | eat |
Token ID | 4483 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
quest | +0.031 |
ement | +0.027 |
site | +0.026 |
exhibit | +0.026 |
ently | +0.026 |
Neg logit contributions | |
burn | -0.019 |
y | -0.018 |
Woo | -0.017 |
their | -0.017 |
ety | -0.016 |
Token | av |
Token ID | 1196 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
burn | +0.007 |
y | +0.006 |
ety | +0.006 |
ot | +0.006 |
Woo | +0.006 |
Neg logit contributions | |
quest | -0.006 |
ement | -0.005 |
site | -0.005 |
ently | -0.005 |
exhibit | -0.005 |
Token | oc |
Token ID | 420 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
quest | +0.005 |
ement | +0.005 |
site | +0.004 |
ently | +0.004 |
ths | +0.004 |
Neg logit contributions | |
burn | -0.010 |
y | -0.009 |
their | -0.009 |
Woo | -0.009 |
ety | -0.009 |
Token | ados |
Token ID | 22484 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
quest | +0.157 |
mission | +0.130 |
passage | +0.127 |
site | +0.127 |
trek | +0.121 |
Neg logit contributions | |
burn | -0.139 |
y | -0.131 |
her | -0.129 |
your | -0.128 |
ety | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
quest | +0.024 |
ement | +0.022 |
site | +0.021 |
ently | +0.021 |
ths | +0.021 |
Neg logit contributions | |
burn | -0.013 |
y | -0.012 |
their | -0.012 |
Woo | -0.011 |
her | -0.011 |
Token | One |
Token ID | 1881 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
quest | +0.009 |
ement | +0.008 |
site | +0.008 |
ently | +0.008 |
ths | +0.008 |
Neg logit contributions | |
burn | -0.010 |
their | -0.010 |
Woo | -0.010 |
y | -0.009 |
Sara | -0.009 |
Token | day |
Token ID | 1110 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
quest | +0.033 |
ement | +0.029 |
exhibit | +0.028 |
site | +0.028 |
ently | +0.027 |
Neg logit contributions | |
burn | -0.031 |
Woo | -0.030 |
groom | -0.028 |
their | -0.027 |
La | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
burn | +0.002 |
y | +0.002 |
groom | +0.002 |
ety | +0.002 |
ksh | +0.002 |
Neg logit contributions | |
quest | -0.002 |
ement | -0.001 |
ently | -0.001 |
exhibit | -0.001 |
site | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
quest | +0.016 |
ement | +0.015 |
site | +0.014 |
ths | +0.014 |
ently | +0.014 |
Neg logit contributions | |
burn | -0.008 |
their | -0.008 |
Woo | -0.007 |
y | -0.007 |
ot | -0.007 |
Token | T |
Token ID | 51 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
quest | +0.011 |
ement | +0.011 |
site | +0.010 |
ths | +0.010 |
ently | +0.010 |
Neg logit contributions | |
burn | -0.004 |
their | -0.003 |
y | -0.003 |
Woo | -0.003 |
Sara | -0.003 |
Token | ina |
Token ID | 1437 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
burn | +0.007 |
their | +0.007 |
Woo | +0.006 |
Sara | +0.006 |
groom | +0.005 |
Neg logit contributions | |
quest | -0.023 |
ement | -0.023 |
ently | -0.023 |
site | -0.022 |
ths | -0.021 |
Token | waited |
Token ID | 13488 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
quest | +0.045 |
ement | +0.042 |
site | +0.041 |
renches | +0.041 |
lair | +0.040 |
Neg logit contributions | |
y | -0.019 |
their | -0.018 |
burn | -0.017 |
her | -0.017 |
ot | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
their | +0.003 |
her | +0.003 |
y | +0.003 |
burn | +0.003 |
ot | +0.002 |
Neg logit contributions | |
quest | -0.004 |
ement | -0.004 |
exhibit | -0.004 |
site | -0.003 |
ths | -0.003 |
Token | amaz |
Token ID | 40642 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
their | +0.006 |
her | +0.006 |
burn | +0.005 |
Woo | +0.005 |
Sara | +0.005 |
Neg logit contributions | |
quest | -0.012 |
site | -0.012 |
ement | -0.012 |
ently | -0.012 |
ths | -0.012 |
Token | ement |
Token ID | 972 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
quest | +0.059 |
exhibit | +0.037 |
lair | +0.028 |
site | +0.027 |
trek | +0.026 |
Neg logit contributions | |
their | -0.245 |
her | -0.240 |
y | -0.238 |
burn | -0.233 |
ful | -0.228 |
Token | as |
Token ID | 355 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
quest | +0.035 |
ement | +0.033 |
site | +0.031 |
ently | +0.031 |
ths | +0.031 |
Neg logit contributions | |
burn | -0.028 |
Woo | -0.026 |
their | -0.025 |
y | -0.025 |
C | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
burn | +0.012 |
y | +0.010 |
ety | +0.010 |
Woo | +0.010 |
their | +0.009 |
Neg logit contributions | |
quest | -0.023 |
ement | -0.022 |
ently | -0.021 |
site | -0.021 |
ths | -0.021 |
Token | old |
Token ID | 1468 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
quest | +0.030 |
ement | +0.028 |
ently | +0.027 |
site | +0.026 |
ths | +0.026 |
Neg logit contributions | |
burn | -0.023 |
their | -0.022 |
y | -0.021 |
Sara | -0.020 |
Woo | -0.020 |
Token | man |
Token ID | 582 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
quest | +0.019 |
ement | +0.017 |
site | +0.017 |
ently | +0.016 |
ths | +0.016 |
Neg logit contributions | |
burn | -0.015 |
Woo | -0.014 |
y | -0.014 |
their | -0.014 |
ety | -0.013 |
Token | " |
Token ID | 366 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
burn | +0.002 |
y | +0.002 |
ety | +0.002 |
Woo | +0.002 |
their | +0.002 |
Neg logit contributions | |
quest | -0.003 |
ement | -0.003 |
site | -0.003 |
ently | -0.003 |
ths | -0.003 |
Token | That |
Token ID | 2504 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
burn | +0.006 |
their | +0.005 |
y | +0.005 |
Woo | +0.005 |
ot | +0.005 |
Neg logit contributions | |
quest | -0.009 |
ths | -0.009 |
ement | -0.009 |
ently | -0.008 |
site | -0.008 |
Token | 's |
Token ID | 338 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
quest | +0.015 |
site | +0.013 |
ement | +0.013 |
exhibit | +0.013 |
mission | +0.013 |
Neg logit contributions | |
burn | -0.011 |
Woo | -0.011 |
ety | -0.011 |
Sara | -0.010 |
S | -0.010 |
Token | an |
Token ID | 281 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
burn | +0.001 |
y | +0.001 |
groom | +0.001 |
aa | +0.001 |
ana | +0.001 |
Neg logit contributions | |
quest | -0.001 |
ths | -0.001 |
ement | -0.001 |
repairs | -0.001 |
site | -0.001 |
Token | ash |
Token ID | 12530 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
quest | +0.065 |
ently | +0.060 |
ement | +0.060 |
site | +0.059 |
ths | +0.059 |
Neg logit contributions | |
burn | -0.043 |
like | -0.043 |
their | -0.043 |
y | -0.042 |
C | -0.041 |
Token | tr |
Token ID | 2213 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
quest | +0.069 |
ement | +0.065 |
site | +0.063 |
ently | +0.062 |
ths | +0.062 |
Neg logit contributions | |
burn | -0.027 |
their | -0.024 |
y | -0.024 |
Woo | -0.023 |
Sara | -0.021 |
Token | ay |
Token ID | 323 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
quest | +0.166 |
ement | +0.144 |
site | +0.144 |
exhibit | +0.138 |
ently | +0.138 |
Neg logit contributions | |
burn | -0.134 |
y | -0.123 |
their | -0.121 |
Woo | -0.116 |
ot | -0.115 |
Token | , |
Token ID | 11 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
quest | +0.091 |
ement | +0.086 |
site | +0.082 |
ently | +0.082 |
ths | +0.080 |
Neg logit contributions | |
burn | -0.068 |
Woo | -0.063 |
their | -0.062 |
y | -0.060 |
ety | -0.059 |
Token | sweet |
Token ID | 6029 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
burn | +0.004 |
y | +0.003 |
ety | +0.003 |
Woo | +0.003 |
their | +0.003 |
Neg logit contributions | |
quest | -0.007 |
ement | -0.006 |
site | -0.006 |
ths | -0.006 |
ently | -0.006 |
Token | ie |
Token ID | 494 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
burn | +0.025 |
Woo | +0.024 |
their | +0.024 |
ety | +0.022 |
y | +0.022 |
Neg logit contributions | |
quest | -0.025 |
ement | -0.023 |
site | -0.022 |
ently | -0.021 |
exhibit | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
quest | +0.003 |
ement | +0.003 |
site | +0.003 |
ently | +0.003 |
exhibit | +0.003 |
Neg logit contributions | |
burn | -0.003 |
Woo | -0.003 |
their | -0.003 |
ety | -0.003 |
groom | -0.003 |
Token | he |
Token ID | 339 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
quest | +0.033 |
ement | +0.031 |
site | +0.030 |
ently | +0.029 |
ths | +0.029 |
Neg logit contributions | |
burn | -0.031 |
y | -0.028 |
Woo | -0.028 |
their | -0.027 |
ety | -0.027 |
Token | did |
Token ID | 750 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
quest | +0.052 |
ement | +0.048 |
site | +0.047 |
ently | +0.046 |
ths | +0.045 |
Neg logit contributions | |
burn | -0.024 |
y | -0.023 |
their | -0.023 |
Woo | -0.022 |
ety | -0.021 |
Token | not |
Token ID | 407 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
quest | +0.002 |
ement | +0.002 |
site | +0.002 |
ently | +0.002 |
ths | +0.002 |
Neg logit contributions | |
burn | -0.001 |
y | -0.001 |
Woo | -0.001 |
ety | -0.001 |
groom | -0.001 |
Token | have |
Token ID | 423 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
burn | +0.016 |
Woo | +0.015 |
y | +0.014 |
their | +0.014 |
groom | +0.013 |
Neg logit contributions | |
quest | -0.024 |
repairs | -0.020 |
site | -0.020 |
mission | -0.020 |
exhibit | -0.020 |
Token | any |
Token ID | 597 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
quest | +0.009 |
ement | +0.008 |
site | +0.008 |
ently | +0.008 |
ths | +0.007 |
Neg logit contributions | |
burn | -0.005 |
their | -0.005 |
Woo | -0.005 |
y | -0.005 |
her | -0.005 |
Token | er |
Token ID | 1931 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
quest | +0.045 |
site | +0.043 |
ths | +0.042 |
ement | +0.041 |
ently | +0.040 |
Neg logit contributions | |
her | -0.027 |
like | -0.024 |
your | -0.024 |
their | -0.024 |
Sara | -0.023 |
Token | asers |
Token ID | 19865 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
quest | +0.149 |
site | +0.133 |
exhibit | +0.120 |
ement | +0.119 |
lair | +0.119 |
Neg logit contributions | |
burn | -0.153 |
y | -0.149 |
her | -0.143 |
ot | -0.142 |
ety | -0.141 |
Token | to |
Token ID | 284 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
quest | +0.074 |
ement | +0.069 |
site | +0.067 |
ently | +0.066 |
ths | +0.066 |
Neg logit contributions | |
burn | -0.033 |
their | -0.032 |
y | -0.032 |
Woo | -0.029 |
her | -0.029 |
Token | sell |
Token ID | 3677 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
quest | +0.030 |
ement | +0.028 |
site | +0.027 |
ently | +0.027 |
ths | +0.026 |
Neg logit contributions | |
burn | -0.020 |
y | -0.018 |
their | -0.018 |
Woo | -0.018 |
ety | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
burn | +0.021 |
Woo | +0.019 |
y | +0.018 |
their | +0.018 |
ot | +0.017 |
Neg logit contributions | |
quest | -0.036 |
ement | -0.033 |
site | -0.032 |
ently | -0.032 |
ths | -0.031 |
Token | The |
Token ID | 383 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
their | +0.002 |
burn | +0.002 |
Sara | +0.002 |
Woo | +0.002 |
C | +0.002 |
Neg logit contributions | |
quest | -0.003 |
ement | -0.003 |
ths | -0.003 |
ently | -0.003 |
site | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
quest | +0.004 |
ement | +0.004 |
site | +0.004 |
ths | +0.004 |
ently | +0.004 |
Neg logit contributions | |
burn | -0.003 |
y | -0.003 |
ety | -0.002 |
ot | -0.002 |
Woo | -0.002 |
Token | eyes |
Token ID | 2951 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
burn | +0.017 |
their | +0.017 |
y | +0.016 |
ot | +0.016 |
c | +0.015 |
Neg logit contributions | |
quest | -0.034 |
ently | -0.032 |
site | -0.032 |
ement | -0.032 |
ths | -0.030 |
Token | grew |
Token ID | 6348 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
burn | +0.024 |
their | +0.022 |
Woo | +0.022 |
y | +0.022 |
Sara | +0.020 |
Neg logit contributions | |
quest | -0.037 |
ement | -0.034 |
site | -0.033 |
ently | -0.032 |
ths | -0.032 |
Token | wide |
Token ID | 3094 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
burn | +0.004 |
Woo | +0.004 |
ana | +0.004 |
groom | +0.004 |
La | +0.004 |
Neg logit contributions | |
quest | -0.005 |
ement | -0.005 |
ently | -0.005 |
site | -0.004 |
ths | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
quest | +0.071 |
ement | +0.067 |
site | +0.063 |
ently | +0.062 |
exhibit | +0.061 |
Neg logit contributions | |
burn | -0.048 |
Woo | -0.044 |
their | -0.043 |
y | -0.042 |
ot | -0.041 |
Token | amaz |
Token ID | 40642 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
burn | +0.001 |
y | +0.001 |
Woo | +0.001 |
their | +0.001 |
ety | +0.001 |
Neg logit contributions | |
quest | -0.002 |
ement | -0.001 |
site | -0.001 |
ently | -0.001 |
ths | -0.001 |
Token | ement |
Token ID | 972 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
quest | +0.056 |
exhibit | +0.032 |
site | +0.027 |
trek | +0.025 |
mission | +0.022 |
Neg logit contributions | |
y | -0.241 |
their | -0.234 |
burn | -0.232 |
her | -0.231 |
ful | -0.224 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
quest | +0.017 |
ement | +0.016 |
ently | +0.015 |
site | +0.015 |
ths | +0.015 |
Neg logit contributions | |
burn | -0.012 |
Woo | -0.011 |
their | -0.010 |
y | -0.010 |
ety | -0.010 |
Token | She |
Token ID | 1375 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
burn | +0.002 |
their | +0.002 |
y | +0.002 |
Woo | +0.002 |
ot | +0.002 |
Neg logit contributions | |
quest | -0.006 |
ement | -0.005 |
site | -0.005 |
ently | -0.005 |
ths | -0.005 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
quest | +0.002 |
ement | +0.002 |
site | +0.002 |
ently | +0.002 |
exhibit | +0.002 |
Neg logit contributions | |
burn | -0.001 |
their | -0.001 |
y | -0.001 |
Woo | -0.001 |
ot | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
quest | +0.050 |
ement | +0.047 |
site | +0.046 |
ently | +0.045 |
ths | +0.044 |
Neg logit contributions | |
burn | -0.019 |
y | -0.016 |
their | -0.016 |
Woo | -0.016 |
ot | -0.014 |
Token | She |
Token ID | 1375 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
quest | +0.002 |
ement | +0.002 |
site | +0.002 |
exhibit | +0.002 |
ently | +0.002 |
Neg logit contributions | |
burn | -0.001 |
groom | -0.001 |
their | -0.001 |
y | -0.001 |
a | -0.001 |
Token | loved |
Token ID | 6151 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
burn | +0.006 |
Woo | +0.005 |
their | +0.005 |
y | +0.005 |
free | +0.004 |
Neg logit contributions | |
quest | -0.007 |
ement | -0.006 |
site | -0.006 |
ths | -0.006 |
exhibit | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
quest | +0.014 |
ths | +0.012 |
site | +0.012 |
exhibit | +0.012 |
repairs | +0.012 |
Neg logit contributions | |
burn | -0.008 |
y | -0.007 |
Woo | -0.006 |
ot | -0.006 |
a | -0.006 |
Token | eat |
Token ID | 4483 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
quest | +0.032 |
ement | +0.028 |
site | +0.028 |
exhibit | +0.027 |
ently | +0.027 |
Neg logit contributions | |
burn | -0.021 |
y | -0.019 |
Woo | -0.019 |
their | -0.018 |
ety | -0.018 |
Token | av |
Token ID | 1196 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
burn | +0.004 |
y | +0.004 |
ety | +0.004 |
ot | +0.004 |
Woo | +0.004 |
Neg logit contributions | |
quest | -0.004 |
ement | -0.004 |
site | -0.003 |
ently | -0.003 |
exhibit | -0.003 |
Token | oc |
Token ID | 420 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
quest | +0.004 |
ement | +0.003 |
site | +0.003 |
ently | +0.003 |
ths | +0.003 |
Neg logit contributions | |
burn | -0.007 |
y | -0.007 |
their | -0.007 |
Woo | -0.007 |
ety | -0.006 |
Token | ados |
Token ID | 22484 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
quest | +0.155 |
mission | +0.129 |
site | +0.126 |
passage | +0.125 |
trek | +0.120 |
Neg logit contributions | |
burn | -0.134 |
y | -0.126 |
her | -0.126 |
your | -0.124 |
ety | -0.120 |
Token | because |
Token ID | 780 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
quest | +0.024 |
ement | +0.022 |
site | +0.022 |
ently | +0.021 |
ths | +0.021 |
Neg logit contributions | |
burn | -0.013 |
their | -0.013 |
y | -0.013 |
Woo | -0.012 |
her | -0.011 |
Token | they |
Token ID | 484 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
quest | +0.058 |
ement | +0.055 |
site | +0.054 |
ths | +0.054 |
ently | +0.052 |
Neg logit contributions | |
burn | -0.038 |
y | -0.032 |
Woo | -0.031 |
ot | -0.031 |
La | -0.031 |
Token | were |
Token ID | 547 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
burn | +0.003 |
Woo | +0.002 |
their | +0.002 |
y | +0.002 |
ot | +0.002 |
Neg logit contributions | |
quest | -0.004 |
ement | -0.004 |
site | -0.004 |
ths | -0.004 |
ently | -0.004 |
Token | y |
Token ID | 331 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
quest | +0.041 |
ement | +0.037 |
site | +0.036 |
ths | +0.036 |
ently | +0.035 |
Neg logit contributions | |
burn | -0.028 |
Woo | -0.024 |
y | -0.024 |
ot | -0.023 |
La | -0.022 |
Token | " |
Token ID | 1 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
quest | +0.020 |
site | +0.018 |
ement | +0.017 |
ently | +0.017 |
ths | +0.017 |
Neg logit contributions | |
burn | -0.016 |
groom | -0.013 |
their | -0.013 |
Woo | -0.013 |
y | -0.013 |
Token | Can |
Token ID | 6090 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
burn | +0.030 |
their | +0.027 |
ful | +0.026 |
y | +0.026 |
ot | +0.025 |
Neg logit contributions | |
quest | -0.046 |
ement | -0.044 |
ths | -0.043 |
site | -0.042 |
repairs | -0.040 |
Token | I |
Token ID | 314 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
quest | +0.037 |
ement | +0.033 |
ths | +0.033 |
site | +0.033 |
ently | +0.032 |
Neg logit contributions | |
burn | -0.027 |
y | -0.025 |
Woo | -0.022 |
their | -0.022 |
groom | -0.022 |
Token | use |
Token ID | 779 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
quest | +0.013 |
ement | +0.012 |
site | +0.011 |
ently | +0.011 |
ths | +0.011 |
Neg logit contributions | |
burn | -0.009 |
their | -0.008 |
y | -0.008 |
Woo | -0.008 |
Sara | -0.007 |
Token | your |
Token ID | 534 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
quest | +0.002 |
ement | +0.002 |
site | +0.002 |
ently | +0.002 |
ths | +0.002 |
Neg logit contributions | |
burn | -0.001 |
y | -0.001 |
their | -0.001 |
Woo | -0.001 |
ety | -0.001 |
Token | er |
Token ID | 1931 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
quest | +0.027 |
ement | +0.026 |
site | +0.026 |
ths | +0.025 |
ently | +0.024 |
Neg logit contributions | |
her | -0.016 |
burn | -0.016 |
their | -0.016 |
ot | -0.016 |
C | -0.015 |
Token | aser |
Token ID | 6005 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
quest | +0.154 |
site | +0.139 |
ement | +0.128 |
exhibit | +0.126 |
trek | +0.123 |
Neg logit contributions | |
burn | -0.144 |
y | -0.139 |
ot | -0.135 |
ety | -0.129 |
a | -0.129 |
Token | , |
Token ID | 11 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
quest | +0.078 |
ement | +0.073 |
site | +0.070 |
ently | +0.069 |
ths | +0.068 |
Neg logit contributions | |
burn | -0.043 |
y | -0.040 |
their | -0.040 |
Woo | -0.038 |
her | -0.037 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
quest | +0.014 |
ement | +0.013 |
site | +0.013 |
ths | +0.012 |
repairs | +0.012 |
Neg logit contributions | |
burn | -0.007 |
y | -0.006 |
free | -0.006 |
ety | -0.005 |
Woo | -0.005 |
Token | ?" |
Token ID | 1701 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
burn | +0.012 |
Woo | +0.011 |
their | +0.011 |
y | +0.010 |
C | +0.010 |
Neg logit contributions | |
quest | -0.016 |
ement | -0.014 |
site | -0.014 |
ently | -0.013 |
exhibit | -0.013 |
Token | Ben |
Token ID | 3932 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
quest | +0.033 |
ement | +0.031 |
site | +0.031 |
ently | +0.030 |
ths | +0.030 |
Neg logit contributions | |
their | -0.006 |
burn | -0.006 |
Woo | -0.005 |
Sara | -0.005 |
her | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
burn | +0.039 |
their | +0.035 |
y | +0.034 |
Woo | +0.034 |
Sara | +0.031 |
Neg logit contributions | |
quest | -0.081 |
ement | -0.076 |
site | -0.073 |
ently | -0.072 |
ths | -0.071 |
Token | forgot |
Token ID | 16453 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
burn | +0.009 |
y | +0.008 |
Woo | +0.008 |
their | +0.008 |
ot | +0.007 |
Neg logit contributions | |
quest | -0.011 |
site | -0.010 |
ement | -0.010 |
exhibit | -0.010 |
ths | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
burn | +0.032 |
y | +0.028 |
ety | +0.027 |
ot | +0.026 |
La | +0.026 |
Neg logit contributions | |
quest | -0.037 |
ement | -0.034 |
site | -0.033 |
ently | -0.032 |
repairs | -0.032 |
Token | buy |
Token ID | 2822 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
quest | +0.027 |
ement | +0.024 |
site | +0.024 |
ently | +0.023 |
ths | +0.023 |
Neg logit contributions | |
burn | -0.019 |
y | -0.017 |
Woo | -0.017 |
their | -0.017 |
ety | -0.016 |
Token | av |
Token ID | 1196 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
burn | +0.008 |
y | +0.007 |
ot | +0.007 |
Woo | +0.007 |
ety | +0.006 |
Neg logit contributions | |
quest | -0.011 |
ement | -0.011 |
site | -0.010 |
ently | -0.010 |
repairs | -0.010 |
Token | oc |
Token ID | 420 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
quest | +0.015 |
ement | +0.013 |
site | +0.012 |
ently | +0.012 |
ths | +0.011 |
Neg logit contributions | |
burn | -0.027 |
y | -0.026 |
their | -0.026 |
Woo | -0.025 |
ety | -0.025 |
Token | ados |
Token ID | 22484 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
quest | +0.154 |
mission | +0.126 |
passage | +0.123 |
site | +0.123 |
trek | +0.121 |
Neg logit contributions | |
burn | -0.138 |
y | -0.129 |
her | -0.127 |
C | -0.125 |
your | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
quest | +0.037 |
ement | +0.035 |
site | +0.034 |
ently | +0.033 |
exhibit | +0.033 |
Neg logit contributions | |
burn | -0.025 |
Woo | -0.021 |
ot | -0.021 |
y | -0.021 |
their | -0.020 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
burn | +0.009 |
y | +0.008 |
their | +0.007 |
groom | +0.007 |
ful | +0.007 |
Neg logit contributions | |
quest | -0.017 |
ement | -0.016 |
site | -0.016 |
ently | -0.015 |
exhibit | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
y | +0.017 |
burn | +0.016 |
their | +0.015 |
her | +0.015 |
Woo | +0.015 |
Neg logit contributions | |
quest | -0.036 |
ement | -0.036 |
ently | -0.034 |
site | -0.034 |
renches | -0.032 |
Token | sad |
Token ID | 6507 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
burn | +0.005 |
y | +0.005 |
Woo | +0.005 |
ot | +0.005 |
ety | +0.005 |
Neg logit contributions | |
quest | -0.009 |
ement | -0.008 |
site | -0.008 |
ths | -0.008 |
repairs | -0.008 |
Token | egg |
Token ID | 5935 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
quest | +0.051 |
ement | +0.050 |
ently | +0.049 |
renches | +0.048 |
ths | +0.047 |
Neg logit contributions | |
y | -0.034 |
burn | -0.033 |
their | -0.032 |
Sara | -0.029 |
c | -0.029 |
Token | ! |
Token ID | 0 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
burn | +0.003 |
Woo | +0.003 |
their | +0.003 |
y | +0.003 |
ety | +0.003 |
Neg logit contributions | |
quest | -0.005 |
ement | -0.005 |
site | -0.004 |
ently | -0.004 |
exhibit | -0.004 |
Token | He |
Token ID | 679 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
quest | +0.009 |
ement | +0.008 |
site | +0.008 |
ently | +0.008 |
ths | +0.008 |
Neg logit contributions | |
burn | -0.005 |
their | -0.005 |
y | -0.005 |
Woo | -0.005 |
ety | -0.004 |
Token | watched |
Token ID | 7342 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
quest | +0.013 |
ement | +0.013 |
site | +0.012 |
ently | +0.012 |
ths | +0.012 |
Neg logit contributions | |
y | -0.007 |
their | -0.006 |
burn | -0.006 |
her | -0.006 |
Sara | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
quest | +0.026 |
ement | +0.024 |
site | +0.023 |
ently | +0.023 |
ths | +0.023 |
Neg logit contributions | |
burn | -0.010 |
their | -0.009 |
y | -0.009 |
Woo | -0.009 |
Sara | -0.008 |
Token | amaz |
Token ID | 40642 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
their | +0.005 |
her | +0.005 |
Sara | +0.004 |
like | +0.004 |
y | +0.004 |
Neg logit contributions | |
quest | -0.008 |
ently | -0.008 |
ement | -0.007 |
renches | -0.007 |
ths | -0.007 |
Token | ement |
Token ID | 972 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
quest | +0.061 |
exhibit | +0.033 |
site | +0.029 |
renches | +0.029 |
mission | +0.029 |
Neg logit contributions | |
their | -0.233 |
her | -0.230 |
y | -0.230 |
your | -0.219 |
ful | -0.217 |
Token | as |
Token ID | 355 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
quest | +0.009 |
ement | +0.009 |
site | +0.008 |
ently | +0.008 |
ths | +0.008 |
Neg logit contributions | |
burn | -0.006 |
their | -0.006 |
y | -0.006 |
her | -0.005 |
Woo | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
burn | +0.019 |
their | +0.019 |
y | +0.018 |
Woo | +0.018 |
Sara | +0.017 |
Neg logit contributions | |
quest | -0.039 |
ement | -0.037 |
site | -0.036 |
ently | -0.035 |
ths | -0.035 |
Token | egg |
Token ID | 5935 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
quest | +0.011 |
ement | +0.010 |
renches | +0.010 |
ently | +0.010 |
site | +0.010 |
Neg logit contributions | |
burn | -0.007 |
y | -0.006 |
their | -0.006 |
her | -0.006 |
Sara | -0.006 |
Token | began |
Token ID | 2540 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
quest | +0.014 |
ement | +0.013 |
site | +0.012 |
ently | +0.012 |
ths | +0.012 |
Neg logit contributions | |
burn | -0.009 |
their | -0.008 |
y | -0.008 |
Woo | -0.008 |
ot | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
quest | +0.015 |
ement | +0.014 |
site | +0.014 |
exhibit | +0.014 |
ths | +0.013 |
Neg logit contributions | |
burn | -0.007 |
y | -0.006 |
Woo | -0.006 |
their | -0.006 |
ety | -0.006 |
Token | rabbit |
Token ID | 22746 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
quest | +0.005 |
ement | +0.005 |
site | +0.005 |
exhibit | +0.004 |
ths | +0.004 |
Neg logit contributions | |
burn | -0.004 |
their | -0.004 |
y | -0.004 |
Woo | -0.004 |
ety | -0.004 |
Token | standing |
Token ID | 5055 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
quest | +0.042 |
ement | +0.039 |
site | +0.038 |
ently | +0.038 |
ths | +0.037 |
Neg logit contributions | |
burn | -0.027 |
y | -0.025 |
their | -0.025 |
Woo | -0.024 |
C | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
quest | +0.034 |
ement | +0.034 |
site | +0.031 |
ently | +0.031 |
ths | +0.030 |
Neg logit contributions | |
burn | -0.035 |
Woo | -0.031 |
their | -0.030 |
groom | -0.029 |
rav | -0.029 |
Token | its |
Token ID | 663 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
quest | +0.035 |
ement | +0.032 |
site | +0.032 |
exhibit | +0.031 |
ently | +0.030 |
Neg logit contributions | |
burn | -0.016 |
y | -0.013 |
ety | -0.013 |
Woo | -0.013 |
ot | -0.013 |
Token | hind |
Token ID | 16222 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
quest | +0.003 |
ement | +0.003 |
site | +0.003 |
ently | +0.003 |
ths | +0.003 |
Neg logit contributions | |
burn | -0.003 |
their | -0.003 |
y | -0.003 |
Woo | -0.002 |
her | -0.002 |
Token | legs |
Token ID | 7405 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
ement | +0.168 |
quest | +0.154 |
renches | +0.153 |
site | +0.152 |
ival | +0.151 |
Neg logit contributions | |
y | -0.109 |
her | -0.109 |
their | -0.107 |
your | -0.100 |
ot | -0.100 |
Token | and |
Token ID | 290 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
quest | +0.001 |
ement | +0.001 |
site | +0.001 |
ently | +0.001 |
exhibit | +0.001 |
Neg logit contributions | |
burn | -0.001 |
their | -0.001 |
Woo | -0.001 |
y | -0.001 |
Sara | -0.001 |
Token | hopping |
Token ID | 47153 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
quest | +0.008 |
ement | +0.007 |
site | +0.007 |
ently | +0.007 |
ths | +0.007 |
Neg logit contributions | |
burn | -0.006 |
y | -0.005 |
their | -0.005 |
Woo | -0.005 |
ety | -0.005 |
Token | around |
Token ID | 1088 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
quest | +0.046 |
ement | +0.041 |
ued | +0.039 |
site | +0.038 |
ently | +0.038 |
Neg logit contributions | |
burn | -0.049 |
groom | -0.042 |
ety | -0.042 |
Woo | -0.042 |
Sara | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
quest | +0.010 |
ement | +0.009 |
site | +0.009 |
ently | +0.008 |
ths | +0.008 |
Neg logit contributions | |
burn | -0.005 |
their | -0.005 |
y | -0.005 |
Woo | -0.005 |
Sara | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
quest | +0.061 |
ement | +0.057 |
ths | +0.056 |
site | +0.055 |
exhibit | +0.054 |
Neg logit contributions | |
burn | -0.044 |
their | -0.041 |
y | -0.041 |
Woo | -0.041 |
ot | -0.040 |
Token | Tim |
Token ID | 5045 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
burn | +0.013 |
y | +0.012 |
their | +0.012 |
Woo | +0.011 |
ety | +0.011 |
Neg logit contributions | |
quest | -0.023 |
ement | -0.021 |
site | -0.020 |
ently | -0.020 |
exhibit | -0.020 |
Token | my |
Token ID | 1820 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
quest | +0.020 |
ement | +0.019 |
site | +0.018 |
ently | +0.018 |
ths | +0.018 |
Neg logit contributions | |
burn | -0.007 |
their | -0.006 |
Woo | -0.006 |
y | -0.005 |
C | -0.005 |
Token | watched |
Token ID | 7342 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
burn | +0.008 |
y | +0.007 |
their | +0.007 |
Woo | +0.007 |
ot | +0.006 |
Neg logit contributions | |
quest | -0.014 |
ement | -0.013 |
site | -0.013 |
ently | -0.013 |
ths | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
quest | +0.002 |
ement | +0.002 |
site | +0.002 |
ently | +0.002 |
exhibit | +0.002 |
Neg logit contributions | |
burn | -0.001 |
their | -0.001 |
y | -0.001 |
Woo | -0.001 |
Sara | -0.001 |
Token | amaz |
Token ID | 40642 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
their | +0.015 |
her | +0.013 |
burn | +0.012 |
Sara | +0.011 |
Woo | +0.010 |
Neg logit contributions | |
quest | -0.051 |
ently | -0.049 |
ement | -0.048 |
site | -0.048 |
ths | -0.047 |
Token | ement |
Token ID | 972 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
quest | +0.059 |
exhibit | +0.032 |
site | +0.027 |
boulder | +0.027 |
trek | +0.026 |
Neg logit contributions | |
their | -0.237 |
y | -0.234 |
her | -0.231 |
burn | -0.227 |
ful | -0.222 |
Token | as |
Token ID | 355 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
quest | +0.008 |
ement | +0.007 |
site | +0.007 |
ently | +0.007 |
ths | +0.007 |
Neg logit contributions | |
burn | -0.005 |
their | -0.005 |
y | -0.005 |
Woo | -0.005 |
Sara | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
burn | +0.023 |
y | +0.021 |
their | +0.020 |
Woo | +0.020 |
ety | +0.019 |
Neg logit contributions | |
quest | -0.034 |
ement | -0.032 |
site | -0.031 |
ently | -0.030 |
ths | -0.030 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
quest | +0.037 |
ement | +0.036 |
ently | +0.035 |
site | +0.035 |
renches | +0.033 |
Neg logit contributions | |
y | -0.016 |
their | -0.015 |
burn | -0.015 |
c | -0.015 |
her | -0.014 |
Token | stars |
Token ID | 5788 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
quest | +0.083 |
ement | +0.075 |
ently | +0.074 |
site | +0.073 |
ths | +0.073 |
Neg logit contributions | |
their | -0.029 |
her | -0.026 |
burn | -0.025 |
Sara | -0.025 |
y | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
burn | +0.002 |
Woo | +0.002 |
groom | +0.002 |
ety | +0.002 |
free | +0.002 |
Neg logit contributions | |
quest | -0.002 |
ement | -0.002 |
site | -0.002 |
exhibit | -0.001 |
ently | -0.001 |
Token | But |
Token ID | 887 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
quest | +0.017 |
exhibit | +0.016 |
site | +0.016 |
ement | +0.016 |
renches | +0.016 |
Neg logit contributions | |
burn | -0.021 |
y | -0.018 |
groom | -0.017 |
ety | -0.016 |
a | -0.016 |
Token | those |
Token ID | 883 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
quest | +0.068 |
ement | +0.064 |
site | +0.062 |
ths | +0.061 |
ently | +0.061 |
Neg logit contributions | |
burn | -0.038 |
y | -0.034 |
Woo | -0.033 |
their | -0.033 |
ety | -0.031 |
Token | are |
Token ID | 389 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
quest | +0.008 |
ement | +0.008 |
site | +0.008 |
ently | +0.008 |
ths | +0.008 |
Neg logit contributions | |
burn | -0.003 |
their | -0.003 |
y | -0.002 |
Woo | -0.002 |
Sara | -0.002 |
Token | not |
Token ID | 407 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
burn | +0.007 |
y | +0.006 |
flower | +0.005 |
free | +0.005 |
Woo | +0.005 |
Neg logit contributions | |
quest | -0.009 |
site | -0.008 |
ths | -0.008 |
renches | -0.008 |
repairs | -0.008 |
Token | tr |
Token ID | 491 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
burn | +0.008 |
Woo | +0.007 |
y | +0.007 |
La | +0.007 |
Qu | +0.007 |
Neg logit contributions | |
quest | -0.012 |
site | -0.011 |
repairs | -0.011 |
ths | -0.010 |
exhibit | -0.010 |
Token | unks |
Token ID | 14125 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
quest | +0.148 |
ement | +0.125 |
site | +0.121 |
ently | +0.118 |
mission | +0.116 |
Neg logit contributions | |
burn | -0.148 |
y | -0.137 |
Woo | -0.130 |
their | -0.129 |
ety | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
quest | +0.100 |
ement | +0.093 |
site | +0.091 |
exhibit | +0.089 |
ently | +0.089 |
Neg logit contributions | |
burn | -0.056 |
Woo | -0.049 |
their | -0.047 |
y | -0.046 |
groom | -0.045 |
Token | Those |
Token ID | 5845 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
renches | +0.021 |
quest | +0.021 |
ement | +0.021 |
site | +0.021 |
exhibit | +0.021 |
Neg logit contributions | |
burn | -0.018 |
y | -0.016 |
groom | -0.015 |
her | -0.014 |
ety | -0.014 |
Token | are |
Token ID | 389 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
quest | +0.026 |
ement | +0.024 |
site | +0.024 |
ently | +0.023 |
exhibit | +0.023 |
Neg logit contributions | |
burn | -0.010 |
y | -0.009 |
their | -0.009 |
Woo | -0.009 |
ety | -0.008 |
Token | my |
Token ID | 616 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
quest | +0.000 |
site | +0.000 |
repairs | +0.000 |
ths | +0.000 |
renches | +0.000 |
Neg logit contributions | |
burn | -0.000 |
y | -0.000 |
Woo | -0.000 |
ety | -0.000 |
free | -0.000 |
Token | learn |
Token ID | 2193 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
quest | +0.026 |
site | +0.023 |
ement | +0.023 |
ently | +0.023 |
exhibit | +0.022 |
Neg logit contributions | |
burn | -0.014 |
y | -0.013 |
Woo | -0.012 |
ety | -0.012 |
their | -0.012 |
Token | more |
Token ID | 517 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
burn | +0.033 |
y | +0.029 |
Woo | +0.028 |
ety | +0.027 |
their | +0.027 |
Neg logit contributions | |
quest | -0.053 |
ement | -0.049 |
site | -0.048 |
ently | -0.047 |
exhibit | -0.046 |
Token | about |
Token ID | 546 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
their | +0.021 |
burn | +0.019 |
y | +0.019 |
her | +0.018 |
your | +0.018 |
Neg logit contributions | |
quest | -0.030 |
ement | -0.028 |
ths | -0.027 |
site | -0.026 |
exhibit | -0.026 |
Token | rh |
Token ID | 9529 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
quest | +0.008 |
ement | +0.008 |
site | +0.008 |
ently | +0.007 |
ths | +0.007 |
Neg logit contributions | |
burn | -0.004 |
y | -0.003 |
Woo | -0.003 |
their | -0.003 |
ot | -0.003 |
Token | in |
Token ID | 259 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
quest | +0.134 |
ement | +0.116 |
mission | +0.110 |
attempts | +0.110 |
site | +0.109 |
Neg logit contributions | |
y | -0.076 |
a | -0.069 |
their | -0.067 |
burn | -0.067 |
S | -0.063 |
Token | oc |
Token ID | 420 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
quest | +0.014 |
ement | +0.013 |
ently | +0.013 |
ths | +0.012 |
renches | +0.012 |
Neg logit contributions | |
y | -0.013 |
their | -0.013 |
burn | -0.012 |
ful | -0.011 |
free | -0.011 |
Token | er |
Token ID | 263 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
quest | +0.120 |
mission | +0.089 |
ement | +0.087 |
site | +0.082 |
attempts | +0.081 |
Neg logit contributions | |
burn | -0.168 |
y | -0.161 |
their | -0.159 |
C | -0.156 |
ful | -0.154 |
Token | oses |
Token ID | 4629 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
burn | +0.031 |
Woo | +0.029 |
their | +0.027 |
groom | +0.027 |
Pop | +0.026 |
Neg logit contributions | |
quest | -0.040 |
ement | -0.038 |
site | -0.037 |
ently | -0.037 |
exhibit | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
quest | +0.014 |
ement | +0.013 |
site | +0.012 |
ently | +0.012 |
ths | +0.012 |
Neg logit contributions | |
burn | -0.008 |
their | -0.007 |
y | -0.007 |
Woo | -0.007 |
Sara | -0.007 |
Token | respect |
Token ID | 2461 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
quest | +0.041 |
ement | +0.039 |
ently | +0.036 |
site | +0.036 |
ths | +0.035 |
Neg logit contributions | |
burn | -0.035 |
their | -0.034 |
y | -0.033 |
Woo | -0.032 |
Sara | -0.031 |
Token | them |
Token ID | 606 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
burn | +0.018 |
Woo | +0.016 |
y | +0.015 |
ety | +0.015 |
groom | +0.014 |
Neg logit contributions | |
quest | -0.030 |
ement | -0.028 |
site | -0.028 |
ently | -0.027 |
exhibit | -0.026 |
Token | animals |
Token ID | 4695 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
quest | +0.008 |
ement | +0.008 |
ently | +0.008 |
ued | +0.007 |
ths | +0.007 |
Neg logit contributions | |
y | -0.005 |
their | -0.005 |
her | -0.004 |
Sara | -0.004 |
c | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
quest | +0.038 |
ement | +0.037 |
site | +0.035 |
ently | +0.035 |
ths | +0.035 |
Neg logit contributions | |
their | -0.018 |
y | -0.018 |
burn | -0.016 |
her | -0.015 |
ot | -0.014 |
Token | watching |
Token ID | 4964 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
quest | +0.025 |
ement | +0.023 |
site | +0.022 |
ently | +0.022 |
ths | +0.021 |
Neg logit contributions | |
burn | -0.015 |
y | -0.013 |
their | -0.013 |
Woo | -0.013 |
ety | -0.012 |
Token | him |
Token ID | 683 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
burn | +0.002 |
ety | +0.002 |
Woo | +0.002 |
y | +0.002 |
groom | +0.002 |
Neg logit contributions | |
quest | -0.003 |
ement | -0.003 |
site | -0.003 |
exhibit | -0.003 |
ently | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
quest | +0.025 |
ement | +0.023 |
site | +0.023 |
ently | +0.022 |
ths | +0.022 |
Neg logit contributions | |
burn | -0.014 |
their | -0.013 |
y | -0.012 |
Woo | -0.012 |
ot | -0.011 |
Token | amaz |
Token ID | 40642 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
their | +0.008 |
burn | +0.008 |
y | +0.007 |
Woo | +0.007 |
her | +0.007 |
Neg logit contributions | |
quest | -0.021 |
ement | -0.020 |
ently | -0.020 |
site | -0.020 |
ths | -0.019 |
Token | ement |
Token ID | 972 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
quest | +0.054 |
exhibit | +0.028 |
trek | +0.024 |
site | +0.024 |
boulder | +0.023 |
Neg logit contributions | |
y | -0.239 |
their | -0.233 |
burn | -0.230 |
her | -0.225 |
ful | -0.219 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
quest | +0.003 |
ement | +0.003 |
site | +0.002 |
ently | +0.002 |
ths | +0.002 |
Neg logit contributions | |
burn | -0.002 |
their | -0.001 |
y | -0.001 |
Woo | -0.001 |
Sara | -0.001 |
Token | |
Token ID | 220 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
their | +0.000 |
Sara | +0.000 |
C | +0.000 |
Woo | +0.000 |
burn | +0.000 |
Neg logit contributions | |
quest | -0.001 |
ement | -0.000 |
ently | -0.000 |
ths | -0.000 |
site | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
their | +0.001 |
burn | +0.001 |
y | +0.001 |
Woo | +0.001 |
Sara | +0.001 |
Neg logit contributions | |
quest | -0.002 |
ement | -0.002 |
ths | -0.002 |
site | -0.002 |
ently | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
quest | +0.009 |
ement | +0.008 |
ths | +0.008 |
ently | +0.008 |
site | +0.008 |
Neg logit contributions | |
their | -0.003 |
y | -0.003 |
Sara | -0.003 |
Woo | -0.003 |
burn | -0.003 |
Token | lesson |
Token ID | 11483 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
ement | +0.053 |
quest | +0.052 |
site | +0.050 |
ths | +0.049 |
ently | +0.049 |
Neg logit contributions | |
burn | -0.021 |
their | -0.020 |
ot | -0.018 |
her | -0.017 |
Woo | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
burn | +0.012 |
their | +0.012 |
y | +0.011 |
Woo | +0.011 |
Sara | +0.011 |
Neg logit contributions | |
quest | -0.020 |
ement | -0.019 |
site | -0.018 |
ently | -0.018 |
ths | -0.018 |
Token | never |
Token ID | 1239 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
burn | +0.015 |
y | +0.013 |
their | +0.013 |
Woo | +0.013 |
ety | +0.012 |
Neg logit contributions | |
quest | -0.025 |
ement | -0.023 |
site | -0.022 |
ently | -0.022 |
ths | -0.022 |
Token | pretended |
Token ID | 36766 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
quest | +0.011 |
ement | +0.010 |
site | +0.010 |
ently | +0.010 |
ths | +0.009 |
Neg logit contributions | |
burn | -0.007 |
their | -0.006 |
y | -0.006 |
Woo | -0.006 |
Sara | -0.006 |
Token | with |
Token ID | 351 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
quest | +0.034 |
ement | +0.033 |
site | +0.031 |
ently | +0.031 |
ths | +0.031 |
Neg logit contributions | |
their | -0.011 |
burn | -0.010 |
her | -0.009 |
y | -0.009 |
Woo | -0.009 |
Token | tr |
Token ID | 491 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
quest | +0.037 |
ement | +0.035 |
site | +0.034 |
ently | +0.033 |
ths | +0.033 |
Neg logit contributions | |
burn | -0.016 |
their | -0.016 |
y | -0.015 |
Woo | -0.015 |
her | -0.014 |
Token | ays |
Token ID | 592 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
quest | +0.175 |
mission | +0.148 |
site | +0.143 |
lair | +0.138 |
repairs | +0.137 |
Neg logit contributions | |
y | -0.112 |
burn | -0.107 |
o | -0.100 |
ety | -0.100 |
ful | -0.098 |
Token | again |
Token ID | 757 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
quest | +0.036 |
ement | +0.033 |
site | +0.032 |
ths | +0.032 |
ently | +0.031 |
Neg logit contributions | |
their | -0.021 |
burn | -0.021 |
y | -0.020 |
her | -0.020 |
Sara | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
burn | +0.035 |
their | +0.033 |
y | +0.032 |
Woo | +0.031 |
Sara | +0.029 |
Neg logit contributions | |
quest | -0.065 |
ement | -0.061 |
site | -0.059 |
ently | -0.058 |
ths | -0.057 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
burn | +0.015 |
y | +0.013 |
their | +0.013 |
Woo | +0.013 |
groom | +0.013 |
Neg logit contributions | |
quest | -0.022 |
ement | -0.020 |
site | -0.020 |
ently | -0.019 |
exhibit | -0.019 |
Token | Billy |
Token ID | 49640 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
quest | +0.035 |
ement | +0.033 |
site | +0.032 |
ently | +0.031 |
exhibit | +0.031 |
Neg logit contributions | |
burn | -0.025 |
y | -0.022 |
their | -0.022 |
Woo | -0.022 |
groom | -0.021 |
Token | me |
Token ID | 502 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
burn | +0.012 |
y | +0.011 |
their | +0.011 |
Woo | +0.011 |
ot | +0.010 |
Neg logit contributions | |
quest | -0.024 |
ement | -0.022 |
site | -0.022 |
ently | -0.021 |
ths | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ement | +0.056 |
quest | +0.056 |
site | +0.052 |
ently | +0.052 |
ths | +0.051 |
Neg logit contributions | |
burn | -0.021 |
their | -0.018 |
y | -0.018 |
Woo | -0.016 |
your | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
quest | +0.008 |
ement | +0.008 |
ently | +0.008 |
site | +0.008 |
ths | +0.008 |
Neg logit contributions | |
burn | -0.002 |
their | -0.002 |
Woo | -0.002 |
y | -0.001 |
Sara | -0.001 |
Token | nearest |
Token ID | 16936 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
burn | +0.029 |
y | +0.028 |
their | +0.027 |
ot | +0.027 |
Woo | +0.027 |
Neg logit contributions | |
quest | -0.021 |
site | -0.018 |
ement | -0.018 |
exhibit | -0.017 |
ths | -0.016 |
Token | fire |
Token ID | 2046 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
burn | +0.005 |
their | +0.004 |
Woo | +0.004 |
y | +0.004 |
C | +0.004 |
Neg logit contributions | |
ement | -0.004 |
quest | -0.004 |
ently | -0.004 |
ths | -0.004 |
renches | -0.004 |
Token | hyd |
Token ID | 7409 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
burn | +0.012 |
y | +0.011 |
their | +0.011 |
Woo | +0.011 |
C | +0.010 |
Neg logit contributions | |
quest | -0.021 |
ement | -0.020 |
site | -0.019 |
ently | -0.019 |
ths | -0.019 |
Token | rant |
Token ID | 5250 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
burn | +0.107 |
Woo | +0.105 |
Sara | +0.101 |
their | +0.100 |
groom | +0.100 |
Neg logit contributions | |
quest | -0.141 |
site | -0.136 |
ently | -0.132 |
ement | -0.130 |
exhibit | -0.129 |
Token | ?" |
Token ID | 1701 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
burn | +0.036 |
Woo | +0.033 |
their | +0.033 |
y | +0.032 |
ot | +0.031 |
Neg logit contributions | |
quest | -0.046 |
site | -0.043 |
ement | -0.042 |
exhibit | -0.041 |
ently | -0.040 |
Token | |
Token ID | 220 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
burn | +0.005 |
y | +0.005 |
their | +0.004 |
Woo | +0.004 |
ety | +0.004 |
Neg logit contributions | |
quest | -0.014 |
ement | -0.013 |
site | -0.012 |
exhibit | -0.012 |
ently | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
burn | +0.007 |
their | +0.007 |
y | +0.007 |
Woo | +0.007 |
Sara | +0.007 |
Neg logit contributions | |
quest | -0.019 |
ement | -0.017 |
site | -0.017 |
ths | -0.017 |
exhibit | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
burn | +0.002 |
y | +0.002 |
Woo | +0.002 |
their | +0.002 |
groom | +0.002 |
Neg logit contributions | |
quest | -0.003 |
ement | -0.003 |
site | -0.003 |
ently | -0.003 |
exhibit | -0.003 |
Token | May |
Token ID | 6747 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
quest | +0.010 |
ement | +0.009 |
site | +0.009 |
ently | +0.009 |
ths | +0.009 |
Neg logit contributions | |
burn | -0.007 |
their | -0.006 |
y | -0.006 |
Woo | -0.006 |
ety | -0.006 |
Token | a |
Token ID | 64 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
burn | +0.017 |
Woo | +0.015 |
their | +0.013 |
C | +0.012 |
free | +0.012 |
Neg logit contributions | |
quest | -0.036 |
ement | -0.033 |
ently | -0.033 |
exhibit | -0.032 |
ths | -0.032 |
Token | walked |
Token ID | 6807 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
burn | +0.006 |
y | +0.006 |
their | +0.006 |
Woo | +0.005 |
ot | +0.005 |
Neg logit contributions | |
quest | -0.013 |
ement | -0.013 |
site | -0.012 |
ently | -0.012 |
ths | -0.012 |
Token | into |
Token ID | 656 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
quest | +0.056 |
site | +0.051 |
ement | +0.050 |
exhibit | +0.049 |
ently | +0.049 |
Neg logit contributions | |
burn | -0.034 |
Woo | -0.029 |
y | -0.027 |
ety | -0.027 |
C | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
burn | +0.021 |
y | +0.017 |
Woo | +0.016 |
ety | +0.016 |
their | +0.015 |
Neg logit contributions | |
quest | -0.069 |
ement | -0.064 |
site | -0.063 |
ently | -0.061 |
exhibit | -0.061 |
Token | living |
Token ID | 2877 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
burn | +0.020 |
y | +0.019 |
their | +0.019 |
Woo | +0.019 |
ot | +0.019 |
Neg logit contributions | |
quest | -0.017 |
site | -0.014 |
ement | -0.014 |
exhibit | -0.014 |
lair | -0.013 |
Token | room |
Token ID | 2119 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
burn | +0.129 |
Woo | +0.118 |
y | +0.116 |
their | +0.116 |
ety | +0.112 |
Neg logit contributions | |
quest | -0.123 |
ement | -0.113 |
site | -0.109 |
ently | -0.106 |
ths | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
their | +0.039 |
y | +0.038 |
her | +0.037 |
burn | +0.034 |
ot | +0.031 |
Neg logit contributions | |
quest | -0.109 |
ement | -0.105 |
renches | -0.101 |
ths | -0.101 |
ently | -0.099 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
burn | +0.019 |
y | +0.017 |
Woo | +0.017 |
their | +0.016 |
ot | +0.016 |
Neg logit contributions | |
quest | -0.021 |
site | -0.018 |
ement | -0.017 |
exhibit | -0.017 |
ths | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
quest | +0.068 |
ement | +0.065 |
site | +0.063 |
ently | +0.061 |
ths | +0.061 |
Neg logit contributions | |
burn | -0.027 |
y | -0.024 |
Woo | -0.022 |
their | -0.022 |
ety | -0.022 |
Token | dad |
Token ID | 9955 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
burn | +0.018 |
their | +0.017 |
y | +0.016 |
Woo | +0.016 |
Sara | +0.015 |
Neg logit contributions | |
quest | -0.025 |
ement | -0.024 |
site | -0.023 |
ently | -0.022 |
ths | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
quest | +0.009 |
ement | +0.008 |
site | +0.008 |
ently | +0.008 |
ths | +0.008 |
Neg logit contributions | |
burn | -0.006 |
their | -0.005 |
y | -0.005 |
Woo | -0.005 |
ety | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
burn | +0.001 |
y | +0.000 |
groom | +0.000 |
ety | +0.000 |
ot | +0.000 |
Neg logit contributions | |
quest | -0.001 |
ement | -0.001 |
site | -0.001 |
exhibit | -0.001 |
repairs | -0.001 |
Token | little |
Token ID | 1310 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
burn | +0.020 |
y | +0.017 |
ful | +0.017 |
Woo | +0.017 |
their | +0.017 |
Neg logit contributions | |
quest | -0.016 |
site | -0.013 |
ement | -0.013 |
exhibit | -0.013 |
mission | -0.013 |
Token | dog |
Token ID | 3290 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
quest | +0.008 |
ement | +0.007 |
exhibit | +0.007 |
site | +0.007 |
mountain | +0.007 |
Neg logit contributions | |
burn | -0.007 |
their | -0.006 |
La | -0.006 |
Woo | -0.006 |
Lara | -0.006 |
Token | named |
Token ID | 3706 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
burn | +0.016 |
their | +0.015 |
y | +0.014 |
Woo | +0.014 |
groom | +0.014 |
Neg logit contributions | |
quest | -0.019 |
ement | -0.017 |
site | -0.017 |
exhibit | -0.016 |
ently | -0.016 |
Token | Sleep |
Token ID | 17376 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
burn | +0.034 |
groom | +0.033 |
y | +0.033 |
band | +0.030 |
flower | +0.030 |
Neg logit contributions | |
quest | -0.044 |
exhibit | -0.039 |
site | -0.037 |
scaven | -0.037 |
repairs | -0.037 |
Token | y |
Token ID | 88 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
burn | +0.112 |
groom | +0.096 |
Woo | +0.089 |
Lara | +0.088 |
inas | +0.085 |
Neg logit contributions | |
quest | -0.140 |
mission | -0.120 |
exhibit | -0.119 |
site | -0.118 |
ement | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
quest | +0.003 |
ement | +0.002 |
site | +0.002 |
exhibit | +0.002 |
ently | +0.002 |
Neg logit contributions | |
burn | -0.002 |
their | -0.002 |
Woo | -0.002 |
ety | -0.002 |
y | -0.002 |
Token | Sleep |
Token ID | 17376 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
quest | +0.015 |
ement | +0.014 |
site | +0.013 |
exhibit | +0.013 |
repairs | +0.013 |
Neg logit contributions | |
burn | -0.008 |
y | -0.008 |
a | -0.008 |
ety | -0.008 |
ot | -0.008 |
Token | y |
Token ID | 88 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
burn | +0.115 |
groom | +0.101 |
Woo | +0.091 |
Lara | +0.087 |
Pop | +0.084 |
Neg logit contributions | |
quest | -0.134 |
ement | -0.117 |
mission | -0.117 |
site | -0.117 |
ently | -0.116 |
Token | was |
Token ID | 373 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
quest | +0.013 |
ement | +0.011 |
site | +0.011 |
exhibit | +0.011 |
ently | +0.011 |
Neg logit contributions | |
burn | -0.011 |
their | -0.009 |
Woo | -0.009 |
ety | -0.009 |
y | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
quest | +0.021 |
ement | +0.019 |
ths | +0.019 |
site | +0.019 |
renches | +0.018 |
Neg logit contributions | |
their | -0.008 |
y | -0.008 |
burn | -0.008 |
Sara | -0.007 |
her | -0.007 |
Token | Jane |
Token ID | 41083 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
quest | +0.012 |
ement | +0.011 |
site | +0.011 |
ently | +0.010 |
ths | +0.010 |
Neg logit contributions | |
burn | -0.008 |
their | -0.008 |
y | -0.008 |
Woo | -0.008 |
Sara | -0.007 |
Token | went |
Token ID | 1816 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ement | +0.020 |
quest | +0.019 |
ently | +0.018 |
site | +0.018 |
renches | +0.018 |
Neg logit contributions | |
y | -0.009 |
their | -0.008 |
her | -0.008 |
c | -0.007 |
burn | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
quest | +0.037 |
site | +0.033 |
ement | +0.033 |
exhibit | +0.033 |
ently | +0.032 |
Neg logit contributions | |
burn | -0.018 |
y | -0.015 |
Woo | -0.015 |
their | -0.015 |
ety | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
burn | +0.017 |
y | +0.015 |
Woo | +0.013 |
their | +0.013 |
ety | +0.012 |
Neg logit contributions | |
quest | -0.061 |
ement | -0.057 |
site | -0.056 |
exhibit | -0.055 |
ently | -0.055 |
Token | living |
Token ID | 2877 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
burn | +0.047 |
y | +0.044 |
their | +0.043 |
Woo | +0.042 |
ot | +0.042 |
Neg logit contributions | |
quest | -0.030 |
site | -0.026 |
ement | -0.025 |
exhibit | -0.024 |
ths | -0.023 |
Token | room |
Token ID | 2119 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
burn | +0.126 |
Woo | +0.115 |
y | +0.114 |
their | +0.114 |
ety | +0.108 |
Neg logit contributions | |
quest | -0.124 |
ement | -0.113 |
site | -0.109 |
ently | -0.105 |
ths | -0.104 |
Token | , |
Token ID | 11 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
their | +0.030 |
y | +0.029 |
her | +0.027 |
like | +0.023 |
burn | +0.023 |
Neg logit contributions | |
quest | -0.107 |
ement | -0.104 |
renches | -0.102 |
ths | -0.100 |
ently | -0.100 |
Token | and |
Token ID | 290 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
burn | +0.011 |
their | +0.010 |
y | +0.010 |
Woo | +0.010 |
Sara | +0.010 |
Neg logit contributions | |
quest | -0.015 |
ement | -0.014 |
site | -0.013 |
ently | -0.013 |
ths | -0.013 |
Token | there |
Token ID | 612 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
burn | +0.020 |
y | +0.018 |
their | +0.017 |
Woo | +0.017 |
ety | +0.016 |
Neg logit contributions | |
quest | -0.031 |
ement | -0.029 |
site | -0.028 |
ently | -0.027 |
ths | -0.027 |
Token | she |
Token ID | 673 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
quest | +0.016 |
ement | +0.015 |
site | +0.014 |
ently | +0.014 |
ths | +0.014 |
Neg logit contributions | |
burn | -0.013 |
Woo | -0.011 |
y | -0.011 |
ety | -0.011 |
their | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
burn | +0.000 |
Woo | +0.000 |
their | +0.000 |
y | +0.000 |
C | +0.000 |
Neg logit contributions | |
quest | -0.001 |
ement | -0.001 |
site | -0.001 |
ths | -0.001 |
ently | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
quest | +0.015 |
ement | +0.014 |
ths | +0.014 |
renches | +0.013 |
site | +0.013 |
Neg logit contributions | |
their | -0.005 |
y | -0.004 |
Sara | -0.004 |
burn | -0.004 |
her | -0.004 |
Token | One |
Token ID | 3198 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
quest | +0.007 |
ement | +0.006 |
site | +0.006 |
ently | +0.006 |
ths | +0.006 |
Neg logit contributions | |
burn | -0.005 |
their | -0.005 |
Woo | -0.005 |
y | -0.005 |
C | -0.005 |
Token | day |
Token ID | 1110 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
quest | +0.009 |
adventure | +0.008 |
exhibit | +0.008 |
mission | +0.008 |
exploration | +0.008 |
Neg logit contributions | |
burn | -0.011 |
groom | -0.010 |
Woo | -0.010 |
Lara | -0.010 |
C | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
burn | +0.005 |
y | +0.004 |
their | +0.004 |
Woo | +0.004 |
ety | +0.004 |
Neg logit contributions | |
quest | -0.005 |
ement | -0.005 |
site | -0.005 |
ently | -0.005 |
exhibit | -0.005 |
Token | Sleep |
Token ID | 17376 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
quest | +0.010 |
ement | +0.009 |
site | +0.008 |
ths | +0.008 |
exhibit | +0.008 |
Neg logit contributions | |
burn | -0.006 |
y | -0.005 |
ety | -0.005 |
ot | -0.005 |
ful | -0.004 |
Token | y |
Token ID | 88 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
burn | +0.101 |
groom | +0.087 |
Woo | +0.083 |
Lara | +0.076 |
Sara | +0.073 |
Neg logit contributions | |
quest | -0.150 |
site | -0.132 |
exhibit | -0.130 |
mission | -0.129 |
ently | -0.127 |
Token | went |
Token ID | 1816 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
quest | +0.006 |
ement | +0.006 |
site | +0.005 |
ently | +0.005 |
ths | +0.005 |
Neg logit contributions | |
burn | -0.003 |
y | -0.003 |
their | -0.003 |
Woo | -0.003 |
Sara | -0.003 |
Token | for |
Token ID | 329 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
quest | +0.041 |
ement | +0.037 |
site | +0.036 |
ently | +0.036 |
exhibit | +0.035 |
Neg logit contributions | |
burn | -0.019 |
y | -0.017 |
their | -0.017 |
Woo | -0.016 |
ety | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
burn | +0.014 |
y | +0.012 |
their | +0.012 |
Woo | +0.012 |
ety | +0.011 |
Neg logit contributions | |
quest | -0.038 |
ement | -0.035 |
site | -0.034 |
ently | -0.034 |
ths | -0.033 |
Token | walk |
Token ID | 2513 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
burn | +0.001 |
y | +0.001 |
their | +0.001 |
Woo | +0.000 |
C | +0.000 |
Neg logit contributions | |
quest | -0.001 |
ement | -0.001 |
site | -0.001 |
exhibit | -0.001 |
ths | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
their | +0.002 |
y | +0.002 |
her | +0.002 |
burn | +0.002 |
like | +0.002 |
Neg logit contributions | |
quest | -0.006 |
ement | -0.005 |
renches | -0.005 |
site | -0.005 |
ently | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
quest | +0.016 |
ement | +0.015 |
site | +0.015 |
ently | +0.014 |
ths | +0.014 |
Neg logit contributions | |
burn | -0.004 |
their | -0.003 |
y | -0.003 |
Woo | -0.003 |
Sara | -0.003 |
Token | walked |
Token ID | 6807 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ement | +0.003 |
quest | +0.003 |
ently | +0.003 |
site | +0.003 |
renches | +0.003 |
Neg logit contributions | |
y | -0.002 |
burn | -0.002 |
their | -0.002 |
her | -0.001 |
ety | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
quest | +0.053 |
site | +0.047 |
exhibit | +0.047 |
ement | +0.046 |
ths | +0.045 |
Neg logit contributions | |
burn | -0.039 |
Woo | -0.033 |
groom | -0.032 |
C | -0.030 |
ety | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
burn | +0.018 |
y | +0.015 |
Woo | +0.013 |
their | +0.012 |
ety | +0.012 |
Neg logit contributions | |
quest | -0.067 |
ement | -0.062 |
site | -0.061 |
exhibit | -0.060 |
ently | -0.059 |
Token | living |
Token ID | 2877 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
burn | +0.031 |
y | +0.029 |
their | +0.029 |
Woo | +0.028 |
ety | +0.028 |
Neg logit contributions | |
quest | -0.026 |
site | -0.023 |
ement | -0.023 |
exhibit | -0.022 |
ently | -0.021 |
Token | room |
Token ID | 2119 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
burn | +0.126 |
Woo | +0.115 |
their | +0.114 |
y | +0.114 |
ety | +0.109 |
Neg logit contributions | |
quest | -0.122 |
ement | -0.111 |
site | -0.108 |
ently | -0.104 |
exhibit | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
their | +0.036 |
y | +0.034 |
her | +0.033 |
burn | +0.030 |
Sara | +0.028 |
Neg logit contributions | |
quest | -0.106 |
ement | -0.101 |
renches | -0.098 |
ths | -0.097 |
ently | -0.096 |
Token | entered |
Token ID | 5982 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
burn | +0.011 |
y | +0.010 |
Woo | +0.010 |
their | +0.010 |
ot | +0.009 |
Neg logit contributions | |
quest | -0.013 |
ement | -0.011 |
site | -0.011 |
exhibit | -0.011 |
ths | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
quest | +0.015 |
ement | +0.014 |
site | +0.013 |
ently | +0.013 |
exhibit | +0.013 |
Neg logit contributions | |
burn | -0.006 |
y | -0.005 |
Woo | -0.005 |
their | -0.004 |
ety | -0.004 |
Token | On |
Token ID | 1550 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
burn | +0.002 |
their | +0.002 |
y | +0.002 |
Woo | +0.002 |
Sara | +0.002 |
Neg logit contributions | |
quest | -0.005 |
ement | -0.004 |
site | -0.004 |
ently | -0.004 |
ths | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
quest | +0.037 |
ement | +0.034 |
ths | +0.032 |
site | +0.032 |
lair | +0.032 |
Neg logit contributions | |
their | -0.015 |
burn | -0.015 |
y | -0.013 |
Woo | -0.013 |
Sara | -0.013 |
Token | They |
Token ID | 2990 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
quest | +0.026 |
ement | +0.025 |
site | +0.024 |
ently | +0.024 |
exhibit | +0.023 |
Neg logit contributions | |
burn | -0.009 |
their | -0.008 |
y | -0.008 |
Woo | -0.008 |
ot | -0.007 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
burn | +0.013 |
their | +0.012 |
Woo | +0.012 |
y | +0.012 |
ety | +0.011 |
Neg logit contributions | |
quest | -0.019 |
ement | -0.017 |
site | -0.017 |
ently | -0.016 |
ths | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
quest | +0.035 |
site | +0.032 |
exhibit | +0.031 |
ement | +0.030 |
ths | +0.029 |
Neg logit contributions | |
burn | -0.024 |
ety | -0.020 |
groom | -0.020 |
y | -0.020 |
Woo | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
burn | +0.014 |
y | +0.013 |
ety | +0.012 |
Woo | +0.011 |
ot | +0.010 |
Neg logit contributions | |
quest | -0.031 |
site | -0.029 |
exhibit | -0.028 |
repairs | -0.028 |
ement | -0.027 |
Token | living |
Token ID | 2877 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
burn | +0.030 |
y | +0.029 |
ety | +0.028 |
Woo | +0.027 |
their | +0.027 |
Neg logit contributions | |
quest | -0.025 |
site | -0.022 |
ement | -0.021 |
exhibit | -0.021 |
lair | -0.020 |
Token | room |
Token ID | 2119 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
burn | +0.130 |
Woo | +0.119 |
y | +0.116 |
their | +0.116 |
ety | +0.114 |
Neg logit contributions | |
quest | -0.118 |
ement | -0.107 |
site | -0.106 |
ently | -0.100 |
exhibit | -0.099 |
Token | , |
Token ID | 11 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
their | +0.037 |
y | +0.033 |
her | +0.032 |
burn | +0.028 |
like | +0.027 |
Neg logit contributions | |
quest | -0.103 |
ement | -0.097 |
ths | -0.095 |
renches | -0.094 |
ently | -0.094 |
Token | where |
Token ID | 810 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
burn | +0.013 |
y | +0.012 |
Woo | +0.011 |
ety | +0.011 |
ot | +0.011 |
Neg logit contributions | |
quest | -0.015 |
site | -0.013 |
ement | -0.013 |
exhibit | -0.012 |
ths | -0.012 |
Token | their |
Token ID | 511 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
burn | +0.036 |
y | +0.033 |
Woo | +0.031 |
Qu | +0.030 |
La | +0.030 |
Neg logit contributions | |
quest | -0.055 |
site | -0.054 |
repairs | -0.052 |
ths | -0.051 |
exhibit | -0.049 |
Token | parents |
Token ID | 3397 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
burn | +0.013 |
their | +0.012 |
y | +0.012 |
Woo | +0.011 |
Sara | +0.011 |
Neg logit contributions | |
quest | -0.019 |
ement | -0.018 |
site | -0.017 |
ently | -0.017 |
ths | -0.016 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
quest | +0.016 |
ement | +0.016 |
site | +0.015 |
ently | +0.015 |
ths | +0.014 |
Neg logit contributions | |
burn | -0.010 |
y | -0.009 |
their | -0.009 |
Woo | -0.009 |
Sara | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
quest | +0.069 |
ement | +0.065 |
site | +0.063 |
ently | +0.062 |
ths | +0.061 |
Neg logit contributions | |
burn | -0.026 |
their | -0.022 |
y | -0.022 |
Woo | -0.022 |
ot | -0.020 |
Token | big |
Token ID | 1263 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
burn | +0.027 |
their | +0.025 |
ety | +0.024 |
Woo | +0.024 |
y | +0.024 |
Neg logit contributions | |
quest | -0.028 |
site | -0.024 |
boulder | -0.023 |
ement | -0.023 |
exhibit | -0.023 |
Token | ball |
Token ID | 2613 |
Feature activation | -3.84e-03 |
Pos logit contributions | |
quest | +0.012 |
ement | +0.010 |
site | +0.010 |
exhibit | +0.010 |
boulder | +0.009 |
Neg logit contributions | |
burn | -0.015 |
their | -0.013 |
ety | -0.013 |
y | -0.013 |
Woo | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
y | +0.000 |
burn | +0.000 |
their | +0.000 |
Woo | +0.000 |
her | +0.000 |
Neg logit contributions | |
quest | -0.000 |
ement | -0.000 |
ths | -0.000 |
ently | -0.000 |
renches | -0.000 |
Token | Sleep |
Token ID | 17376 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
burn | +0.004 |
Woo | +0.004 |
their | +0.004 |
C | +0.004 |
y | +0.004 |
Neg logit contributions | |
quest | -0.008 |
ement | -0.008 |
ths | -0.007 |
site | -0.007 |
ently | -0.007 |
Token | y |
Token ID | 88 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
burn | +0.103 |
groom | +0.088 |
Woo | +0.084 |
C | +0.075 |
Pop | +0.074 |
Neg logit contributions | |
quest | -0.157 |
ement | -0.142 |
site | -0.139 |
ently | -0.136 |
mission | -0.135 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
quest | +0.004 |
ement | +0.004 |
renches | +0.004 |
ently | +0.004 |
site | +0.004 |
Neg logit contributions | |
y | -0.002 |
burn | -0.002 |
their | -0.002 |
Woo | -0.002 |
her | -0.002 |
Token | balls |
Token ID | 11333 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
quest | +0.001 |
ement | +0.001 |
site | +0.001 |
ently | +0.001 |
ths | +0.001 |
Neg logit contributions | |
burn | -0.000 |
y | -0.000 |
their | -0.000 |
Woo | -0.000 |
ot | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
quest | +0.014 |
ement | +0.013 |
site | +0.013 |
ths | +0.012 |
ently | +0.012 |
Neg logit contributions | |
burn | -0.006 |
y | -0.006 |
their | -0.006 |
Woo | -0.006 |
her | -0.005 |
Token | He |
Token ID | 679 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
quest | +0.004 |
ement | +0.003 |
ths | +0.003 |
site | +0.003 |
ently | +0.003 |
Neg logit contributions | |
Woo | -0.002 |
C | -0.002 |
burn | -0.002 |
their | -0.002 |
Sara | -0.002 |
Token | L |
Token ID | 43 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
quest | +0.000 |
ement | +0.000 |
site | +0.000 |
ently | +0.000 |
ths | +0.000 |
Neg logit contributions | |
burn | -0.000 |
their | -0.000 |
y | -0.000 |
Woo | -0.000 |
groom | -0.000 |
Token | ily |
Token ID | 813 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
y | +0.021 |
burn | +0.020 |
her | +0.019 |
their | +0.019 |
Woo | +0.019 |
Neg logit contributions | |
quest | -0.055 |
site | -0.050 |
ement | -0.049 |
ths | -0.048 |
exhibit | -0.048 |
Token | went |
Token ID | 1816 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
y | +0.008 |
their | +0.007 |
her | +0.007 |
c | +0.007 |
ety | +0.006 |
Neg logit contributions | |
ement | -0.015 |
ently | -0.014 |
quest | -0.013 |
site | -0.013 |
ths | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ement | +0.043 |
quest | +0.042 |
ently | +0.040 |
ths | +0.040 |
site | +0.039 |
Neg logit contributions | |
their | -0.013 |
burn | -0.012 |
her | -0.011 |
Woo | -0.011 |
y | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
burn | +0.013 |
y | +0.010 |
their | +0.009 |
Woo | +0.009 |
ety | +0.008 |
Neg logit contributions | |
quest | -0.063 |
ement | -0.059 |
site | -0.058 |
ently | -0.057 |
exhibit | -0.057 |
Token | living |
Token ID | 2877 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
burn | +0.043 |
y | +0.042 |
ot | +0.040 |
their | +0.040 |
ety | +0.040 |
Neg logit contributions | |
quest | -0.028 |
site | -0.024 |
exhibit | -0.023 |
ement | -0.022 |
lair | -0.021 |
Token | room |
Token ID | 2119 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
burn | +0.117 |
their | +0.110 |
y | +0.109 |
Woo | +0.107 |
Sara | +0.103 |
Neg logit contributions | |
quest | -0.128 |
ement | -0.117 |
site | -0.112 |
ently | -0.110 |
ths | -0.108 |
Token | where |
Token ID | 810 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
their | +0.030 |
y | +0.029 |
her | +0.028 |
like | +0.025 |
burn | +0.022 |
Neg logit contributions | |
quest | -0.106 |
ement | -0.105 |
renches | -0.102 |
ths | -0.100 |
ently | -0.099 |
Token | she |
Token ID | 673 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
burn | +0.040 |
y | +0.035 |
ksh | +0.034 |
Woo | +0.033 |
Qu | +0.033 |
Neg logit contributions | |
quest | -0.059 |
site | -0.053 |
repairs | -0.053 |
ths | -0.052 |
ement | -0.051 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
y | +0.000 |
her | +0.000 |
c | +0.000 |
had | +0.000 |
ety | +0.000 |
Neg logit contributions | |
ement | -0.001 |
ently | -0.001 |
site | -0.001 |
attempts | -0.001 |
ths | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
quest | +0.083 |
ement | +0.079 |
site | +0.076 |
ently | +0.075 |
ths | +0.075 |
Neg logit contributions | |
burn | -0.021 |
their | -0.020 |
Woo | -0.017 |
her | -0.017 |
y | -0.017 |
Token | spray |
Token ID | 11662 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
quest | +0.043 |
ement | +0.042 |
ently | +0.042 |
ths | +0.040 |
site | +0.039 |
Neg logit contributions | |
burn | -0.028 |
their | -0.027 |
her | -0.024 |
Woo | -0.024 |
c | -0.023 |
Token | from |
Token ID | 422 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
quest | +0.026 |
ement | +0.024 |
site | +0.024 |
ently | +0.023 |
exhibit | +0.023 |
Neg logit contributions | |
burn | -0.019 |
Woo | -0.017 |
their | -0.017 |
y | -0.016 |
ety | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
quest | +0.008 |
ement | +0.007 |
site | +0.007 |
ently | +0.007 |
ths | +0.007 |
Neg logit contributions | |
burn | -0.002 |
y | -0.002 |
Woo | -0.002 |
their | -0.002 |
ety | -0.002 |
Token | nearby |
Token ID | 6716 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
quest | +0.004 |
site | +0.004 |
ement | +0.004 |
exhibit | +0.004 |
repairs | +0.004 |
Neg logit contributions | |
burn | -0.004 |
y | -0.004 |
Woo | -0.004 |
their | -0.004 |
ety | -0.004 |
Token | fire |
Token ID | 2046 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
quest | +0.012 |
ement | +0.010 |
site | +0.010 |
ently | +0.009 |
exhibit | +0.009 |
Neg logit contributions | |
burn | -0.016 |
their | -0.015 |
y | -0.015 |
Woo | -0.015 |
ety | -0.014 |
Token | hyd |
Token ID | 7409 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
burn | +0.014 |
y | +0.012 |
their | +0.012 |
Woo | +0.012 |
C | +0.011 |
Neg logit contributions | |
quest | -0.023 |
ement | -0.022 |
site | -0.021 |
ently | -0.021 |
ths | -0.020 |
Token | rant |
Token ID | 5250 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
burn | +0.105 |
Woo | +0.100 |
Sara | +0.096 |
their | +0.095 |
groom | +0.094 |
Neg logit contributions | |
quest | -0.138 |
ently | -0.131 |
site | -0.130 |
ement | -0.130 |
ths | -0.119 |
Token | to |
Token ID | 284 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
burn | +0.016 |
their | +0.015 |
Woo | +0.015 |
y | +0.015 |
ety | +0.014 |
Neg logit contributions | |
quest | -0.025 |
ement | -0.023 |
site | -0.023 |
ently | -0.022 |
ths | -0.022 |
Token | keep |
Token ID | 1394 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
burn | +0.009 |
y | +0.008 |
Woo | +0.008 |
ety | +0.007 |
their | +0.007 |
Neg logit contributions | |
quest | -0.015 |
site | -0.013 |
ement | -0.013 |
exhibit | -0.013 |
ently | -0.013 |
Token | her |
Token ID | 607 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
burn | +0.018 |
y | +0.016 |
Woo | +0.016 |
ety | +0.015 |
groom | +0.015 |
Neg logit contributions | |
quest | -0.036 |
ement | -0.034 |
site | -0.033 |
ently | -0.033 |
ths | -0.033 |
Token | dry |
Token ID | 5894 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
quest | +0.018 |
ement | +0.017 |
site | +0.017 |
ently | +0.016 |
ths | +0.016 |
Neg logit contributions | |
burn | -0.010 |
their | -0.009 |
y | -0.009 |
Woo | -0.009 |
ot | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
burn | +0.020 |
their | +0.018 |
y | +0.018 |
Woo | +0.018 |
Sara | +0.017 |
Neg logit contributions | |
quest | -0.037 |
ement | -0.035 |
site | -0.034 |
ently | -0.033 |
ths | -0.033 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -8.65e-02 |
Pos logit contributions | |
burn | +0.007 |
y | +0.007 |
their | +0.006 |
Woo | +0.006 |
ot | +0.006 |
Neg logit contributions | |
quest | -0.014 |
ement | -0.013 |
site | -0.013 |
ently | -0.013 |
exhibit | -0.012 |
Token | went |
Token ID | 1816 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
burn | +0.002 |
Woo | +0.002 |
their | +0.002 |
y | +0.002 |
C | +0.002 |
Neg logit contributions | |
quest | -0.003 |
ement | -0.002 |
site | -0.002 |
ths | -0.002 |
exhibit | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
quest | +0.026 |
site | +0.024 |
ement | +0.023 |
exhibit | +0.023 |
ently | +0.023 |
Neg logit contributions | |
burn | -0.015 |
y | -0.013 |
Woo | -0.013 |
their | -0.013 |
ety | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
burn | +0.025 |
y | +0.024 |
ety | +0.021 |
Woo | +0.020 |
ot | +0.019 |
Neg logit contributions | |
quest | -0.048 |
site | -0.043 |
exhibit | -0.042 |
ement | -0.042 |
repairs | -0.042 |
Token | living |
Token ID | 2877 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
y | +0.040 |
burn | +0.040 |
ety | +0.038 |
ot | +0.038 |
free | +0.037 |
Neg logit contributions | |
quest | -0.026 |
site | -0.022 |
exhibit | -0.021 |
lair | -0.020 |
ement | -0.020 |
Token | room |
Token ID | 2119 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
burn | +0.131 |
Woo | +0.121 |
y | +0.118 |
their | +0.117 |
ety | +0.116 |
Neg logit contributions | |
quest | -0.113 |
ement | -0.102 |
site | -0.101 |
ently | -0.095 |
exhibit | -0.095 |
Token | and |
Token ID | 290 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
their | +0.037 |
y | +0.036 |
burn | +0.035 |
her | +0.034 |
Sara | +0.031 |
Neg logit contributions | |
quest | -0.099 |
ement | -0.095 |
renches | -0.091 |
ently | -0.090 |
ths | -0.090 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
burn | +0.022 |
y | +0.020 |
Woo | +0.019 |
C | +0.019 |
S | +0.018 |
Neg logit contributions | |
quest | -0.021 |
exhibit | -0.018 |
site | -0.018 |
ths | -0.017 |
trek | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
quest | +0.075 |
ement | +0.071 |
site | +0.069 |
ently | +0.068 |
ths | +0.068 |
Neg logit contributions | |
burn | -0.024 |
y | -0.021 |
their | -0.020 |
Woo | -0.020 |
ety | -0.018 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
burn | +0.017 |
their | +0.016 |
y | +0.016 |
Woo | +0.016 |
ot | +0.015 |
Neg logit contributions | |
quest | -0.023 |
ement | -0.021 |
site | -0.020 |
ently | -0.020 |
ths | -0.020 |
Token | dog |
Token ID | 3290 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
quest | +0.008 |
ement | +0.007 |
exhibit | +0.007 |
site | +0.007 |
mountain | +0.007 |
Neg logit contributions | |
burn | -0.007 |
their | -0.006 |
La | -0.006 |
Woo | -0.006 |
Lara | -0.006 |
Token | named |
Token ID | 3706 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
burn | +0.016 |
their | +0.015 |
y | +0.014 |
Woo | +0.014 |
groom | +0.014 |
Neg logit contributions | |
quest | -0.019 |
ement | -0.017 |
site | -0.017 |
exhibit | -0.016 |
ently | -0.016 |
Token | Sleep |
Token ID | 17376 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
burn | +0.034 |
groom | +0.033 |
y | +0.033 |
band | +0.030 |
flower | +0.030 |
Neg logit contributions | |
quest | -0.044 |
exhibit | -0.039 |
site | -0.037 |
scaven | -0.037 |
repairs | -0.037 |
Token | y |
Token ID | 88 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
burn | +0.112 |
groom | +0.096 |
Woo | +0.089 |
Lara | +0.088 |
inas | +0.085 |
Neg logit contributions | |
quest | -0.140 |
mission | -0.120 |
exhibit | -0.119 |
site | -0.118 |
ement | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
quest | +0.003 |
ement | +0.002 |
site | +0.002 |
exhibit | +0.002 |
ently | +0.002 |
Neg logit contributions | |
burn | -0.002 |
their | -0.002 |
Woo | -0.002 |
ety | -0.002 |
y | -0.002 |
Token | Sleep |
Token ID | 17376 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
quest | +0.015 |
ement | +0.014 |
site | +0.013 |
exhibit | +0.013 |
repairs | +0.013 |
Neg logit contributions | |
burn | -0.008 |
y | -0.008 |
a | -0.008 |
ety | -0.008 |
ot | -0.008 |
Token | y |
Token ID | 88 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
burn | +0.115 |
groom | +0.101 |
Woo | +0.091 |
Lara | +0.087 |
Pop | +0.084 |
Neg logit contributions | |
quest | -0.134 |
ement | -0.117 |
mission | -0.117 |
site | -0.117 |
ently | -0.116 |
Token | was |
Token ID | 373 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
quest | +0.013 |
ement | +0.011 |
site | +0.011 |
exhibit | +0.011 |
ently | +0.011 |
Neg logit contributions | |
burn | -0.011 |
their | -0.009 |
Woo | -0.009 |
ety | -0.009 |
y | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
burn | +0.001 |
ety | +0.001 |
rav | +0.001 |
y | +0.001 |
ana | +0.001 |
Neg logit contributions | |
quest | -0.001 |
ement | -0.001 |
burying | -0.001 |
scaven | -0.001 |
exploration | -0.001 |
Token | very |
Token ID | 845 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
burn | +0.018 |
ety | +0.017 |
inas | +0.016 |
asc | +0.016 |
uzz | +0.016 |
Neg logit contributions | |
quest | -0.020 |
mission | -0.017 |
mountain | -0.016 |
cave | -0.016 |
journey | -0.016 |
Token | sleepy |
Token ID | 42023 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
burn | +0.039 |
y | +0.032 |
ety | +0.031 |
flower | +0.030 |
Woo | +0.030 |
Neg logit contributions | |
quest | -0.053 |
mission | -0.044 |
ement | -0.044 |
site | -0.043 |
exhibit | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
quest | +0.003 |
ement | +0.003 |
site | +0.003 |
ently | +0.003 |
ths | +0.003 |
Neg logit contributions | |
burn | -0.001 |
their | -0.001 |
y | -0.001 |
Woo | -0.001 |
Sara | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
burn | +0.003 |
y | +0.002 |
Woo | +0.002 |
ety | +0.002 |
ot | +0.002 |
Neg logit contributions | |
quest | -0.006 |
site | -0.006 |
ths | -0.006 |
ement | -0.006 |
exhibit | -0.005 |
Token | lightning |
Token ID | 14357 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
quest | +0.013 |
ement | +0.012 |
ently | +0.011 |
ths | +0.011 |
exhibit | +0.011 |
Neg logit contributions | |
their | -0.008 |
burn | -0.008 |
y | -0.007 |
Sara | -0.007 |
Woo | -0.007 |
Token | struck |
Token ID | 7425 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
quest | +0.032 |
ement | +0.030 |
ently | +0.029 |
site | +0.028 |
exhibit | +0.028 |
Neg logit contributions | |
burn | -0.018 |
y | -0.017 |
their | -0.017 |
ot | -0.015 |
Woo | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
burn | +0.006 |
Woo | +0.005 |
groom | +0.005 |
ety | +0.005 |
y | +0.005 |
Neg logit contributions | |
quest | -0.011 |
site | -0.011 |
ement | -0.011 |
ently | -0.010 |
ths | -0.010 |
Token | hyd |
Token ID | 7409 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
burn | +0.010 |
their | +0.010 |
y | +0.010 |
Woo | +0.009 |
Sara | +0.009 |
Neg logit contributions | |
quest | -0.012 |
ement | -0.012 |
ently | -0.011 |
ths | -0.011 |
site | -0.010 |
Token | rant |
Token ID | 5250 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
burn | +0.101 |
Woo | +0.097 |
their | +0.089 |
Sara | +0.089 |
her | +0.088 |
Neg logit contributions | |
quest | -0.143 |
site | -0.138 |
ement | -0.137 |
ently | -0.131 |
exhibit | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
burn | +0.028 |
their | +0.025 |
Woo | +0.025 |
y | +0.025 |
ety | +0.024 |
Neg logit contributions | |
quest | -0.042 |
ement | -0.039 |
site | -0.037 |
ently | -0.036 |
exhibit | -0.036 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
burn | +0.006 |
their | +0.006 |
Woo | +0.006 |
Sara | +0.006 |
y | +0.006 |
Neg logit contributions | |
quest | -0.015 |
ement | -0.014 |
ently | -0.014 |
ths | -0.014 |
site | -0.014 |
Token | water |
Token ID | 1660 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
quest | +0.069 |
ement | +0.064 |
site | +0.061 |
ently | +0.060 |
ths | +0.059 |
Neg logit contributions | |
burn | -0.047 |
their | -0.044 |
y | -0.043 |
Woo | -0.042 |
Sara | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
burn | +0.028 |
their | +0.025 |
y | +0.025 |
Woo | +0.025 |
ety | +0.023 |
Neg logit contributions | |
quest | -0.045 |
ement | -0.042 |
site | -0.041 |
ently | -0.040 |
ths | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
quest | +0.038 |
ement | +0.036 |
site | +0.035 |
ently | +0.034 |
ths | +0.034 |
Neg logit contributions | |
burn | -0.021 |
their | -0.019 |
y | -0.019 |
Woo | -0.018 |
Sara | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
quest | +0.007 |
ement | +0.006 |
site | +0.006 |
ently | +0.006 |
ths | +0.006 |
Neg logit contributions | |
burn | -0.004 |
y | -0.003 |
their | -0.003 |
Woo | -0.003 |
ot | -0.003 |
Token | ran |
Token ID | 4966 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
quest | +0.011 |
ement | +0.011 |
ently | +0.010 |
site | +0.010 |
exhibit | +0.010 |
Neg logit contributions | |
y | -0.005 |
their | -0.005 |
Sara | -0.005 |
her | -0.005 |
burn | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
quest | +0.032 |
site | +0.029 |
ement | +0.029 |
exhibit | +0.029 |
ths | +0.028 |
Neg logit contributions | |
burn | -0.019 |
y | -0.016 |
Woo | -0.015 |
their | -0.015 |
groom | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
burn | +0.013 |
y | +0.011 |
their | +0.011 |
Woo | +0.011 |
ety | +0.009 |
Neg logit contributions | |
quest | -0.043 |
ement | -0.041 |
site | -0.040 |
ently | -0.039 |
exhibit | -0.039 |
Token | living |
Token ID | 2877 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
burn | +0.035 |
y | +0.032 |
Woo | +0.032 |
their | +0.031 |
ety | +0.031 |
Neg logit contributions | |
quest | -0.031 |
site | -0.027 |
ement | -0.027 |
exhibit | -0.026 |
ently | -0.025 |
Token | room |
Token ID | 2119 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
burn | +0.122 |
their | +0.112 |
Woo | +0.112 |
y | +0.111 |
ety | +0.106 |
Neg logit contributions | |
quest | -0.122 |
ement | -0.112 |
site | -0.108 |
ently | -0.105 |
ths | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
their | +0.040 |
y | +0.039 |
her | +0.038 |
burn | +0.036 |
Sara | +0.035 |
Neg logit contributions | |
quest | -0.096 |
ement | -0.089 |
renches | -0.087 |
ths | -0.086 |
ently | -0.086 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
burn | +0.013 |
y | +0.012 |
their | +0.012 |
Woo | +0.012 |
ot | +0.011 |
Neg logit contributions | |
quest | -0.016 |
ement | -0.015 |
site | -0.014 |
ently | -0.014 |
ths | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
quest | +0.085 |
ement | +0.080 |
site | +0.078 |
ently | +0.077 |
ths | +0.076 |
Neg logit contributions | |
burn | -0.026 |
their | -0.025 |
Woo | -0.023 |
y | -0.022 |
Sara | -0.021 |
Token | couch |
Token ID | 18507 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
burn | +0.009 |
their | +0.008 |
y | +0.008 |
Woo | +0.008 |
Sara | +0.008 |
Neg logit contributions | |
quest | -0.012 |
ement | -0.011 |
site | -0.010 |
ently | -0.010 |
ths | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
quest | +0.017 |
ement | +0.015 |
site | +0.015 |
ths | +0.015 |
ently | +0.015 |
Neg logit contributions | |
burn | -0.008 |
their | -0.008 |
y | -0.008 |
Woo | -0.008 |
Sara | -0.007 |
Token | She |
Token ID | 3347 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
quest | +0.009 |
ths | +0.009 |
ement | +0.009 |
site | +0.009 |
ently | +0.009 |
Neg logit contributions | |
burn | -0.007 |
Woo | -0.006 |
groom | -0.005 |
y | -0.005 |
their | -0.005 |
Token | walked |
Token ID | 6807 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
quest | +0.005 |
ement | +0.005 |
site | +0.005 |
ently | +0.005 |
ths | +0.005 |
Neg logit contributions | |
burn | -0.004 |
their | -0.003 |
y | -0.003 |
Woo | -0.003 |
C | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
quest | +0.060 |
site | +0.056 |
exhibit | +0.054 |
ement | +0.052 |
ently | +0.051 |
Neg logit contributions | |
burn | -0.050 |
Woo | -0.042 |
ety | -0.041 |
groom | -0.039 |
C | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
burn | +0.018 |
y | +0.016 |
ety | +0.014 |
free | +0.013 |
Woo | +0.013 |
Neg logit contributions | |
quest | -0.036 |
site | -0.033 |
exhibit | -0.033 |
ement | -0.033 |
repairs | -0.032 |
Token | living |
Token ID | 2877 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
burn | +0.034 |
their | +0.032 |
y | +0.031 |
Woo | +0.031 |
Sara | +0.029 |
Neg logit contributions | |
quest | -0.035 |
ement | -0.033 |
site | -0.031 |
ently | -0.031 |
ths | -0.030 |
Token | room |
Token ID | 2119 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
burn | +0.116 |
their | +0.109 |
y | +0.108 |
Woo | +0.105 |
Sara | +0.101 |
Neg logit contributions | |
quest | -0.127 |
ement | -0.117 |
site | -0.111 |
ently | -0.109 |
ths | -0.108 |
Token | and |
Token ID | 290 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
their | +0.036 |
y | +0.034 |
her | +0.032 |
burn | +0.030 |
Sara | +0.029 |
Neg logit contributions | |
quest | -0.094 |
ement | -0.088 |
renches | -0.086 |
ths | -0.086 |
ently | -0.084 |
Token | said |
Token ID | 531 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
burn | +0.016 |
y | +0.013 |
Woo | +0.013 |
free | +0.013 |
ot | +0.013 |
Neg logit contributions | |
quest | -0.016 |
site | -0.014 |
exhibit | -0.014 |
ths | -0.013 |
ement | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ement | +0.024 |
quest | +0.023 |
ently | +0.022 |
site | +0.021 |
ued | +0.020 |
Neg logit contributions | |
burn | -0.041 |
ety | -0.038 |
ksh | -0.035 |
y | -0.035 |
flower | -0.034 |
Token | " |
Token ID | 366 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
burn | +0.004 |
y | +0.003 |
ety | +0.003 |
Woo | +0.003 |
groom | +0.003 |
Neg logit contributions | |
quest | -0.004 |
ement | -0.004 |
site | -0.004 |
ently | -0.004 |
ths | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
quest | +0.006 |
ement | +0.005 |
site | +0.005 |
ently | +0.005 |
ths | +0.005 |
Neg logit contributions | |
burn | -0.003 |
their | -0.003 |
y | -0.003 |
Woo | -0.003 |
her | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
Sara | +0.005 |
their | +0.005 |
C | +0.005 |
Lily | +0.004 |
Woo | +0.004 |
Neg logit contributions | |
quest | -0.013 |
ement | -0.012 |
ently | -0.012 |
ths | -0.012 |
lair | -0.012 |
Token | ran |
Token ID | 4966 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
burn | +0.002 |
y | +0.002 |
their | +0.002 |
Woo | +0.001 |
ot | +0.001 |
Neg logit contributions | |
quest | -0.003 |
ement | -0.003 |
site | -0.003 |
ently | -0.002 |
ths | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
quest | +0.031 |
site | +0.028 |
ement | +0.028 |
exhibit | +0.027 |
ths | +0.027 |
Neg logit contributions | |
burn | -0.016 |
y | -0.014 |
Woo | -0.013 |
their | -0.013 |
groom | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
their | +0.019 |
her | +0.016 |
Sara | +0.016 |
burn | +0.015 |
Woo | +0.014 |
Neg logit contributions | |
ement | -0.058 |
quest | -0.057 |
ths | -0.054 |
ently | -0.054 |
renches | -0.052 |
Token | living |
Token ID | 2877 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
burn | +0.040 |
y | +0.038 |
their | +0.037 |
Woo | +0.037 |
ety | +0.036 |
Neg logit contributions | |
quest | -0.029 |
site | -0.026 |
exhibit | -0.025 |
ement | -0.024 |
lair | -0.023 |
Token | room |
Token ID | 2119 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
burn | +0.107 |
their | +0.105 |
y | +0.103 |
Woo | +0.097 |
Sara | +0.096 |
Neg logit contributions | |
quest | -0.133 |
ement | -0.123 |
ently | -0.116 |
ths | -0.114 |
site | -0.114 |
Token | and |
Token ID | 290 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
their | +0.038 |
y | +0.036 |
her | +0.033 |
burn | +0.031 |
ful | +0.029 |
Neg logit contributions | |
quest | -0.108 |
ement | -0.103 |
renches | -0.101 |
ths | -0.100 |
ently | -0.099 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
burn | +0.017 |
their | +0.016 |
y | +0.016 |
Woo | +0.015 |
ot | +0.015 |
Neg logit contributions | |
quest | -0.022 |
ement | -0.020 |
site | -0.020 |
ently | -0.019 |
ths | -0.019 |
Token | his |
Token ID | 465 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
quest | +0.074 |
ement | +0.069 |
ently | +0.067 |
ths | +0.065 |
site | +0.065 |
Neg logit contributions | |
their | -0.025 |
burn | -0.022 |
her | -0.021 |
Woo | -0.021 |
Sara | -0.021 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
burn | +0.003 |
their | +0.003 |
Sara | +0.003 |
y | +0.003 |
her | +0.003 |
Neg logit contributions | |
quest | -0.005 |
ently | -0.005 |
ement | -0.005 |
ths | -0.005 |
site | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
quest | +0.003 |
ement | +0.003 |
site | +0.003 |
ently | +0.002 |
ths | +0.002 |
Neg logit contributions | |
burn | -0.002 |
their | -0.002 |
y | -0.002 |
Woo | -0.002 |
Sara | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
burn | +0.004 |
y | +0.003 |
their | +0.003 |
Woo | +0.003 |
ety | +0.003 |
Neg logit contributions | |
quest | -0.007 |
ement | -0.007 |
site | -0.006 |
ently | -0.006 |
ths | -0.006 |
Token | walked |
Token ID | 6807 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ement | +0.026 |
quest | +0.025 |
site | +0.024 |
ently | +0.024 |
renches | +0.024 |
Neg logit contributions | |
y | -0.011 |
their | -0.011 |
burn | -0.010 |
c | -0.010 |
her | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
quest | +0.054 |
site | +0.048 |
ement | +0.048 |
exhibit | +0.046 |
ently | +0.046 |
Neg logit contributions | |
burn | -0.036 |
Woo | -0.031 |
ety | -0.030 |
y | -0.029 |
groom | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
burn | +0.017 |
their | +0.016 |
Woo | +0.015 |
y | +0.014 |
Sara | +0.014 |
Neg logit contributions | |
quest | -0.063 |
ement | -0.061 |
site | -0.059 |
ently | -0.058 |
ths | -0.058 |
Token | living |
Token ID | 2877 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
burn | +0.033 |
their | +0.032 |
y | +0.031 |
Woo | +0.030 |
Sara | +0.029 |
Neg logit contributions | |
quest | -0.034 |
ement | -0.032 |
ently | -0.030 |
site | -0.030 |
ths | -0.030 |
Token | room |
Token ID | 2119 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
burn | +0.108 |
their | +0.106 |
y | +0.104 |
Woo | +0.098 |
Sara | +0.097 |
Neg logit contributions | |
quest | -0.131 |
ement | -0.121 |
site | -0.114 |
ently | -0.114 |
ths | -0.113 |
Token | and |
Token ID | 290 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
their | +0.038 |
y | +0.037 |
her | +0.034 |
burn | +0.032 |
Sara | +0.031 |
Neg logit contributions | |
quest | -0.094 |
ement | -0.088 |
renches | -0.087 |
ths | -0.086 |
ently | -0.085 |
Token | said |
Token ID | 531 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
burn | +0.012 |
their | +0.011 |
y | +0.011 |
Woo | +0.011 |
Sara | +0.010 |
Neg logit contributions | |
quest | -0.016 |
ement | -0.014 |
site | -0.014 |
ently | -0.014 |
ths | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
quest | +0.024 |
ement | +0.022 |
ently | +0.021 |
site | +0.021 |
ths | +0.020 |
Neg logit contributions | |
burn | -0.025 |
ety | -0.023 |
y | -0.022 |
Woo | -0.021 |
their | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
burn | +0.006 |
y | +0.005 |
Woo | +0.005 |
their | +0.005 |
ety | +0.005 |
Neg logit contributions | |
quest | -0.009 |
ement | -0.009 |
site | -0.008 |
ently | -0.008 |
ths | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
burn | +0.010 |
y | +0.009 |
their | +0.008 |
groom | +0.008 |
Woo | +0.008 |
Neg logit contributions | |
quest | -0.018 |
ement | -0.017 |
site | -0.017 |
ently | -0.016 |
exhibit | -0.016 |
Token | car |
Token ID | 1097 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
burn | +0.011 |
their | +0.011 |
Woo | +0.010 |
C | +0.010 |
Sara | +0.010 |
Neg logit contributions | |
quest | -0.014 |
ement | -0.013 |
ently | -0.013 |
ths | -0.012 |
site | -0.012 |
Token | hits |
Token ID | 7127 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
their | +0.003 |
y | +0.003 |
burn | +0.003 |
her | +0.003 |
Sara | +0.003 |
Neg logit contributions | |
quest | -0.007 |
ement | -0.007 |
ently | -0.006 |
ths | -0.006 |
site | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
burn | +0.001 |
groom | +0.001 |
ety | +0.001 |
y | +0.001 |
Woo | +0.001 |
Neg logit contributions | |
site | -0.002 |
quest | -0.002 |
ement | -0.002 |
ently | -0.002 |
exhibit | -0.002 |
Token | fire |
Token ID | 2046 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
burn | +0.050 |
Woo | +0.046 |
their | +0.045 |
ety | +0.045 |
y | +0.045 |
Neg logit contributions | |
quest | -0.043 |
site | -0.038 |
ement | -0.037 |
exhibit | -0.035 |
boulder | -0.034 |
Token | hyd |
Token ID | 7409 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
burn | +0.037 |
their | +0.034 |
y | +0.033 |
Woo | +0.033 |
Sara | +0.031 |
Neg logit contributions | |
quest | -0.050 |
ement | -0.046 |
site | -0.044 |
ently | -0.043 |
ths | -0.043 |
Token | rant |
Token ID | 5250 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
burn | +0.105 |
Woo | +0.102 |
groom | +0.097 |
Sara | +0.095 |
their | +0.094 |
Neg logit contributions | |
quest | -0.131 |
site | -0.127 |
ently | -0.124 |
ement | -0.123 |
renches | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
burn | +0.023 |
their | +0.020 |
y | +0.020 |
Woo | +0.020 |
ety | +0.019 |
Neg logit contributions | |
quest | -0.039 |
ement | -0.036 |
site | -0.035 |
ently | -0.034 |
ths | -0.034 |
Token | The |
Token ID | 383 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
burn | +0.010 |
y | +0.009 |
their | +0.008 |
Woo | +0.008 |
ety | +0.008 |
Neg logit contributions | |
quest | -0.017 |
ement | -0.016 |
site | -0.016 |
ently | -0.016 |
exhibit | -0.015 |
Token | fire |
Token ID | 2046 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
burn | +0.010 |
their | +0.009 |
Woo | +0.009 |
y | +0.009 |
Sara | +0.008 |
Neg logit contributions | |
quest | -0.011 |
ement | -0.010 |
ently | -0.009 |
ths | -0.009 |
site | -0.009 |
Token | hyd |
Token ID | 7409 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
burn | +0.011 |
their | +0.010 |
y | +0.010 |
Woo | +0.009 |
ot | +0.009 |
Neg logit contributions | |
quest | -0.017 |
ement | -0.015 |
ently | -0.015 |
site | -0.014 |
ths | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
quest | +0.011 |
ement | +0.010 |
site | +0.010 |
ths | +0.009 |
ently | +0.009 |
Neg logit contributions | |
burn | -0.005 |
their | -0.005 |
Woo | -0.004 |
y | -0.004 |
Sara | -0.004 |
Token | He |
Token ID | 1544 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
quest | +0.005 |
ement | +0.004 |
site | +0.004 |
ently | +0.004 |
ths | +0.004 |
Neg logit contributions | |
burn | -0.003 |
y | -0.003 |
their | -0.003 |
Woo | -0.003 |
ety | -0.003 |
Token | went |
Token ID | 1816 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ement | +0.029 |
quest | +0.029 |
ently | +0.028 |
site | +0.027 |
renches | +0.027 |
Neg logit contributions | |
y | -0.013 |
their | -0.013 |
her | -0.012 |
c | -0.012 |
burn | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
quest | +0.048 |
ement | +0.045 |
site | +0.043 |
ently | +0.043 |
ths | +0.042 |
Neg logit contributions | |
burn | -0.019 |
their | -0.016 |
y | -0.016 |
Woo | -0.016 |
Sara | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
their | +0.019 |
her | +0.017 |
Sara | +0.015 |
your | +0.014 |
burn | +0.014 |
Neg logit contributions | |
ement | -0.061 |
quest | -0.060 |
ths | -0.058 |
ently | -0.058 |
renches | -0.055 |
Token | living |
Token ID | 2877 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
burn | +0.043 |
their | +0.041 |
y | +0.040 |
Woo | +0.040 |
C | +0.038 |
Neg logit contributions | |
quest | -0.038 |
ement | -0.035 |
site | -0.033 |
ently | -0.033 |
ths | -0.032 |
Token | room |
Token ID | 2119 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
burn | +0.110 |
their | +0.106 |
y | +0.105 |
Woo | +0.100 |
Sara | +0.098 |
Neg logit contributions | |
quest | -0.130 |
ement | -0.119 |
site | -0.112 |
ently | -0.112 |
ths | -0.110 |
Token | , |
Token ID | 11 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
their | +0.035 |
y | +0.034 |
her | +0.032 |
burn | +0.028 |
like | +0.028 |
Neg logit contributions | |
quest | -0.102 |
ement | -0.099 |
renches | -0.097 |
ths | -0.096 |
ently | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
burn | +0.008 |
their | +0.008 |
y | +0.008 |
Woo | +0.007 |
her | +0.007 |
Neg logit contributions | |
quest | -0.012 |
ement | -0.011 |
ently | -0.011 |
site | -0.011 |
ths | -0.010 |
Token | noticed |
Token ID | 6810 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
burn | +0.019 |
their | +0.019 |
y | +0.018 |
Woo | +0.018 |
her | +0.018 |
Neg logit contributions | |
quest | -0.029 |
ement | -0.028 |
ently | -0.026 |
site | -0.026 |
ths | -0.025 |
Token | that |
Token ID | 326 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
quest | +0.053 |
ement | +0.048 |
ently | +0.047 |
site | +0.046 |
ths | +0.046 |
Neg logit contributions | |
their | -0.025 |
burn | -0.024 |
Woo | -0.023 |
her | -0.023 |
Sara | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
quest | +0.008 |
ement | +0.007 |
ths | +0.007 |
site | +0.007 |
ently | +0.007 |
Neg logit contributions | |
their | -0.003 |
burn | -0.003 |
y | -0.003 |
Woo | -0.003 |
Sara | -0.003 |
Token | They |
Token ID | 2990 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
burn | +0.001 |
their | +0.001 |
y | +0.001 |
Woo | +0.001 |
Sara | +0.001 |
Neg logit contributions | |
quest | -0.002 |
ement | -0.002 |
site | -0.002 |
ently | -0.002 |
ths | -0.002 |
Token | went |
Token ID | 1816 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
their | +0.010 |
burn | +0.010 |
y | +0.009 |
her | +0.009 |
ot | +0.009 |
Neg logit contributions | |
quest | -0.014 |
ement | -0.014 |
site | -0.013 |
ently | -0.013 |
lair | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
quest | +0.043 |
ement | +0.040 |
site | +0.039 |
ently | +0.038 |
ths | +0.038 |
Neg logit contributions | |
burn | -0.026 |
their | -0.024 |
y | -0.024 |
Woo | -0.024 |
Sara | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
burn | +0.017 |
y | +0.016 |
ety | +0.013 |
Woo | +0.013 |
groom | +0.012 |
Neg logit contributions | |
quest | -0.038 |
site | -0.035 |
exhibit | -0.034 |
repairs | -0.034 |
ement | -0.033 |
Token | living |
Token ID | 2877 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
burn | +0.049 |
y | +0.048 |
their | +0.045 |
Woo | +0.045 |
ot | +0.044 |
Neg logit contributions | |
quest | -0.028 |
site | -0.025 |
exhibit | -0.023 |
repairs | -0.022 |
lair | -0.022 |
Token | room |
Token ID | 2119 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
burn | +0.112 |
their | +0.107 |
y | +0.105 |
Woo | +0.102 |
Sara | +0.099 |
Neg logit contributions | |
quest | -0.128 |
ement | -0.118 |
site | -0.111 |
ently | -0.110 |
ths | -0.108 |
Token | and |
Token ID | 290 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
their | +0.032 |
her | +0.027 |
y | +0.027 |
like | +0.023 |
burn | +0.022 |
Neg logit contributions | |
quest | -0.101 |
ement | -0.096 |
renches | -0.093 |
ths | -0.093 |
ently | -0.093 |
Token | played |
Token ID | 2826 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
burn | +0.008 |
y | +0.007 |
Woo | +0.007 |
groom | +0.007 |
S | +0.007 |
Neg logit contributions | |
quest | -0.009 |
exhibit | -0.008 |
site | -0.008 |
ths | -0.008 |
trek | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
quest | +0.045 |
ement | +0.043 |
ths | +0.041 |
ently | +0.040 |
site | +0.039 |
Neg logit contributions | |
their | -0.023 |
burn | -0.021 |
her | -0.020 |
Woo | -0.020 |
Sara | -0.019 |
Token | game |
Token ID | 983 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
burn | +0.043 |
their | +0.039 |
y | +0.039 |
Woo | +0.039 |
ety | +0.037 |
Neg logit contributions | |
quest | -0.045 |
ement | -0.041 |
site | -0.040 |
ently | -0.039 |
ths | -0.038 |
Token | " |
Token ID | 1 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
quest | +0.027 |
site | +0.025 |
ement | +0.025 |
ths | +0.024 |
ently | +0.024 |
Neg logit contributions | |
burn | -0.016 |
y | -0.013 |
Woo | -0.013 |
ety | -0.012 |
groom | -0.012 |
Token | Ben |
Token ID | 11696 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
burn | +0.020 |
y | +0.018 |
their | +0.017 |
Woo | +0.017 |
ot | +0.017 |
Neg logit contributions | |
quest | -0.031 |
site | -0.029 |
ement | -0.029 |
ths | -0.029 |
ently | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
quest | +0.025 |
ement | +0.023 |
site | +0.022 |
ently | +0.021 |
ths | +0.021 |
Neg logit contributions | |
burn | -0.019 |
their | -0.017 |
y | -0.017 |
Woo | -0.017 |
ot | -0.016 |
Token | look |
Token ID | 804 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
quest | +0.015 |
ement | +0.013 |
site | +0.013 |
ently | +0.013 |
ths | +0.013 |
Neg logit contributions | |
burn | -0.008 |
y | -0.007 |
their | -0.007 |
Woo | -0.007 |
ety | -0.006 |
Token | ! |
Token ID | 0 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
their | +0.002 |
burn | +0.002 |
y | +0.002 |
Woo | +0.002 |
Sara | +0.002 |
Neg logit contributions | |
quest | -0.003 |
ement | -0.003 |
site | -0.003 |
ently | -0.003 |
ths | -0.003 |
Token | There |
Token ID | 1318 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
quest | +0.052 |
exhibit | +0.048 |
ement | +0.048 |
site | +0.047 |
ently | +0.045 |
Neg logit contributions | |
burn | -0.043 |
their | -0.038 |
y | -0.038 |
groom | -0.036 |
Woo | -0.035 |
Token | is |
Token ID | 318 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
quest | +0.130 |
ement | +0.123 |
ently | +0.118 |
ths | +0.118 |
site | +0.117 |
Neg logit contributions | |
their | -0.046 |
y | -0.043 |
burn | -0.043 |
your | -0.039 |
our | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
their | +0.004 |
burn | +0.004 |
Woo | +0.004 |
Sara | +0.004 |
y | +0.004 |
Neg logit contributions | |
quest | -0.011 |
ement | -0.010 |
ently | -0.010 |
ths | -0.010 |
site | -0.010 |
Token | window |
Token ID | 4324 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
quest | +0.012 |
site | +0.011 |
ement | +0.010 |
exhibit | +0.010 |
lair | +0.010 |
Neg logit contributions | |
burn | -0.014 |
y | -0.013 |
Woo | -0.013 |
their | -0.013 |
ety | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
quest | +0.006 |
ement | +0.006 |
site | +0.005 |
ently | +0.005 |
exhibit | +0.005 |
Neg logit contributions | |
burn | -0.005 |
Woo | -0.004 |
their | -0.004 |
y | -0.004 |
ety | -0.004 |
Token | We |
Token ID | 775 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
quest | +0.031 |
ement | +0.028 |
site | +0.028 |
exhibit | +0.027 |
ently | +0.026 |
Neg logit contributions | |
burn | -0.030 |
y | -0.028 |
their | -0.027 |
Woo | -0.026 |
groom | -0.026 |
Token | black |
Token ID | 2042 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
burn | +0.034 |
free | +0.031 |
rav | +0.031 |
y | +0.030 |
groom | +0.030 |
Neg logit contributions | |
quest | -0.039 |
site | -0.035 |
lair | -0.035 |
attempts | -0.033 |
burying | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
quest | +0.095 |
ement | +0.087 |
site | +0.085 |
ths | +0.084 |
ently | +0.084 |
Neg logit contributions | |
burn | -0.046 |
y | -0.044 |
their | -0.043 |
Woo | -0.040 |
Sara | -0.039 |
Token | furry |
Token ID | 40857 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
burn | +0.017 |
ana | +0.015 |
y | +0.014 |
ful | +0.014 |
groom | +0.014 |
Neg logit contributions | |
quest | -0.016 |
mission | -0.013 |
attempts | -0.013 |
walks | -0.013 |
boulder | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
quest | +0.049 |
ement | +0.046 |
site | +0.044 |
exhibit | +0.044 |
ently | +0.043 |
Neg logit contributions | |
burn | -0.035 |
Woo | -0.031 |
their | -0.030 |
y | -0.029 |
groom | -0.029 |
Token | has |
Token ID | 468 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
burn | +0.011 |
y | +0.009 |
ana | +0.009 |
ful | +0.009 |
ety | +0.009 |
Neg logit contributions | |
quest | -0.011 |
mission | -0.009 |
walks | -0.009 |
attempts | -0.009 |
boulder | -0.008 |
Token | sharp |
Token ID | 7786 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
quest | +0.002 |
repairs | +0.002 |
lair | +0.002 |
site | +0.002 |
ement | +0.002 |
Neg logit contributions | |
burn | -0.002 |
y | -0.002 |
ety | -0.002 |
Woo | -0.002 |
ot | -0.002 |
Token | teeth |
Token ID | 9941 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
quest | +0.084 |
ement | +0.077 |
site | +0.073 |
ently | +0.071 |
exhibit | +0.069 |
Neg logit contributions | |
burn | -0.100 |
their | -0.093 |
y | -0.092 |
Woo | -0.092 |
ot | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
quest | +0.011 |
ement | +0.010 |
site | +0.010 |
ently | +0.009 |
exhibit | +0.009 |
Neg logit contributions | |
burn | -0.010 |
groom | -0.009 |
Woo | -0.009 |
Lara | -0.009 |
ot | -0.009 |
Token | The |
Token ID | 383 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ement | +0.001 |
quest | +0.001 |
site | +0.001 |
exhibit | +0.001 |
ently | +0.001 |
Neg logit contributions | |
burn | -0.001 |
groom | -0.001 |
y | -0.001 |
ety | -0.001 |
flower | -0.001 |
Token | dog |
Token ID | 3290 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
burn | +0.003 |
y | +0.002 |
their | +0.002 |
Woo | +0.002 |
ety | +0.002 |
Neg logit contributions | |
quest | -0.004 |
ement | -0.004 |
site | -0.004 |
exhibit | -0.003 |
ently | -0.003 |
Token | bar |
Token ID | 2318 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
quest | +0.006 |
ement | +0.006 |
site | +0.006 |
ently | +0.006 |
ths | +0.006 |
Neg logit contributions | |
burn | -0.004 |
their | -0.004 |
y | -0.004 |
Woo | -0.004 |
Sara | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
burn | +0.010 |
y | +0.010 |
their | +0.010 |
Woo | +0.009 |
her | +0.009 |
Neg logit contributions | |
quest | -0.019 |
ement | -0.018 |
site | -0.018 |
ths | -0.017 |
ently | -0.017 |
Token | You |
Token ID | 921 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
burn | +0.003 |
y | +0.003 |
their | +0.003 |
ety | +0.003 |
Woo | +0.003 |
Neg logit contributions | |
quest | -0.005 |
ement | -0.004 |
site | -0.004 |
exhibit | -0.004 |
ently | -0.004 |
Token | have |
Token ID | 423 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
burn | +0.001 |
their | +0.001 |
y | +0.001 |
Woo | +0.001 |
ety | +0.001 |
Neg logit contributions | |
quest | -0.002 |
ement | -0.002 |
site | -0.002 |
ently | -0.002 |
ths | -0.002 |
Token | other |
Token ID | 584 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
burn | +0.012 |
their | +0.011 |
y | +0.011 |
Woo | +0.011 |
Sara | +0.010 |
Neg logit contributions | |
quest | -0.028 |
ement | -0.027 |
site | -0.026 |
ently | -0.026 |
ths | -0.025 |
Token | cr |
Token ID | 1067 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
quest | +0.044 |
ement | +0.041 |
site | +0.040 |
ently | +0.040 |
ths | +0.039 |
Neg logit contributions | |
their | -0.024 |
burn | -0.024 |
y | -0.023 |
her | -0.023 |
your | -0.023 |
Token | ay |
Token ID | 323 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
quest | +0.056 |
ement | +0.050 |
site | +0.049 |
ths | +0.047 |
exhibit | +0.047 |
Neg logit contributions | |
burn | -0.046 |
y | -0.043 |
their | -0.042 |
Woo | -0.041 |
ot | -0.040 |
Token | ons |
Token ID | 684 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
quest | +0.064 |
ement | +0.051 |
site | +0.049 |
ths | +0.044 |
ently | +0.043 |
Neg logit contributions | |
burn | -0.167 |
their | -0.161 |
y | -0.161 |
Woo | -0.156 |
ot | -0.156 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
quest | +0.003 |
ement | +0.003 |
ently | +0.003 |
site | +0.003 |
exhibit | +0.003 |
Neg logit contributions | |
burn | -0.003 |
Woo | -0.002 |
their | -0.002 |
La | -0.002 |
Pop | -0.002 |
Token | Let |
Token ID | 3914 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
quest | +0.005 |
ement | +0.005 |
site | +0.005 |
exhibit | +0.005 |
ently | +0.005 |
Neg logit contributions | |
burn | -0.004 |
y | -0.004 |
their | -0.003 |
ety | -0.003 |
groom | -0.003 |
Token | me |
Token ID | 502 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
quest | +0.013 |
ement | +0.012 |
ths | +0.012 |
ently | +0.012 |
site | +0.012 |
Neg logit contributions | |
burn | -0.012 |
free | -0.012 |
y | -0.011 |
ot | -0.011 |
Woo | -0.011 |
Token | make |
Token ID | 787 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
quest | +0.034 |
ement | +0.033 |
site | +0.032 |
ently | +0.031 |
ths | +0.031 |
Neg logit contributions | |
burn | -0.017 |
their | -0.016 |
y | -0.016 |
ot | -0.015 |
her | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
quest | +0.048 |
ement | +0.045 |
site | +0.043 |
ently | +0.042 |
exhibit | +0.042 |
Neg logit contributions | |
burn | -0.038 |
their | -0.034 |
Woo | -0.034 |
y | -0.034 |
ot | -0.032 |
Token | elephants |
Token ID | 25368 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
quest | +0.001 |
ement | +0.001 |
site | +0.001 |
ently | +0.001 |
exhibit | +0.001 |
Neg logit contributions | |
burn | -0.001 |
their | -0.001 |
y | -0.001 |
Woo | -0.001 |
ot | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
quest | +0.055 |
ement | +0.051 |
site | +0.049 |
ently | +0.048 |
exhibit | +0.047 |
Neg logit contributions | |
burn | -0.040 |
their | -0.036 |
Woo | -0.036 |
y | -0.036 |
ot | -0.034 |
Token | monkeys |
Token ID | 26697 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
quest | +0.009 |
ement | +0.008 |
site | +0.008 |
ently | +0.008 |
ths | +0.008 |
Neg logit contributions | |
burn | -0.005 |
their | -0.005 |
y | -0.005 |
Woo | -0.004 |
Sara | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
quest | +0.034 |
ement | +0.031 |
site | +0.031 |
exhibit | +0.030 |
ently | +0.029 |
Neg logit contributions | |
burn | -0.027 |
Woo | -0.024 |
their | -0.024 |
y | -0.024 |
ot | -0.023 |
Token | gir |
Token ID | 37370 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
quest | +0.047 |
ement | +0.044 |
site | +0.041 |
ently | +0.041 |
ths | +0.040 |
Neg logit contributions | |
burn | -0.039 |
their | -0.037 |
y | -0.036 |
Woo | -0.036 |
Sara | -0.034 |
Token | aff |
Token ID | 2001 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
quest | +0.127 |
ement | +0.116 |
site | +0.112 |
ently | +0.110 |
ths | +0.110 |
Neg logit contributions | |
burn | -0.088 |
their | -0.083 |
y | -0.083 |
Woo | -0.080 |
Sara | -0.077 |
Token | es |
Token ID | 274 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
quest | +0.012 |
exhibit | +0.012 |
ement | +0.012 |
ently | +0.011 |
site | +0.011 |
Neg logit contributions | |
burn | -0.026 |
Woo | -0.025 |
Lara | -0.023 |
C | -0.023 |
ot | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
burn | +0.007 |
their | +0.006 |
y | +0.006 |
Woo | +0.006 |
ot | +0.006 |
Neg logit contributions | |
quest | -0.012 |
ement | -0.011 |
site | -0.011 |
ently | -0.010 |
exhibit | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
quest | +0.006 |
ement | +0.006 |
site | +0.006 |
ently | +0.005 |
exhibit | +0.005 |
Neg logit contributions | |
burn | -0.004 |
y | -0.003 |
Woo | -0.003 |
their | -0.003 |
ety | -0.003 |
Token | pretend |
Token ID | 16614 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
burn | +0.005 |
Woo | +0.004 |
y | +0.004 |
their | +0.004 |
ety | +0.004 |
Neg logit contributions | |
quest | -0.009 |
ement | -0.008 |
site | -0.008 |
exhibit | -0.008 |
ths | -0.008 |
Token | Every |
Token ID | 3887 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
quest | +0.029 |
ement | +0.027 |
site | +0.026 |
ently | +0.025 |
ths | +0.025 |
Neg logit contributions | |
burn | -0.021 |
their | -0.020 |
y | -0.019 |
Woo | -0.019 |
Sara | -0.018 |
Token | time |
Token ID | 640 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
their | +0.001 |
y | +0.001 |
burn | +0.001 |
ot | +0.001 |
her | +0.001 |
Neg logit contributions | |
quest | -0.002 |
ement | -0.002 |
renches | -0.002 |
ently | -0.002 |
site | -0.002 |
Token | Andy |
Token ID | 12382 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
quest | +0.025 |
ement | +0.023 |
site | +0.023 |
ths | +0.022 |
exhibit | +0.022 |
Neg logit contributions | |
burn | -0.013 |
y | -0.011 |
Woo | -0.011 |
ety | -0.011 |
their | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
quest | +0.070 |
ement | +0.065 |
site | +0.064 |
ently | +0.062 |
ths | +0.061 |
Neg logit contributions | |
burn | -0.038 |
y | -0.036 |
their | -0.034 |
Woo | -0.032 |
ot | -0.031 |
Token | N |
Token ID | 399 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
quest | +0.001 |
site | +0.001 |
exhibit | +0.001 |
attempts | +0.001 |
ement | +0.001 |
Neg logit contributions | |
burn | -0.001 |
Woo | -0.001 |
ety | -0.001 |
y | -0.001 |
free | -0.001 |
Token | iki |
Token ID | 5580 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
burn | +0.016 |
Woo | +0.015 |
their | +0.015 |
y | +0.014 |
C | +0.013 |
Neg logit contributions | |
quest | -0.023 |
ement | -0.022 |
ently | -0.021 |
site | -0.021 |
exhibit | -0.020 |
Token | thought |
Token ID | 1807 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
quest | +0.127 |
ement | +0.122 |
site | +0.120 |
ently | +0.116 |
renches | +0.116 |
Neg logit contributions | |
y | -0.057 |
their | -0.056 |
burn | -0.054 |
her | -0.049 |
ot | -0.048 |
Token | of |
Token ID | 286 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
quest | +0.059 |
ement | +0.054 |
site | +0.053 |
ths | +0.052 |
exhibit | +0.052 |
Neg logit contributions | |
their | -0.031 |
y | -0.028 |
burn | -0.027 |
her | -0.027 |
Sara | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
quest | +0.003 |
ement | +0.003 |
site | +0.003 |
ently | +0.003 |
ths | +0.003 |
Neg logit contributions | |
burn | -0.001 |
their | -0.001 |
y | -0.001 |
Woo | -0.001 |
her | -0.001 |
Token | symbol |
Token ID | 6194 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
quest | +0.033 |
ement | +0.031 |
ths | +0.031 |
site | +0.030 |
ently | +0.030 |
Neg logit contributions | |
their | -0.016 |
y | -0.014 |
her | -0.014 |
ot | -0.014 |
like | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
quest | +0.047 |
ement | +0.043 |
site | +0.043 |
ently | +0.042 |
ths | +0.041 |
Neg logit contributions | |
their | -0.028 |
burn | -0.028 |
y | -0.028 |
her | -0.026 |
ot | -0.025 |
Token | ! |
Token ID | 0 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
burn | +0.001 |
their | +0.001 |
y | +0.001 |
Woo | +0.001 |
ety | +0.001 |
Neg logit contributions | |
quest | -0.002 |
ement | -0.002 |
site | -0.002 |
ently | -0.002 |
ths | -0.002 |
Token | |
Token ID | 220 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
burn | +0.005 |
their | +0.004 |
y | +0.004 |
Woo | +0.004 |
groom | +0.004 |
Neg logit contributions | |
quest | -0.008 |
ement | -0.007 |
site | -0.007 |
ently | -0.007 |
exhibit | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
burn | +0.008 |
y | +0.007 |
their | +0.007 |
Woo | +0.007 |
groom | +0.007 |
Neg logit contributions | |
quest | -0.013 |
ement | -0.012 |
site | -0.012 |
ently | -0.011 |
exhibit | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
burn | +0.000 |
their | +0.000 |
y | +0.000 |
Woo | +0.000 |
Sara | +0.000 |
Neg logit contributions | |
quest | -0.001 |
ement | -0.000 |
site | -0.000 |
ently | -0.000 |
ths | -0.000 |
Token | S |
Token ID | 50 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
burn | +0.003 |
y | +0.002 |
their | +0.002 |
Woo | +0.002 |
ety | +0.002 |
Neg logit contributions | |
quest | -0.004 |
ement | -0.004 |
site | -0.004 |
ently | -0.004 |
ths | -0.004 |
Token | ally |
Token ID | 453 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
quest | +0.005 |
ement | +0.005 |
site | +0.005 |
ently | +0.005 |
ths | +0.005 |
Neg logit contributions | |
burn | -0.004 |
their | -0.004 |
y | -0.004 |
Woo | -0.004 |
Sara | -0.004 |
Token | soon |
Token ID | 2582 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
quest | +0.036 |
ement | +0.034 |
site | +0.033 |
ently | +0.032 |
ths | +0.032 |
Neg logit contributions | |
burn | -0.023 |
their | -0.021 |
y | -0.020 |
Woo | -0.020 |
Sara | -0.019 |
Token | realised |
Token ID | 19169 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
burn | +0.004 |
Woo | +0.003 |
free | +0.003 |
ety | +0.003 |
ksh | +0.003 |
Neg logit contributions | |
quest | -0.004 |
ement | -0.003 |
site | -0.003 |
exhibit | -0.003 |
ths | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
quest | +0.002 |
ement | +0.002 |
site | +0.002 |
ently | +0.002 |
ths | +0.002 |
Neg logit contributions | |
burn | -0.002 |
y | -0.002 |
Woo | -0.002 |
ety | -0.002 |
their | -0.002 |
Token | exploring |
Token ID | 13504 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
burn | +0.024 |
y | +0.021 |
Woo | +0.019 |
ety | +0.019 |
ot | +0.019 |
Neg logit contributions | |
quest | -0.045 |
ement | -0.042 |
site | -0.041 |
ths | -0.040 |
ently | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +5.83e-03 |
Pos logit contributions | |
quest | +0.035 |
ement | +0.033 |
site | +0.032 |
ently | +0.032 |
ths | +0.031 |
Neg logit contributions | |
burn | -0.017 |
their | -0.015 |
y | -0.015 |
Woo | -0.014 |
Sara | -0.013 |
Token | old |
Token ID | 727 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
quest | +0.013 |
ement | +0.011 |
site | +0.010 |
ently | +0.010 |
ths | +0.010 |
Neg logit contributions | |
burn | -0.027 |
y | -0.026 |
their | -0.026 |
Woo | -0.025 |
ot | -0.025 |
Token | started |
Token ID | 2067 |
Feature activation | -9.61e-02 |
Pos logit contributions | |
quest | +0.008 |
ement | +0.008 |
site | +0.007 |
ently | +0.007 |
ths | +0.007 |
Neg logit contributions | |
burn | -0.005 |
their | -0.005 |
Woo | -0.005 |
y | -0.005 |
ety | -0.004 |
Token | testing |
Token ID | 4856 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
burn | +0.002 |
Woo | +0.001 |
y | +0.001 |
their | +0.001 |
ety | +0.001 |
Neg logit contributions | |
quest | -0.003 |
ement | -0.003 |
site | -0.003 |
ths | -0.003 |
ently | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
burn | +0.005 |
their | +0.004 |
y | +0.004 |
Woo | +0.004 |
her | +0.004 |
Neg logit contributions | |
quest | -0.009 |
ement | -0.008 |
site | -0.008 |
ently | -0.008 |
ths | -0.008 |
Token | trying |
Token ID | 2111 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
quest | +0.014 |
ement | +0.013 |
site | +0.012 |
ently | +0.012 |
ths | +0.012 |
Neg logit contributions | |
burn | -0.011 |
y | -0.010 |
their | -0.010 |
Woo | -0.010 |
ety | -0.009 |
Token | new |
Token ID | 649 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
burn | +0.006 |
their | +0.006 |
y | +0.005 |
Woo | +0.005 |
her | +0.005 |
Neg logit contributions | |
quest | -0.014 |
ement | -0.014 |
site | -0.013 |
ently | -0.013 |
ths | -0.013 |
Token | things |
Token ID | 1243 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
quest | +0.057 |
ement | +0.052 |
site | +0.052 |
ued | +0.051 |
ently | +0.051 |
Neg logit contributions | |
their | -0.047 |
her | -0.044 |
y | -0.042 |
your | -0.040 |
like | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
their | +0.006 |
burn | +0.006 |
y | +0.005 |
her | +0.005 |
Woo | +0.005 |
Neg logit contributions | |
quest | -0.013 |
ement | -0.012 |
site | -0.012 |
ently | -0.012 |
exhibit | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
burn | +0.002 |
their | +0.002 |
y | +0.002 |
Woo | +0.002 |
Sara | +0.002 |
Neg logit contributions | |
quest | -0.003 |
ement | -0.003 |
site | -0.003 |
ently | -0.003 |
ths | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
burn | +0.002 |
their | +0.002 |
y | +0.002 |
Woo | +0.002 |
Sara | +0.002 |
Neg logit contributions | |
quest | -0.003 |
ement | -0.003 |
site | -0.003 |
ently | -0.003 |
ths | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
burn | +0.010 |
y | +0.009 |
their | +0.009 |
Woo | +0.008 |
her | +0.008 |
Neg logit contributions | |
quest | -0.020 |
ement | -0.019 |
site | -0.018 |
ently | -0.018 |
exhibit | -0.018 |
Token | named |
Token ID | 3706 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
burn | +0.045 |
Woo | +0.041 |
their | +0.040 |
y | +0.039 |
groom | +0.038 |
Neg logit contributions | |
quest | -0.044 |
ement | -0.039 |
site | -0.038 |
exhibit | -0.038 |
ths | -0.037 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
burn | +0.032 |
groom | +0.025 |
y | +0.024 |
La | +0.022 |
Woo | +0.022 |
Neg logit contributions | |
quest | -0.057 |
exhibit | -0.054 |
repairs | -0.051 |
site | -0.050 |
ently | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +4.23e-03 |
Pos logit contributions | |
burn | +0.035 |
Woo | +0.031 |
their | +0.030 |
groom | +0.029 |
y | +0.029 |
Neg logit contributions | |
quest | -0.048 |
ement | -0.043 |
site | -0.043 |
exhibit | -0.042 |
ently | -0.042 |
Token | She |
Token ID | 1375 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
quest | +0.000 |
ement | +0.000 |
exhibit | +0.000 |
renches | +0.000 |
site | +0.000 |
Neg logit contributions | |
burn | -0.000 |
groom | -0.000 |
a | -0.000 |
ful | -0.000 |
our | -0.000 |
Token | loved |
Token ID | 6151 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
burn | +0.005 |
Woo | +0.005 |
ful | +0.004 |
groom | +0.004 |
their | +0.004 |
Neg logit contributions | |
quest | -0.005 |
mission | -0.004 |
site | -0.004 |
trek | -0.004 |
exhibit | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
quest | +0.021 |
ths | +0.019 |
site | +0.019 |
repairs | +0.019 |
exhibit | +0.019 |
Neg logit contributions | |
burn | -0.012 |
y | -0.011 |
ot | -0.010 |
a | -0.010 |
Woo | -0.010 |
Token | draw |
Token ID | 3197 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
quest | +0.025 |
ement | +0.022 |
site | +0.022 |
exhibit | +0.021 |
ently | +0.021 |
Neg logit contributions | |
burn | -0.016 |
y | -0.015 |
Woo | -0.014 |
their | -0.014 |
ety | -0.014 |
Token | pictures |
Token ID | 5986 |
Feature activation | +5.88e-03 |
Pos logit contributions | |
quest | +0.004 |
ement | +0.004 |
site | +0.003 |
ently | +0.003 |
exhibit | +0.003 |
Neg logit contributions | |
burn | -0.003 |
Woo | -0.003 |
y | -0.003 |
their | -0.002 |
ety | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
quest | +0.000 |
ement | +0.000 |
site | +0.000 |
ently | +0.000 |
ths | +0.000 |
Neg logit contributions | |
burn | -0.000 |
their | -0.000 |
y | -0.000 |
Woo | -0.000 |
Sara | -0.000 |
Token | flowers |
Token ID | 12734 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
quest | +0.013 |
ement | +0.012 |
site | +0.012 |
exhibit | +0.011 |
repairs | +0.011 |
Neg logit contributions | |
burn | -0.010 |
y | -0.008 |
Woo | -0.008 |
ety | -0.008 |
ot | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
quest | +0.006 |
ement | +0.006 |
site | +0.005 |
exhibit | +0.005 |
ently | +0.005 |
Neg logit contributions | |
burn | -0.006 |
Woo | -0.005 |
ot | -0.005 |
groom | -0.005 |
Pop | -0.005 |
Token | Rib |
Token ID | 23133 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
quest | +0.001 |
ement | +0.001 |
site | +0.001 |
exhibit | +0.001 |
boulder | +0.001 |
Neg logit contributions | |
burn | -0.000 |
y | -0.000 |
ety | -0.000 |
their | -0.000 |
free | -0.000 |
Token | bit |
Token ID | 2545 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
burn | +0.039 |
Woo | +0.036 |
their | +0.036 |
Sara | +0.033 |
her | +0.033 |
Neg logit contributions | |
quest | -0.062 |
ement | -0.058 |
ently | -0.056 |
exhibit | -0.053 |
renches | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
quest | +0.019 |
ement | +0.017 |
exhibit | +0.017 |
ently | +0.017 |
site | +0.016 |
Neg logit contributions | |
burn | -0.022 |
La | -0.020 |
Woo | -0.019 |
their | -0.019 |
Pop | -0.019 |
Token | You |
Token ID | 921 |
Feature activation | +9.36e-03 |
Pos logit contributions | |
quest | +0.037 |
ement | +0.035 |
exhibit | +0.033 |
site | +0.033 |
ently | +0.032 |
Neg logit contributions | |
burn | -0.026 |
y | -0.023 |
their | -0.022 |
groom | -0.021 |
her | -0.020 |
Token | are |
Token ID | 389 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
quest | +0.000 |
ement | +0.000 |
site | +0.000 |
exhibit | +0.000 |
ently | +0.000 |
Neg logit contributions | |
burn | -0.000 |
their | -0.000 |
y | -0.000 |
Woo | -0.000 |
Sara | -0.000 |
Token | very |
Token ID | 845 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
burn | +0.004 |
y | +0.004 |
aa | +0.003 |
ot | +0.003 |
ety | +0.003 |
Neg logit contributions | |
quest | -0.004 |
burying | -0.004 |
lair | -0.004 |
adventure | -0.004 |
exploration | -0.004 |
Token | green |
Token ID | 4077 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
quest | +0.019 |
ement | +0.016 |
mission | +0.016 |
exploration | +0.016 |
exhibit | +0.015 |
Neg logit contributions | |
burn | -0.018 |
y | -0.014 |
ksh | -0.013 |
ety | -0.013 |
Woo | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
quest | +0.051 |
ement | +0.048 |
site | +0.045 |
exhibit | +0.045 |
ently | +0.044 |
Neg logit contributions | |
burn | -0.037 |
their | -0.033 |
Woo | -0.032 |
groom | -0.030 |
ot | -0.030 |
Token | slim |
Token ID | 18862 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
burn | +0.002 |
ana | +0.002 |
y | +0.002 |
ety | +0.002 |
S | +0.002 |
Neg logit contributions | |
quest | -0.002 |
exploration | -0.002 |
mission | -0.002 |
ement | -0.002 |
ths | -0.002 |
Token | y |
Token ID | 88 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ement | +0.001 |
quest | +0.001 |
exhibit | +0.001 |
ently | +0.001 |
lair | +0.001 |
Neg logit contributions | |
burn | -0.000 |
Lara | -0.000 |
groom | -0.000 |
La | -0.000 |
Woo | -0.000 |
Token | ." |
Token ID | 526 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
quest | +0.037 |
ement | +0.034 |
site | +0.033 |
ently | +0.032 |
exhibit | +0.032 |
Neg logit contributions | |
burn | -0.021 |
Woo | -0.018 |
their | -0.018 |
y | -0.017 |
ety | -0.016 |
Token | first |
Token ID | 717 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
quest | +0.079 |
ement | +0.075 |
site | +0.072 |
ently | +0.071 |
exhibit | +0.070 |
Neg logit contributions | |
burn | -0.037 |
their | -0.034 |
y | -0.033 |
Woo | -0.032 |
Sara | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
quest | +0.096 |
ement | +0.090 |
ently | +0.086 |
site | +0.086 |
exhibit | +0.084 |
Neg logit contributions | |
their | -0.048 |
burn | -0.048 |
Sara | -0.044 |
y | -0.044 |
Woo | -0.043 |
Token | can |
Token ID | 460 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
quest | +0.018 |
ement | +0.017 |
site | +0.016 |
ently | +0.016 |
ths | +0.016 |
Neg logit contributions | |
burn | -0.008 |
y | -0.007 |
their | -0.007 |
Woo | -0.007 |
ety | -0.006 |
Token | you |
Token ID | 345 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
burn | +0.009 |
their | +0.008 |
y | +0.008 |
Woo | +0.008 |
Sara | +0.007 |
Neg logit contributions | |
quest | -0.018 |
ement | -0.017 |
site | -0.016 |
ently | -0.016 |
ths | -0.016 |
Token | give |
Token ID | 1577 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
burn | +0.006 |
their | +0.005 |
y | +0.005 |
Woo | +0.005 |
ot | +0.005 |
Neg logit contributions | |
quest | -0.010 |
ement | -0.010 |
ently | -0.009 |
site | -0.009 |
ths | -0.009 |
Token | me |
Token ID | 502 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
burn | +0.041 |
y | +0.037 |
Woo | +0.036 |
their | +0.036 |
ot | +0.034 |
Neg logit contributions | |
quest | -0.058 |
ement | -0.053 |
site | -0.052 |
ths | -0.051 |
exhibit | -0.051 |
Token | back |
Token ID | 736 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
quest | +0.095 |
exhibit | +0.089 |
repairs | +0.086 |
ement | +0.086 |
site | +0.085 |
Neg logit contributions | |
burn | -0.055 |
y | -0.050 |
Woo | -0.048 |
ety | -0.045 |
free | -0.045 |
Token | my |
Token ID | 616 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
quest | +0.011 |
site | +0.011 |
exhibit | +0.011 |
ement | +0.010 |
ently | +0.010 |
Neg logit contributions | |
burn | -0.006 |
Woo | -0.005 |
y | -0.005 |
free | -0.005 |
groom | -0.005 |
Token | toy |
Token ID | 13373 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
their | +0.004 |
burn | +0.004 |
our | +0.003 |
your | +0.003 |
Sara | +0.003 |
Neg logit contributions | |
quest | -0.005 |
ently | -0.005 |
ement | -0.005 |
ths | -0.005 |
site | -0.005 |
Token | truck |
Token ID | 7779 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
quest | +0.080 |
ement | +0.074 |
ently | +0.071 |
attempts | +0.071 |
site | +0.069 |
Neg logit contributions | |
burn | -0.055 |
their | -0.050 |
y | -0.049 |
Woo | -0.048 |
C | -0.046 |
Token | ? |
Token ID | 30 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
quest | +0.073 |
ement | +0.068 |
site | +0.066 |
ently | +0.064 |
ths | +0.063 |
Neg logit contributions | |
burn | -0.046 |
their | -0.042 |
Woo | -0.042 |
y | -0.041 |
Sara | -0.039 |
Token | at |
Token ID | 379 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
quest | +0.048 |
ement | +0.045 |
site | +0.042 |
ently | +0.041 |
exhibit | +0.041 |
Neg logit contributions | |
burn | -0.036 |
y | -0.032 |
Woo | -0.032 |
their | -0.031 |
ety | -0.030 |
Token | all |
Token ID | 477 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
quest | +0.059 |
ement | +0.057 |
site | +0.054 |
exhibit | +0.053 |
ently | +0.053 |
Neg logit contributions | |
burn | -0.020 |
y | -0.017 |
Woo | -0.016 |
ety | -0.015 |
ot | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
burn | +0.012 |
Woo | +0.010 |
ety | +0.010 |
free | +0.009 |
y | +0.009 |
Neg logit contributions | |
quest | -0.022 |
ement | -0.022 |
site | -0.021 |
exhibit | -0.020 |
ently | -0.020 |
Token | pictures |
Token ID | 5986 |
Feature activation | +9.39e-02 |
Pos logit contributions | |
quest | +0.013 |
ently | +0.013 |
ement | +0.013 |
ths | +0.012 |
iously | +0.012 |
Neg logit contributions | |
their | -0.009 |
burn | -0.008 |
y | -0.008 |
our | -0.008 |
groom | -0.008 |
Token | they |
Token ID | 484 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
quest | +0.003 |
ement | +0.003 |
site | +0.003 |
ently | +0.003 |
ths | +0.003 |
Neg logit contributions | |
burn | -0.002 |
their | -0.002 |
y | -0.002 |
her | -0.001 |
Woo | -0.001 |
Token | took |
Token ID | 1718 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
burn | +0.004 |
Woo | +0.004 |
y | +0.003 |
their | +0.003 |
Sara | +0.003 |
Neg logit contributions | |
quest | -0.008 |
ement | -0.008 |
site | -0.008 |
ths | -0.007 |
ently | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
burn | +0.002 |
Woo | +0.001 |
y | +0.001 |
ety | +0.001 |
their | +0.001 |
Neg logit contributions | |
quest | -0.003 |
ement | -0.003 |
site | -0.002 |
ently | -0.002 |
exhibit | -0.002 |
Token | smiled |
Token ID | 13541 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
quest | +0.003 |
site | +0.002 |
ement | +0.002 |
exhibit | +0.002 |
ths | +0.002 |
Neg logit contributions | |
burn | -0.002 |
y | -0.002 |
Woo | -0.002 |
ety | -0.001 |
ot | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
burn | +0.007 |
ety | +0.007 |
Woo | +0.007 |
Pop | +0.006 |
Anna | +0.006 |
Neg logit contributions | |
quest | -0.006 |
ement | -0.006 |
ently | -0.005 |
ths | -0.005 |
site | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
burn | +0.004 |
y | +0.003 |
their | +0.003 |
Woo | +0.003 |
groom | +0.003 |
Neg logit contributions | |
quest | -0.007 |
ement | -0.007 |
site | -0.007 |
exhibit | -0.006 |
ently | -0.006 |
Token | couldn |
Token ID | 3521 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
burn | +0.002 |
Woo | +0.002 |
y | +0.002 |
their | +0.002 |
Sara | +0.002 |
Neg logit contributions | |
quest | -0.004 |
ement | -0.003 |
site | -0.003 |
ths | -0.003 |
exhibit | -0.003 |
Token | when |
Token ID | 618 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
burn | +0.025 |
Woo | +0.024 |
Sara | +0.023 |
Pop | +0.022 |
C | +0.022 |
Neg logit contributions | |
quest | -0.029 |
ement | -0.025 |
site | -0.025 |
exhibit | -0.024 |
ently | -0.024 |
Token | they |
Token ID | 484 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
burn | +0.004 |
y | +0.003 |
Woo | +0.003 |
ety | +0.003 |
ot | +0.003 |
Neg logit contributions | |
quest | -0.006 |
ement | -0.006 |
site | -0.006 |
ths | -0.006 |
repairs | -0.005 |
Token | needed |
Token ID | 2622 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
burn | +0.008 |
their | +0.007 |
y | +0.007 |
Woo | +0.007 |
her | +0.006 |
Neg logit contributions | |
quest | -0.014 |
ement | -0.013 |
site | -0.013 |
ently | -0.013 |
ths | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
quest | +0.016 |
ement | +0.015 |
site | +0.014 |
ently | +0.014 |
ths | +0.014 |
Neg logit contributions | |
their | -0.007 |
burn | -0.007 |
her | -0.007 |
Woo | -0.007 |
Sara | -0.006 |
Token | help |
Token ID | 1037 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
quest | +0.028 |
ement | +0.027 |
ently | +0.026 |
site | +0.026 |
ths | +0.026 |
Neg logit contributions | |
burn | -0.019 |
their | -0.018 |
her | -0.016 |
y | -0.016 |
Woo | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
burn | +0.039 |
Woo | +0.035 |
y | +0.034 |
their | +0.033 |
ety | +0.032 |
Neg logit contributions | |
quest | -0.061 |
ement | -0.056 |
site | -0.055 |
ently | -0.054 |
exhibit | -0.053 |
Token | no |
Token ID | 645 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
quest | +0.013 |
ement | +0.012 |
site | +0.012 |
ently | +0.012 |
ths | +0.011 |
Neg logit contributions | |
burn | -0.008 |
their | -0.008 |
y | -0.007 |
Woo | -0.007 |
her | -0.007 |
Token | matter |
Token ID | 2300 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
quest | +0.004 |
ement | +0.003 |
site | +0.003 |
ently | +0.003 |
ths | +0.003 |
Neg logit contributions | |
burn | -0.002 |
their | -0.002 |
y | -0.002 |
Woo | -0.002 |
Sara | -0.002 |
Token | how |
Token ID | 703 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
quest | +0.024 |
ement | +0.022 |
site | +0.021 |
ently | +0.020 |
ths | +0.020 |
Neg logit contributions | |
burn | -0.021 |
their | -0.020 |
y | -0.020 |
Woo | -0.019 |
her | -0.019 |
Token | small |
Token ID | 1402 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
burn | +0.021 |
their | +0.019 |
y | +0.019 |
Woo | +0.019 |
Sara | +0.018 |
Neg logit contributions | |
quest | -0.038 |
ement | -0.036 |
site | -0.035 |
ently | -0.034 |
ths | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
quest | +0.066 |
ement | +0.062 |
site | +0.060 |
ently | +0.059 |
ths | +0.058 |
Neg logit contributions | |
burn | -0.035 |
Woo | -0.031 |
y | -0.030 |
their | -0.030 |
ety | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
burn | +0.033 |
their | +0.031 |
y | +0.030 |
Woo | +0.029 |
ot | +0.027 |
Neg logit contributions | |
quest | -0.065 |
ement | -0.061 |
site | -0.059 |
ently | -0.058 |
ths | -0.058 |
Token | made |
Token ID | 925 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
quest | +0.001 |
ement | +0.001 |
site | +0.001 |
ths | +0.001 |
ently | +0.001 |
Neg logit contributions | |
burn | -0.000 |
y | -0.000 |
Woo | -0.000 |
their | -0.000 |
ety | -0.000 |
Token | them |
Token ID | 606 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
burn | +0.023 |
y | +0.021 |
Woo | +0.020 |
their | +0.019 |
ety | +0.019 |
Neg logit contributions | |
quest | -0.048 |
ement | -0.045 |
site | -0.044 |
ently | -0.043 |
ths | -0.042 |
Token | more |
Token ID | 517 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
quest | +0.024 |
ement | +0.021 |
site | +0.021 |
ently | +0.021 |
repairs | +0.021 |
Neg logit contributions | |
burn | -0.016 |
Woo | -0.015 |
y | -0.014 |
ety | -0.014 |
C | -0.013 |
Token | fun |
Token ID | 1257 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
burn | +0.027 |
their | +0.024 |
y | +0.024 |
Woo | +0.024 |
ety | +0.023 |
Neg logit contributions | |
quest | -0.042 |
ement | -0.039 |
site | -0.038 |
ently | -0.037 |
ths | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
burn | +0.000 |
their | +0.000 |
y | +0.000 |
Woo | +0.000 |
Sara | +0.000 |
Neg logit contributions | |
quest | -0.001 |
ement | -0.001 |
site | -0.001 |
ently | -0.001 |
ths | -0.001 |
Token | useful |
Token ID | 4465 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
quest | +0.012 |
ement | +0.011 |
site | +0.011 |
ths | +0.010 |
repairs | +0.010 |
Neg logit contributions | |
burn | -0.008 |
y | -0.007 |
Woo | -0.007 |
ety | -0.007 |
their | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
quest | +0.003 |
ement | +0.003 |
site | +0.003 |
ently | +0.003 |
ths | +0.003 |
Neg logit contributions | |
burn | -0.002 |
their | -0.002 |
y | -0.002 |
Woo | -0.002 |
her | -0.002 |
Token | You |
Token ID | 921 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
burn | +0.011 |
y | +0.010 |
their | +0.009 |
groom | +0.009 |
ety | +0.009 |
Neg logit contributions | |
quest | -0.014 |
ement | -0.013 |
site | -0.012 |
exhibit | -0.012 |
repairs | -0.012 |
Token | are |
Token ID | 389 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
burn | +0.002 |
their | +0.002 |
y | +0.002 |
Woo | +0.002 |
Sara | +0.002 |
Neg logit contributions | |
quest | -0.005 |
ement | -0.004 |
site | -0.004 |
ently | -0.004 |
exhibit | -0.004 |
Token | very |
Token ID | 845 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
burn | +0.004 |
y | +0.004 |
ety | +0.004 |
aa | +0.003 |
ot | +0.003 |
Neg logit contributions | |
quest | -0.005 |
repairs | -0.005 |
ths | -0.005 |
site | -0.005 |
ement | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
quest | +0.001 |
ement | +0.001 |
site | +0.001 |
ently | +0.001 |
ths | +0.001 |
Neg logit contributions | |
burn | -0.001 |
y | -0.001 |
their | -0.001 |
Woo | -0.001 |
ety | -0.001 |
Token | You |
Token ID | 1639 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
their | +0.012 |
burn | +0.011 |
our | +0.011 |
Woo | +0.010 |
Sara | +0.010 |
Neg logit contributions | |
quest | -0.015 |
ths | -0.014 |
ement | -0.014 |
ently | -0.013 |
site | -0.013 |
Token | should |
Token ID | 815 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
quest | +0.020 |
ement | +0.019 |
site | +0.018 |
ently | +0.018 |
ths | +0.018 |
Neg logit contributions | |
burn | -0.010 |
their | -0.009 |
y | -0.009 |
Woo | -0.009 |
Sara | -0.008 |
Token | eat |
Token ID | 4483 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
burn | +0.004 |
y | +0.004 |
their | +0.004 |
ety | +0.003 |
Woo | +0.003 |
Neg logit contributions | |
quest | -0.007 |
mission | -0.006 |
ement | -0.006 |
site | -0.005 |
ently | -0.005 |
Token | more |
Token ID | 517 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
quest | +0.002 |
ement | +0.001 |
site | +0.001 |
ently | +0.001 |
ths | +0.001 |
Neg logit contributions | |
burn | -0.001 |
y | -0.001 |
their | -0.001 |
Woo | -0.001 |
ety | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
their | +0.002 |
your | +0.002 |
y | +0.002 |
her | +0.002 |
Sara | +0.002 |
Neg logit contributions | |
quest | -0.004 |
ement | -0.004 |
site | -0.004 |
ths | -0.004 |
lair | -0.004 |
Token | so |
Token ID | 523 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
quest | +0.006 |
ement | +0.005 |
ths | +0.005 |
attempts | +0.005 |
site | +0.005 |
Neg logit contributions | |
burn | -0.005 |
y | -0.005 |
their | -0.004 |
Woo | -0.004 |
groom | -0.004 |
Token | you |
Token ID | 345 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
quest | +0.034 |
ement | +0.032 |
site | +0.031 |
ently | +0.031 |
ths | +0.030 |
Neg logit contributions | |
burn | -0.019 |
y | -0.017 |
their | -0.016 |
Woo | -0.016 |
ety | -0.015 |
Token | can |
Token ID | 460 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
burn | +0.021 |
their | +0.019 |
Woo | +0.019 |
y | +0.018 |
C | +0.017 |
Neg logit contributions | |
quest | -0.035 |
ement | -0.032 |
site | -0.031 |
ently | -0.031 |
exhibit | -0.031 |
Token | be |
Token ID | 307 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
burn | +0.013 |
their | +0.012 |
y | +0.012 |
Woo | +0.012 |
ety | +0.011 |
Neg logit contributions | |
quest | -0.021 |
ement | -0.019 |
site | -0.019 |
ently | -0.018 |
ths | -0.018 |
Token | healthy |
Token ID | 5448 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
quest | +0.000 |
ths | +0.000 |
attempts | +0.000 |
ement | +0.000 |
lair | +0.000 |
Neg logit contributions | |
burn | -0.000 |
y | -0.000 |
Woo | -0.000 |
rav | -0.000 |
C | -0.000 |
Token | you |
Token ID | 345 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
quest | +0.056 |
ement | +0.052 |
site | +0.051 |
ently | +0.050 |
ths | +0.049 |
Neg logit contributions | |
burn | -0.028 |
their | -0.025 |
y | -0.025 |
Woo | -0.024 |
Sara | -0.023 |
Token | have |
Token ID | 423 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
burn | +0.013 |
their | +0.012 |
y | +0.012 |
Woo | +0.011 |
ot | +0.011 |
Neg logit contributions | |
quest | -0.030 |
ement | -0.029 |
site | -0.028 |
ently | -0.028 |
ths | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
burn | +0.009 |
y | +0.008 |
their | +0.008 |
Woo | +0.008 |
ot | +0.007 |
Neg logit contributions | |
quest | -0.020 |
ement | -0.018 |
site | -0.018 |
ently | -0.017 |
ths | -0.017 |
Token | problem |
Token ID | 1917 |
Feature activation | -5.73e-02 |
Pos logit contributions | |
quest | +0.037 |
ement | +0.036 |
ently | +0.035 |
site | +0.034 |
ths | +0.033 |
Neg logit contributions | |
burn | -0.028 |
their | -0.025 |
y | -0.024 |
Woo | -0.024 |
ot | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
their | +0.001 |
burn | +0.001 |
y | +0.001 |
Sara | +0.001 |
Woo | +0.001 |
Neg logit contributions | |
quest | -0.002 |
ement | -0.002 |
site | -0.002 |
ths | -0.002 |
lair | -0.002 |
Token | talk |
Token ID | 1561 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
quest | +0.018 |
ement | +0.017 |
site | +0.017 |
ths | +0.016 |
repairs | +0.016 |
Neg logit contributions | |
burn | -0.008 |
y | -0.008 |
ety | -0.007 |
their | -0.007 |
Woo | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
burn | +0.020 |
Woo | +0.018 |
ety | +0.017 |
groom | +0.017 |
their | +0.017 |
Neg logit contributions | |
quest | -0.033 |
site | -0.031 |
ement | -0.030 |
ently | -0.030 |
exhibit | -0.030 |
Token | someone |
Token ID | 2130 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
quest | +0.027 |
site | +0.024 |
ement | +0.024 |
ths | +0.024 |
ently | +0.023 |
Neg logit contributions | |
burn | -0.019 |
y | -0.017 |
Woo | -0.016 |
their | -0.016 |
ety | -0.016 |
Token | about |
Token ID | 546 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
quest | +0.012 |
ement | +0.011 |
site | +0.011 |
ently | +0.010 |
ths | +0.010 |
Neg logit contributions | |
burn | -0.009 |
their | -0.009 |
y | -0.008 |
Woo | -0.008 |
Sara | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
burn | +0.005 |
y | +0.005 |
Woo | +0.005 |
their | +0.004 |
ety | +0.004 |
Neg logit contributions | |
quest | -0.010 |
ement | -0.009 |
site | -0.009 |
ently | -0.009 |
ths | -0.009 |
Token | ." |
Token ID | 526 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
burn | +0.007 |
y | +0.006 |
their | +0.006 |
Woo | +0.006 |
Sara | +0.005 |
Neg logit contributions | |
quest | -0.015 |
ement | -0.014 |
site | -0.014 |
ently | -0.014 |
ths | -0.013 |
Token | play |
Token ID | 711 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
quest | +0.030 |
exhibit | +0.026 |
ement | +0.026 |
site | +0.026 |
mission | +0.025 |
Neg logit contributions | |
burn | -0.021 |
Woo | -0.020 |
y | -0.020 |
their | -0.019 |
ety | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
quest | +0.038 |
ement | +0.036 |
ently | +0.034 |
site | +0.034 |
ths | +0.033 |
Neg logit contributions | |
their | -0.018 |
burn | -0.018 |
Woo | -0.017 |
y | -0.016 |
her | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
quest | +0.011 |
site | +0.011 |
exhibit | +0.010 |
ement | +0.010 |
repairs | +0.010 |
Neg logit contributions | |
burn | -0.005 |
y | -0.004 |
Woo | -0.004 |
ety | -0.004 |
groom | -0.004 |
Token | park |
Token ID | 3952 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
quest | +0.015 |
site | +0.013 |
exhibit | +0.012 |
ement | +0.011 |
ths | +0.011 |
Neg logit contributions | |
burn | -0.030 |
y | -0.028 |
free | -0.027 |
ful | -0.027 |
ana | -0.027 |
Token | every |
Token ID | 790 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
burn | +0.006 |
their | +0.005 |
y | +0.005 |
Woo | +0.005 |
Sara | +0.005 |
Neg logit contributions | |
quest | -0.011 |
ement | -0.010 |
site | -0.010 |
ently | -0.010 |
ths | -0.009 |
Token | day |
Token ID | 1110 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
quest | +0.004 |
ement | +0.003 |
site | +0.003 |
exhibit | +0.003 |
ths | +0.003 |
Neg logit contributions | |
burn | -0.003 |
Woo | -0.002 |
their | -0.002 |
y | -0.002 |
C | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
burn | +0.050 |
their | +0.046 |
y | +0.046 |
Woo | +0.044 |
Sara | +0.042 |
Neg logit contributions | |
quest | -0.096 |
ement | -0.089 |
site | -0.087 |
ently | -0.085 |
ths | -0.084 |
Token | Today |
Token ID | 6288 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
quest | +0.006 |
ement | +0.006 |
site | +0.006 |
exhibit | +0.006 |
ently | +0.005 |
Neg logit contributions | |
burn | -0.007 |
y | -0.006 |
groom | -0.006 |
ful | -0.006 |
Woo | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
burn | +0.007 |
groom | +0.006 |
Woo | +0.006 |
free | +0.006 |
ety | +0.006 |
Neg logit contributions | |
quest | -0.007 |
ement | -0.007 |
site | -0.006 |
exhibit | -0.006 |
ently | -0.006 |
Token | they |
Token ID | 484 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
burn | +0.003 |
y | +0.003 |
free | +0.003 |
ot | +0.003 |
bo | +0.002 |
Neg logit contributions | |
quest | -0.004 |
site | -0.004 |
ement | -0.004 |
exhibit | -0.004 |
ths | -0.004 |
Token | see |
Token ID | 766 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
burn | +0.013 |
y | +0.011 |
their | +0.011 |
Woo | +0.011 |
ot | +0.010 |
Neg logit contributions | |
quest | -0.022 |
ement | -0.019 |
site | -0.019 |
exhibit | -0.019 |
ths | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
quest | +0.012 |
ths | +0.012 |
ement | +0.011 |
site | +0.011 |
hours | +0.011 |
Neg logit contributions | |
y | -0.011 |
burn | -0.011 |
asc | -0.010 |
ksh | -0.010 |
ety | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
burn | +0.014 |
Woo | +0.013 |
their | +0.013 |
y | +0.012 |
groom | +0.012 |
Neg logit contributions | |
quest | -0.020 |
ement | -0.018 |
site | -0.018 |
ently | -0.017 |
ths | -0.017 |
Token | time |
Token ID | 640 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
quest | +0.021 |
ement | +0.019 |
site | +0.018 |
ths | +0.017 |
ently | +0.017 |
Neg logit contributions | |
burn | -0.028 |
y | -0.027 |
free | -0.027 |
Woo | -0.026 |
ana | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
burn | +0.011 |
Woo | +0.010 |
y | +0.010 |
their | +0.009 |
C | +0.009 |
Neg logit contributions | |
quest | -0.023 |
ement | -0.021 |
ently | -0.021 |
site | -0.021 |
exhibit | -0.020 |
Token | go |
Token ID | 467 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
quest | +0.030 |
site | +0.025 |
ement | +0.025 |
repairs | +0.024 |
mission | +0.024 |
Neg logit contributions | |
y | -0.025 |
burn | -0.023 |
ety | -0.022 |
free | -0.022 |
a | -0.022 |
Token | home |
Token ID | 1363 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
quest | +0.008 |
ement | +0.007 |
site | +0.007 |
exhibit | +0.007 |
ently | +0.007 |
Neg logit contributions | |
burn | -0.005 |
y | -0.005 |
Woo | -0.005 |
their | -0.004 |
groom | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
burn | +0.057 |
Woo | +0.053 |
groom | +0.050 |
y | +0.050 |
ety | +0.050 |
Neg logit contributions | |
quest | -0.064 |
site | -0.058 |
ement | -0.058 |
ently | -0.057 |
exhibit | -0.055 |
Token | They |
Token ID | 1119 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
burn | +0.012 |
y | +0.010 |
groom | +0.010 |
flower | +0.009 |
free | +0.009 |
Neg logit contributions | |
quest | -0.017 |
ement | -0.015 |
site | -0.015 |
exhibit | -0.015 |
ently | -0.014 |
Token | had |
Token ID | 550 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
burn | +0.001 |
y | +0.001 |
their | +0.001 |
Woo | +0.001 |
ot | +0.001 |
Neg logit contributions | |
quest | -0.001 |
ement | -0.001 |
site | -0.001 |
exhibit | -0.001 |
ths | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
burn | +0.001 |
y | +0.001 |
free | +0.001 |
ot | +0.001 |
flower | +0.001 |
Neg logit contributions | |
quest | -0.001 |
repairs | -0.001 |
lair | -0.001 |
plans | -0.001 |
site | -0.001 |
Token | fun |
Token ID | 1257 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
quest | +0.016 |
ement | +0.014 |
site | +0.014 |
exhibit | +0.013 |
ths | +0.013 |
Neg logit contributions | |
burn | -0.010 |
y | -0.010 |
Woo | -0.009 |
their | -0.009 |
C | -0.009 |
Token | can |
Token ID | 460 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
quest | +0.015 |
exhibit | +0.013 |
ement | +0.013 |
repairs | +0.013 |
site | +0.013 |
Neg logit contributions | |
burn | -0.008 |
Woo | -0.007 |
y | -0.007 |
their | -0.007 |
ety | -0.007 |
Token | squeeze |
Token ID | 21229 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
burn | +0.007 |
y | +0.007 |
free | +0.007 |
Woo | +0.007 |
their | +0.006 |
Neg logit contributions | |
quest | -0.012 |
exhibit | -0.010 |
site | -0.010 |
ement | -0.010 |
mission | -0.010 |
Token | her |
Token ID | 607 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
quest | +0.016 |
ement | +0.016 |
ently | +0.016 |
site | +0.016 |
exhibit | +0.015 |
Neg logit contributions | |
burn | -0.013 |
groom | -0.011 |
band | -0.010 |
ety | -0.010 |
asc | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
quest | +0.017 |
ement | +0.015 |
exhibit | +0.015 |
site | +0.015 |
ently | +0.014 |
Neg logit contributions | |
burn | -0.012 |
Woo | -0.011 |
y | -0.010 |
their | -0.010 |
ety | -0.010 |
Token | she |
Token ID | 673 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
quest | +0.013 |
repairs | +0.011 |
site | +0.011 |
exhibit | +0.011 |
mission | +0.011 |
Neg logit contributions | |
y | -0.008 |
burn | -0.008 |
Woo | -0.007 |
free | -0.007 |
ety | -0.007 |
Token | will |
Token ID | 481 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
quest | +0.026 |
ement | +0.024 |
site | +0.022 |
exhibit | +0.022 |
ently | +0.022 |
Neg logit contributions | |
burn | -0.016 |
Woo | -0.014 |
their | -0.014 |
y | -0.014 |
C | -0.013 |
Token | laugh |
Token ID | 6487 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
burn | +0.042 |
y | +0.040 |
ksh | +0.037 |
ety | +0.036 |
Av | +0.036 |
Neg logit contributions | |
quest | -0.069 |
mission | -0.059 |
site | -0.058 |
repairs | -0.057 |
lair | -0.056 |
Token | ." |
Token ID | 526 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
burn | +0.005 |
ety | +0.004 |
Woo | +0.004 |
groom | +0.004 |
Av | +0.004 |
Neg logit contributions | |
quest | -0.005 |
ement | -0.005 |
ently | -0.005 |
site | -0.004 |
lair | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
burn | +0.003 |
y | +0.003 |
their | +0.002 |
Woo | +0.002 |
groom | +0.002 |
Neg logit contributions | |
quest | -0.004 |
ement | -0.004 |
site | -0.004 |
ently | -0.004 |
exhibit | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
quest | +0.035 |
ement | +0.033 |
site | +0.031 |
ths | +0.031 |
ently | +0.031 |
Neg logit contributions | |
their | -0.015 |
burn | -0.015 |
Woo | -0.014 |
y | -0.013 |
Sara | -0.013 |
Token | Max |
Token ID | 11518 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
quest | +0.029 |
site | +0.027 |
ths | +0.027 |
ement | +0.026 |
ently | +0.026 |
Neg logit contributions | |
burn | -0.014 |
y | -0.012 |
Woo | -0.011 |
ety | -0.011 |
groom | -0.011 |
Token | kind |
Token ID | 1611 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
burn | +0.038 |
their | +0.035 |
y | +0.035 |
Woo | +0.034 |
Sara | +0.032 |
Neg logit contributions | |
quest | -0.054 |
ement | -0.051 |
site | -0.049 |
ently | -0.049 |
ths | -0.048 |
Token | man |
Token ID | 582 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
burn | +0.068 |
their | +0.062 |
Woo | +0.060 |
y | +0.059 |
ety | +0.058 |
Neg logit contributions | |
quest | -0.081 |
ement | -0.073 |
site | -0.071 |
exhibit | -0.069 |
ently | -0.068 |
Token | came |
Token ID | 1625 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
burn | +0.018 |
y | +0.017 |
their | +0.017 |
Woo | +0.016 |
C | +0.016 |
Neg logit contributions | |
quest | -0.029 |
ement | -0.027 |
site | -0.026 |
ently | -0.026 |
ths | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
burn | +0.001 |
Woo | +0.000 |
their | +0.000 |
y | +0.000 |
ot | +0.000 |
Neg logit contributions | |
quest | -0.001 |
ement | -0.001 |
site | -0.001 |
exhibit | -0.001 |
ently | -0.001 |
Token | helped |
Token ID | 4193 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
burn | +0.013 |
their | +0.012 |
y | +0.012 |
Woo | +0.012 |
Sara | +0.011 |
Neg logit contributions | |
quest | -0.018 |
ement | -0.017 |
site | -0.016 |
ently | -0.016 |
ths | -0.016 |
Token | restore |
Token ID | 11169 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
burn | +0.027 |
y | +0.024 |
Woo | +0.023 |
their | +0.022 |
ety | +0.021 |
Neg logit contributions | |
quest | -0.063 |
ement | -0.059 |
site | -0.058 |
ently | -0.057 |
ths | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
burn | +0.036 |
y | +0.030 |
Woo | +0.030 |
ety | +0.028 |
their | +0.028 |
Neg logit contributions | |
quest | -0.077 |
ement | -0.073 |
site | -0.071 |
ently | -0.070 |
ths | -0.068 |
Token | yard |
Token ID | 12699 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
quest | +0.009 |
ement | +0.008 |
ently | +0.008 |
ths | +0.008 |
site | +0.008 |
Neg logit contributions | |
burn | -0.007 |
their | -0.007 |
y | -0.006 |
groom | -0.006 |
Sara | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
quest | +0.044 |
ement | +0.041 |
site | +0.039 |
ently | +0.039 |
ths | +0.038 |
Neg logit contributions | |
burn | -0.024 |
their | -0.022 |
y | -0.021 |
Woo | -0.021 |
Sara | -0.019 |
Token | He |
Token ID | 679 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
burn | +0.012 |
their | +0.011 |
Woo | +0.011 |
y | +0.011 |
Sara | +0.010 |
Neg logit contributions | |
quest | -0.021 |
ement | -0.020 |
site | -0.019 |
ently | -0.019 |
ths | -0.019 |
Token | planted |
Token ID | 18969 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
quest | +0.019 |
ement | +0.018 |
ently | +0.017 |
site | +0.017 |
exhibit | +0.016 |
Neg logit contributions | |
their | -0.009 |
y | -0.009 |
burn | -0.009 |
ot | -0.008 |
her | -0.008 |
Token | ally |
Token ID | 453 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
quest | +0.010 |
site | +0.009 |
ement | +0.009 |
lair | +0.009 |
exhibit | +0.009 |
Neg logit contributions | |
burn | -0.009 |
y | -0.009 |
ety | -0.008 |
their | -0.008 |
Woo | -0.008 |
Token | said |
Token ID | 531 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
quest | +0.049 |
ement | +0.046 |
site | +0.044 |
ently | +0.043 |
ths | +0.042 |
Neg logit contributions | |
burn | -0.030 |
y | -0.028 |
their | -0.027 |
Woo | -0.026 |
ot | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
quest | +0.027 |
ement | +0.026 |
ently | +0.025 |
site | +0.023 |
ths | +0.023 |
Neg logit contributions | |
burn | -0.034 |
ety | -0.032 |
y | -0.030 |
groom | -0.030 |
Woo | -0.030 |
Token | " |
Token ID | 366 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
quest | +0.008 |
ement | +0.008 |
site | +0.008 |
ently | +0.008 |
ths | +0.007 |
Neg logit contributions | |
burn | -0.007 |
y | -0.006 |
ety | -0.006 |
Woo | -0.006 |
their | -0.006 |
Token | Then |
Token ID | 6423 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
burn | +0.010 |
their | +0.009 |
y | +0.008 |
Woo | +0.008 |
ot | +0.008 |
Neg logit contributions | |
quest | -0.017 |
ement | -0.016 |
ths | -0.016 |
site | -0.016 |
ently | -0.016 |
Token | give |
Token ID | 1577 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
quest | +0.085 |
ement | +0.081 |
site | +0.078 |
ently | +0.077 |
ths | +0.075 |
Neg logit contributions | |
burn | -0.040 |
their | -0.037 |
y | -0.035 |
Woo | -0.035 |
Sara | -0.034 |
Token | me |
Token ID | 502 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
burn | +0.051 |
y | +0.046 |
Woo | +0.045 |
their | +0.044 |
groom | +0.044 |
Neg logit contributions | |
quest | -0.072 |
ement | -0.066 |
ths | -0.064 |
site | -0.063 |
ently | -0.063 |
Token | a |
Token ID | 257 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
quest | +0.091 |
ement | +0.082 |
exhibit | +0.081 |
ently | +0.081 |
site | +0.080 |
Neg logit contributions | |
burn | -0.047 |
y | -0.044 |
ety | -0.041 |
Woo | -0.040 |
their | -0.039 |
Token | kiss |
Token ID | 9245 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
quest | +0.028 |
ement | +0.024 |
site | +0.024 |
exhibit | +0.023 |
mission | +0.023 |
Neg logit contributions | |
burn | -0.019 |
y | -0.018 |
their | -0.018 |
Woo | -0.017 |
ety | -0.017 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ety | +0.030 |
Av | +0.029 |
Woo | +0.029 |
burn | +0.028 |
their | +0.028 |
Neg logit contributions | |
quest | -0.032 |
ement | -0.031 |
ently | -0.029 |
exhibit | -0.029 |
site | -0.028 |
Token | |
Token ID | 220 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
quest | +0.005 |
site | +0.005 |
ement | +0.005 |
ths | +0.005 |
lair | +0.005 |
Neg logit contributions | |
their | -0.002 |
burn | -0.002 |
Woo | -0.002 |
y | -0.002 |
Sara | -0.002 |