TOP ACTIVATIONS
MAX = 10.533

have stopped the rh in oc eros . He is sleeping
try to grab the av oc ados . But the rock
They forget about the av oc ados . They just want
back to the rh in oc eros and showed it what
to pet the rh in oc eros . It looked so
unicorn took the rh in oc eros to a nearby pond
food for the rh in oc eros and his friends .
to see the rh in oc eros anymore . He is
happened to the rh in oc eros , but it was
and took the rh in oc eros home with her .
wait until the rh in oc eros is gone ."
care of the rh in oc eros and it needed to
store to get more av oc ados . Gary looked at
had never seen the av oc ados . They wished they
to help the rh in oc eros . The zo oke
thanked the elderly rh in oc eros for his wonderful surprise
net on the rh in oc eros . They put the
and hugged the rh in oc eros . He finally understood
trapped with the rh in oc eros . They looked for
will visit the rh in oc eros at the zoo .

MIN ACTIVATIONS
MIN = -9.294

. He was a mis chie vous little baby and always
, but it didn 't seem to work . He got
, but it didn 't seem to work . The star
didn â t seem to work .
, but it didn 't seem tasty to her . She
didn â t seem to be ending . Diana
answer , but it did seem to move away from Bob
, but it didn 't seem to change much .
. <|endoftext|> Joe y had been a very obedient boy yesterday
, but it didn 't seem to notice anything . Sandy
" Yes , it does seem friendly . But we have
, but he didn 't seem to win very often .
, but it didn 't seem to work . Lily laughed
, but she said they didn 't have a plan yet
<|endoftext|> Peter was a mis chie vous 3 year old who
her come back . You seem like a good boy .
. But Coco did not seem to understand . He would
it . <|endoftext|> Sam had been playing with his friends all
, but he didn 't seem to be getting bigger or
little boy named Joe had been feeling restless . His mom

INTERVAL 5.576 - 10.533
CONTAINS 1.771%

Things had been moved around and the sand was in different
kids learned about the jewel and asked to come and see
She walked up to it and knocked on the door .
flower was growing even bigger and brighter . The comet was
! She thanked the man and sailed away . It was

INTERVAL 0.619 - 5.576
CONTAINS 43.077%

Peter was sad that the ot ter was gone , but
. On Monday morning , the family gathered
, but she was brave and decided to go in anyway
was messy , sticks poking out and leaves all over the
, her mom my helped her get ready for class by

INTERVAL -4.338 - 0.619
CONTAINS 45.922%

big k ite with a colorful tail . Anna and her
do you have in the jar ?" he asked .
It hurts my mouth . It is not tasty . It
wise owl knew what to do . He took the nail
with her new friend . They would play games , tell

INTERVAL -9.294 - -4.338
CONTAINS 9.230%

vine too , but I am too small ." Bob o
ways to enjoy broccoli ." L ily was still
rabbit named Peter . He was a spoiled rabbit , living
the garden . They are not happy . "
kept playing the drum . Joe kept playing his
Token have
Token ID423
Feature activation-4.27e+00

Pos logit contributions
 Su+0.034
 Suz+0.034
 Sus+0.034
 Mill+0.033
 Alf+0.033
Neg logit contributions
wy-0.020
istered-0.019
ggy-0.019
 ruined-0.019
 sharp-0.018
Token stopped
Token ID5025
Feature activation-9.02e-02

Pos logit contributions
wy+0.074
istered+0.070
uch+0.068
 ruined+0.068
ggy+0.067
Neg logit contributions
 Su-0.109
 Suz-0.107
 Sus-0.106
 Mill-0.106
 Alf-0.105
Token the
Token ID262
Feature activation+1.38e+00

Pos logit contributions
 ruined+0.002
wy+0.002
 sharp+0.002
 burns+0.002
ggy+0.002
Neg logit contributions
 Suz-0.002
 Su-0.002
 Mill-0.002
 Sus-0.002
 Alf-0.002
Token rh
Token ID9529
Feature activation+1.98e+00

Pos logit contributions
 Suz+0.029
 Su+0.029
 Mill+0.028
 Sus+0.028
 Jan+0.027
Neg logit contributions
 ruined-0.031
 sharp-0.029
wy-0.029
ggy-0.029
 pain-0.028
Tokenin
Token ID259
Feature activation+2.53e+00

Pos logit contributions
 Alf+0.045
 Su+0.045
 Suz+0.045
 Sus+0.044
 Mill+0.044
Neg logit contributions
 ruined-0.034
wy-0.034
 sharp-0.034
istered-0.033
 sting-0.033
Tokenoc
Token ID420
Feature activation+1.05e+01

Pos logit contributions
 Suz+0.047
 Su+0.046
 Sus+0.045
 Mill+0.045
 Jan+0.041
Neg logit contributions
 ruined-0.064
ggy-0.062
wy-0.062
 burns-0.061
 sharp-0.061
Tokeneros
Token ID27498
Feature activation+2.09e+00

Pos logit contributions
 Suz+0.246
 Su+0.238
 Mill+0.238
 Sus+0.234
 Ally+0.231
Neg logit contributions
wy-0.219
ps-0.215
 ruined-0.213
 burns-0.212
ggy-0.211
Token.
Token ID13
Feature activation+2.46e+00

Pos logit contributions
 Suz+0.060
 Su+0.059
 Mill+0.058
 Sus+0.058
 Alf+0.056
Neg logit contributions
 ruined-0.032
wy-0.030
ggy-0.029
 sharp-0.029
 burns-0.028
Token He
Token ID679
Feature activation-5.60e-01

Pos logit contributions
 Suz+0.051
 Mill+0.050
 Su+0.048
 Sus+0.047
 Ally+0.046
Neg logit contributions
 burns-0.049
 ruined-0.048
 pain-0.046
 sharp-0.046
istered-0.046
Token is
Token ID318
Feature activation-5.57e+00

Pos logit contributions
wy+0.010
istered+0.009
kin+0.009
ggie+0.009
ggy+0.009
Neg logit contributions
 Alf-0.014
 Suz-0.013
 Sus-0.013
 Su-0.013
 Mill-0.013
Token sleeping
Token ID11029
Feature activation+8.39e-01

Pos logit contributions
wy+0.104
uch+0.100
istered+0.097
arest+0.094
ggy+0.092
Neg logit contributions
 Su-0.135
 Sus-0.133
 Suz-0.132
 Alf-0.132
 Mill-0.130
Token try
Token ID1949
Feature activation-4.37e-01

Pos logit contributions
 Suz+0.131
 Su+0.128
 Alf+0.127
 Mill+0.127
 Sus+0.124
Neg logit contributions
wy-0.100
 ruined-0.099
ggy-0.096
ggie-0.095
uch-0.093
Token to
Token ID284
Feature activation+1.29e+00

Pos logit contributions
 ruined+0.010
 sharp+0.010
ggy+0.010
wy+0.010
 sting+0.009
Neg logit contributions
 Suz-0.009
 Su-0.009
 Mill-0.009
 Sus-0.008
 Alf-0.008
Token grab
Token ID5552
Feature activation+1.74e+00

Pos logit contributions
 Suz+0.023
 Mill+0.022
 Su+0.022
 Twe+0.021
line+0.021
Neg logit contributions
istered-0.032
 ruined-0.030
wy-0.030
 burns-0.028
 horrible-0.028
Token the
Token ID262
Feature activation+1.52e+00

Pos logit contributions
 Suz+0.033
 Su+0.033
 Sus+0.032
 Mill+0.032
 Alf+0.031
Neg logit contributions
 ruined-0.042
wy-0.042
ggy-0.041
istered-0.040
uch-0.040
Token av
Token ID1196
Feature activation+2.12e-01

Pos logit contributions
 Suz+0.031
 Mill+0.030
 Sus+0.030
 Su+0.030
 Alf+0.029
Neg logit contributions
ggy-0.035
ggie-0.034
wy-0.033
istered-0.033
 ruined-0.032
Tokenoc
Token ID420
Feature activation+1.05e+01

Pos logit contributions
 Suz+0.003
 Su+0.003
 Mill+0.003
 Sus+0.003
 Alf+0.003
Neg logit contributions
 ruined-0.006
wy-0.006
ggy-0.006
 sharp-0.006
istered-0.006
Tokenados
Token ID22484
Feature activation+7.48e-02

Pos logit contributions
 Suz+0.154
 Su+0.151
 Sus+0.147
 Mill+0.143
 Alf+0.136
Neg logit contributions
wy-0.306
 ruined-0.295
 sharp-0.291
 burns-0.290
ggy-0.290
Token.
Token ID13
Feature activation+1.98e+00

Pos logit contributions
 Suz+0.002
 Su+0.002
 Mill+0.002
 Sus+0.002
 Alf+0.002
Neg logit contributions
wy-0.002
 ruined-0.002
ggy-0.001
ggie-0.001
istered-0.001
Token But
Token ID887
Feature activation+4.42e+00

Pos logit contributions
 Suz+0.043
 Mill+0.043
 Alf+0.041
 Sus+0.041
 Jan+0.040
Neg logit contributions
 sharp-0.038
 ruined-0.037
 sting-0.037
ggy-0.037
 burns-0.037
Token the
Token ID262
Feature activation-1.78e-01

Pos logit contributions
 Suz+0.093
 Mill+0.092
 Su+0.092
 Sus+0.090
 Alf+0.090
Neg logit contributions
 ruined-0.098
 sharp-0.092
 hurt-0.091
wy-0.090
 bad-0.090
Token rock
Token ID3881
Feature activation-5.91e-01

Pos logit contributions
ggy+0.004
wy+0.004
ggie+0.004
 ruined+0.004
istered+0.004
Neg logit contributions
 Mill-0.004
 Suz-0.004
 Su-0.004
 Sus-0.004
 Alf-0.004
Token They
Token ID1119
Feature activation-8.77e-01

Pos logit contributions
 Suz+0.045
 Mill+0.044
 Alf+0.043
 Su+0.043
 Sus+0.042
Neg logit contributions
 ruined-0.056
 burns-0.054
 sharp-0.054
ggy-0.053
 sting-0.053
Token forget
Token ID6044
Feature activation+5.98e-01

Pos logit contributions
wy+0.018
ggy+0.017
ggie+0.017
istered+0.017
 ruined+0.017
Neg logit contributions
 Su-0.020
 Suz-0.020
 Sus-0.019
 Alf-0.019
 Mill-0.018
Token about
Token ID546
Feature activation+1.79e+00

Pos logit contributions
 Suz+0.016
 Mill+0.016
 Su+0.016
 Alf+0.016
 Sus+0.016
Neg logit contributions
 ruined-0.009
 bad-0.009
 sharp-0.009
ggy-0.009
 burns-0.008
Token the
Token ID262
Feature activation+7.30e-01

Pos logit contributions
 Suz+0.038
 Mill+0.037
 Su+0.037
 Alf+0.037
 Sus+0.036
Neg logit contributions
 ruined-0.040
 sharp-0.038
wy-0.037
ggy-0.037
 pain-0.036
Token av
Token ID1196
Feature activation+2.24e-01

Pos logit contributions
 Suz+0.017
 Su+0.017
 Mill+0.017
 Sus+0.017
 Alf+0.016
Neg logit contributions
wy-0.014
ggy-0.014
ggie-0.013
 ruined-0.013
istered-0.013
Tokenoc
Token ID420
Feature activation+1.04e+01

Pos logit contributions
 Suz+0.003
 Su+0.003
 Mill+0.003
 Sus+0.003
 Alf+0.003
Neg logit contributions
 ruined-0.007
wy-0.007
ggy-0.006
 sharp-0.006
ggie-0.006
Tokenados
Token ID22484
Feature activation-2.61e-01

Pos logit contributions
 Suz+0.163
 Su+0.163
 Sus+0.155
 Mill+0.149
 Alf+0.145
Neg logit contributions
wy-0.298
 ruined-0.288
ps-0.284
 burns-0.283
uch-0.281
Token.
Token ID13
Feature activation+1.68e+00

Pos logit contributions
wy+0.005
 ruined+0.005
istered+0.005
ggy+0.005
ggie+0.005
Neg logit contributions
 Suz-0.006
 Su-0.006
 Mill-0.006
 Sus-0.006
 Alf-0.006
Token They
Token ID1119
Feature activation-9.93e-01

Pos logit contributions
 Suz+0.030
 Mill+0.029
 Su+0.029
 Sus+0.029
 Alf+0.028
Neg logit contributions
 ruined-0.042
ggy-0.040
 sharp-0.040
 burns-0.040
wy-0.040
Token just
Token ID655
Feature activation+1.67e+00

Pos logit contributions
wy+0.020
ggy+0.020
ggie+0.020
istered+0.020
uch+0.019
Neg logit contributions
 Suz-0.022
 Su-0.022
 Sus-0.021
 Alf-0.021
 Mill-0.020
Token want
Token ID765
Feature activation-1.45e+00

Pos logit contributions
 Suz+0.038
 Su+0.037
 Sus+0.037
 Mill+0.036
 Alf+0.036
Neg logit contributions
ggy-0.034
ggie-0.033
wy-0.033
istered-0.032
uch-0.031
Token back
Token ID736
Feature activation+2.83e+00

Pos logit contributions
 Suz+0.015
 Alf+0.015
 Mill+0.014
 Su+0.014
 Sus+0.014
Neg logit contributions
 sharp-0.012
 big-0.011
 ruined-0.011
wy-0.011
ps-0.011
Token to
Token ID284
Feature activation+3.50e+00

Pos logit contributions
 Cr+0.062
 Alf+0.061
 Suz+0.061
 Su+0.060
 Mill+0.059
Neg logit contributions
 sharp-0.053
 big-0.051
 ruined-0.051
 hurt-0.050
ggy-0.049
Token the
Token ID262
Feature activation+2.34e+00

Pos logit contributions
 Suz+0.078
 Mill+0.077
 Alf+0.076
 cities+0.074
 Jan+0.073
Neg logit contributions
 sharp-0.064
 ruined-0.064
 hurt-0.062
 pain-0.062
ggy-0.061
Token rh
Token ID9529
Feature activation+1.74e+00

Pos logit contributions
 Suz+0.048
 Su+0.047
 Mill+0.046
 Sus+0.046
 Alf+0.045
Neg logit contributions
 ruined-0.053
wy-0.053
ggy-0.051
 sharp-0.050
istered-0.050
Tokenin
Token ID259
Feature activation+2.88e+00

Pos logit contributions
 Alf+0.041
 Su+0.041
 Suz+0.041
 Sus+0.040
ress+0.039
Neg logit contributions
 ruined-0.031
wy-0.030
istered-0.029
 burns-0.029
 sting-0.029
Tokenoc
Token ID420
Feature activation+1.04e+01

Pos logit contributions
 Su+0.062
 Sus+0.061
 Suz+0.061
 Mill+0.059
 Ally+0.057
Neg logit contributions
ggy-0.063
 sharp-0.061
 hurt-0.060
 ruined-0.059
ggie-0.059
Tokeneros
Token ID27498
Feature activation+2.73e+00

Pos logit contributions
 Suz+0.274
 Mill+0.267
 Su+0.266
 Sus+0.264
 Ally+0.261
Neg logit contributions
ps-0.196
wy-0.188
ggy-0.187
 burns-0.181
ggie-0.181
Token and
Token ID290
Feature activation+7.05e+00

Pos logit contributions
 Suz+0.080
 Su+0.079
 Mill+0.077
 Sus+0.077
 Alf+0.076
Neg logit contributions
 ruined-0.036
ggy-0.036
 sharp-0.034
ggie-0.034
 hurt-0.033
Token showed
Token ID3751
Feature activation+3.62e+00

Pos logit contributions
 Suz+0.185
 Su+0.182
 Mill+0.182
 Alf+0.179
 Sus+0.178
Neg logit contributions
 ruined-0.113
 sharp-0.108
 hurt-0.105
ggy-0.105
wy-0.100
Token it
Token ID340
Feature activation-1.42e+00

Pos logit contributions
 Suz+0.072
 Mill+0.068
 Su+0.068
 Alf+0.066
 Sus+0.065
Neg logit contributions
 sharp-0.078
ggy-0.077
 ruined-0.076
ggie-0.076
wy-0.074
Token what
Token ID644
Feature activation-5.39e-01

Pos logit contributions
 ruined+0.032
 sharp+0.032
ggy+0.031
wy+0.030
ggie+0.030
Neg logit contributions
 Su-0.029
 Suz-0.028
 Mill-0.028
 Sus-0.027
 Alf-0.027
Token to
Token ID284
Feature activation-6.38e-01

Pos logit contributions
 ruined+0.064
wy+0.063
ggy+0.061
 sharp+0.061
ggie+0.060
Neg logit contributions
 Suz-0.054
 Su-0.053
 Mill-0.052
 Sus-0.052
 Alf-0.051
Token pet
Token ID4273
Feature activation+4.64e+00

Pos logit contributions
wy+0.015
istered+0.014
ery+0.013
kin+0.013
arest+0.013
Neg logit contributions
 Suz-0.014
 Su-0.014
 Mill-0.014
 Sus-0.014
 Twe-0.013
Token the
Token ID262
Feature activation+1.66e+00

Pos logit contributions
 Suz+0.105
 Su+0.100
 Mill+0.100
 Sus+0.099
 Alf+0.097
Neg logit contributions
 ruined-0.094
 sharp-0.092
wy-0.091
 hurt-0.089
ggy-0.088
Token rh
Token ID9529
Feature activation+1.73e+00

Pos logit contributions
 Alf+0.032
 Suz+0.032
 Su+0.032
 Mill+0.032
 Sus+0.031
Neg logit contributions
wy-0.038
 ruined-0.037
ggy-0.037
ggie-0.036
istered-0.036
Tokenin
Token ID259
Feature activation+2.65e+00

Pos logit contributions
 Alf+0.038
 Suz+0.037
 Sus+0.036
 Su+0.036
 Mill+0.036
Neg logit contributions
 ruined-0.032
 pain-0.031
istered-0.031
 sharp-0.031
wy-0.031
Tokenoc
Token ID420
Feature activation+1.03e+01

Pos logit contributions
 Suz+0.049
 Su+0.048
 Sus+0.047
 Mill+0.047
 Jan+0.043
Neg logit contributions
 ruined-0.066
ggy-0.066
wy-0.065
 sharp-0.064
ggie-0.064
Tokeneros
Token ID27498
Feature activation+2.18e+00

Pos logit contributions
 Suz+0.248
 Su+0.243
 Mill+0.237
 Sus+0.236
 Ally+0.230
Neg logit contributions
wy-0.211
ps-0.203
ggy-0.201
 burns-0.200
 ruined-0.199
Token.
Token ID13
Feature activation+2.09e+00

Pos logit contributions
 Suz+0.059
 Su+0.059
 Mill+0.058
 Sus+0.058
 Alf+0.057
Neg logit contributions
 ruined-0.035
wy-0.034
ggy-0.033
 sharp-0.032
ggie-0.031
Token It
Token ID632
Feature activation-2.47e+00

Pos logit contributions
 Suz+0.044
 Su+0.043
 Mill+0.042
 Sus+0.042
 Alf+0.041
Neg logit contributions
 ruined-0.044
ggy-0.043
 sharp-0.043
wy-0.043
 burns-0.042
Token looked
Token ID3114
Feature activation-3.56e+00

Pos logit contributions
wy+0.049
arest+0.046
istered+0.045
kin+0.045
itch+0.043
Neg logit contributions
 Suz-0.058
 Mill-0.057
 Su-0.055
 Sus-0.054
 Alf-0.054
Token so
Token ID523
Feature activation-9.30e-01

Pos logit contributions
wy+0.055
ggy+0.054
ggie+0.052
uch+0.051
kin+0.049
Neg logit contributions
 Suz-0.098
 Sus-0.098
 Su-0.098
 Mill-0.097
 Alf-0.094
Token unicorn
Token ID44986
Feature activation+4.61e-01

Pos logit contributions
 Alf+0.043
 Suz+0.043
 Mill+0.043
 Su+0.043
 Sus+0.042
Neg logit contributions
wy-0.049
 ruined-0.048
istered-0.047
ggy-0.047
ggie-0.046
Token took
Token ID1718
Feature activation+1.32e+00

Pos logit contributions
 Su+0.012
 Suz+0.012
 Sus+0.012
 Mill+0.012
 Alf+0.011
Neg logit contributions
 ruined-0.008
 sharp-0.007
ggy-0.007
wy-0.007
ggie-0.007
Token the
Token ID262
Feature activation+1.64e+00

Pos logit contributions
 Suz+0.038
 Su+0.038
 Sus+0.037
 Mill+0.037
 Alf+0.036
Neg logit contributions
 ruined-0.018
 sharp-0.018
wy-0.017
 pain-0.017
ggy-0.017
Token rh
Token ID9529
Feature activation+1.56e+00

Pos logit contributions
 Alf+0.035
 Mill+0.035
 Suz+0.034
 Su+0.034
 Sus+0.033
Neg logit contributions
wy-0.034
ggy-0.034
 ruined-0.034
ggie-0.033
istered-0.033
Tokenin
Token ID259
Feature activation+2.29e+00

Pos logit contributions
 Alf+0.038
 Suz+0.037
 Su+0.037
 Sus+0.037
 Mill+0.037
Neg logit contributions
 ruined-0.027
wy-0.025
istered-0.025
 sting-0.025
 burns-0.025
Tokenoc
Token ID420
Feature activation+1.03e+01

Pos logit contributions
 Su+0.044
 Suz+0.043
 Sus+0.043
 Mill+0.041
 Jos+0.038
Neg logit contributions
 sharp-0.056
wy-0.056
 ruined-0.054
ggy-0.054
 burns-0.053
Tokeneros
Token ID27498
Feature activation+1.94e+00

Pos logit contributions
 Suz+0.244
 Su+0.240
 Mill+0.234
 Sus+0.233
 Ally+0.225
Neg logit contributions
wy-0.216
ps-0.208
ggy-0.206
ggie-0.202
 ruined-0.201
Token to
Token ID284
Feature activation+1.70e+00

Pos logit contributions
 Su+0.042
 Suz+0.041
 Sus+0.040
 Mill+0.038
 Alf+0.038
Neg logit contributions
 sharp-0.042
 ruined-0.042
 burns-0.040
ggy-0.039
 hurt-0.039
Token a
Token ID257
Feature activation-2.58e+00

Pos logit contributions
 Suz+0.044
 Su+0.043
 Mill+0.043
 Sus+0.043
 Alf+0.042
Neg logit contributions
 ruined-0.029
wy-0.028
 sharp-0.028
ggy-0.028
 sting-0.027
Token nearby
Token ID6716
Feature activation+1.94e+00

Pos logit contributions
 ruined+0.037
 sharp+0.036
ggy+0.034
wy+0.034
 bad+0.033
Neg logit contributions
 Suz-0.076
 Su-0.075
 Sus-0.073
 Mill-0.073
 Alf-0.072
Token pond
Token ID16723
Feature activation+9.05e-01

Pos logit contributions
 Suz+0.046
 Su+0.045
 Sus+0.045
 Mill+0.044
 Hil+0.042
Neg logit contributions
 sharp-0.039
 big-0.037
 ruined-0.036
 bad-0.035
 pain-0.035
Token food
Token ID2057
Feature activation+8.61e-01

Pos logit contributions
 Suz+0.015
 Su+0.015
 Sus+0.014
 Mill+0.014
 Alf+0.014
Neg logit contributions
wy-0.012
 ruined-0.012
 sharp-0.011
ggy-0.011
 burns-0.011
Token for
Token ID329
Feature activation+9.72e-01

Pos logit contributions
 Suz+0.018
 Su+0.018
 Sus+0.017
 Mill+0.017
 Alf+0.017
Neg logit contributions
 ruined-0.019
wy-0.019
 sharp-0.018
ggy-0.018
 burns-0.018
Token the
Token ID262
Feature activation+1.72e+00

Pos logit contributions
 Suz+0.022
 Su+0.021
 Sus+0.021
 Mill+0.020
 Alf+0.020
Neg logit contributions
 ruined-0.020
 sharp-0.020
ggy-0.019
wy-0.019
 bad-0.019
Token rh
Token ID9529
Feature activation+1.81e+00

Pos logit contributions
 Suz+0.041
 Su+0.040
 Mill+0.039
 Sus+0.039
 Alf+0.038
Neg logit contributions
 ruined-0.034
wy-0.033
 sharp-0.033
ggy-0.032
 pain-0.032
Tokenin
Token ID259
Feature activation+2.75e+00

Pos logit contributions
 Alf+0.043
 Suz+0.042
 Su+0.042
 Mill+0.041
 Sus+0.041
Neg logit contributions
 ruined-0.031
wy-0.030
 pain-0.030
 burns-0.030
 sting-0.030
Tokenoc
Token ID420
Feature activation+1.03e+01

Pos logit contributions
 Sus+0.058
 Su+0.057
 Suz+0.057
 Mill+0.055
 Jos+0.053
Neg logit contributions
ggy-0.062
wy-0.062
 ruined-0.060
 sharp-0.060
 hurt-0.059
Tokeneros
Token ID27498
Feature activation+1.68e+00

Pos logit contributions
 Suz+0.228
 Su+0.223
 Sus+0.219
 Mill+0.218
 Ally+0.209
Neg logit contributions
wy-0.229
ggy-0.221
 ruined-0.219
ggie-0.215
 burns-0.215
Token and
Token ID290
Feature activation+7.01e+00

Pos logit contributions
 Suz+0.047
 Su+0.047
 Sus+0.046
 Mill+0.046
 Alf+0.045
Neg logit contributions
 ruined-0.026
wy-0.025
ggy-0.024
 sharp-0.024
 burns-0.023
Token his
Token ID465
Feature activation+8.10e-01

Pos logit contributions
 Suz+0.170
 Su+0.169
 Sus+0.167
 Mill+0.162
 Alf+0.160
Neg logit contributions
 ruined-0.135
 sharp-0.129
wy-0.125
 burns-0.124
 hurt-0.124
Token friends
Token ID2460
Feature activation-4.68e-01

Pos logit contributions
 Suz+0.022
 Su+0.022
 Sus+0.022
 Mill+0.022
 Alf+0.021
Neg logit contributions
 ruined-0.013
wy-0.012
 sharp-0.012
ggy-0.012
 burns-0.011
Token.
Token ID13
Feature activation+2.58e+00

Pos logit contributions
 ruined+0.007
wy+0.007
ggy+0.007
 sharp+0.007
ggie+0.007
Neg logit contributions
 Suz-0.013
 Su-0.013
 Mill-0.012
 Sus-0.012
 Alf-0.012
Token to
Token ID284
Feature activation-1.76e+00

Pos logit contributions
 ruined+0.072
 sharp+0.070
 burns+0.068
wy+0.068
ggy+0.068
Neg logit contributions
 Suz-0.061
 Su-0.060
 Mill-0.058
 Sus-0.058
 Alf-0.057
Token see
Token ID766
Feature activation+1.59e+00

Pos logit contributions
wy+0.037
istered+0.035
 ruined+0.034
ery+0.033
 sharp+0.033
Neg logit contributions
 Su-0.041
 Suz-0.040
 Sus-0.039
 Mill-0.039
 Alf-0.039
Token the
Token ID262
Feature activation+5.55e-01

Pos logit contributions
 Suz+0.037
 Su+0.036
 Mill+0.036
 Sus+0.035
 Alf+0.034
Neg logit contributions
 ruined-0.032
 sharp-0.031
 bad-0.030
wy-0.030
 hurt-0.029
Token rh
Token ID9529
Feature activation+1.38e+00

Pos logit contributions
 Suz+0.011
 Su+0.011
 Mill+0.011
 Sus+0.011
 Alf+0.011
Neg logit contributions
wy-0.012
 ruined-0.012
ggy-0.012
istered-0.012
ggie-0.012
Tokenin
Token ID259
Feature activation+2.14e+00

Pos logit contributions
 Alf+0.032
 Suz+0.032
 Su+0.031
 Sus+0.031
 Mill+0.031
Neg logit contributions
 ruined-0.024
wy-0.024
 sharp-0.024
istered-0.023
 pain-0.023
Tokenoc
Token ID420
Feature activation+1.03e+01

Pos logit contributions
 Suz+0.039
 Su+0.038
 Mill+0.038
 Sus+0.038
 Jan+0.034
Neg logit contributions
 ruined-0.055
ggy-0.054
wy-0.053
 sharp-0.052
 burns-0.052
Tokeneros
Token ID27498
Feature activation+1.68e+00

Pos logit contributions
 Suz+0.242
 Su+0.236
 Mill+0.232
 Sus+0.230
 Ally+0.227
Neg logit contributions
wy-0.212
 ruined-0.208
ps-0.206
 burns-0.205
ggy-0.205
Token anymore
Token ID7471
Feature activation+8.53e-01

Pos logit contributions
 Suz+0.043
 Su+0.042
 Mill+0.042
 Sus+0.041
 Alf+0.041
Neg logit contributions
 ruined-0.029
wy-0.029
ggy-0.028
 sharp-0.027
ggie-0.027
Token.
Token ID13
Feature activation+1.69e+00

Pos logit contributions
 Suz+0.019
 Su+0.018
 Sus+0.018
 Mill+0.018
 Alf+0.018
Neg logit contributions
wy-0.017
 ruined-0.017
istered-0.016
uch-0.016
 sharp-0.016
Token He
Token ID679
Feature activation-8.06e-01

Pos logit contributions
 Suz+0.033
 Su+0.033
 Mill+0.032
 Sus+0.032
 Alf+0.030
Neg logit contributions
 ruined-0.038
 burns-0.037
 sharp-0.037
istered-0.036
wy-0.036
Token is
Token ID318
Feature activation-5.85e+00

Pos logit contributions
wy+0.014
istered+0.014
kin+0.014
arest+0.013
ggie+0.013
Neg logit contributions
 Alf-0.018
 Suz-0.017
 Mill-0.017
 Su-0.017
 K-0.017
Token happened
Token ID3022
Feature activation-1.04e+00

Pos logit contributions
wy+0.019
 ruined+0.019
istered+0.018
ggy+0.018
 sharp+0.018
Neg logit contributions
 Suz-0.018
 Su-0.018
 Mill-0.017
 Sus-0.017
 Alf-0.017
Token to
Token ID284
Feature activation+7.49e-01

Pos logit contributions
 ruined+0.021
wy+0.021
ggy+0.020
 sharp+0.019
istered+0.019
Neg logit contributions
 Suz-0.024
 Su-0.023
 Mill-0.023
 Sus-0.023
 Alf-0.023
Token the
Token ID262
Feature activation+2.02e+00

Pos logit contributions
 Suz+0.015
 Su+0.014
 Mill+0.014
 Sus+0.014
 Alf+0.014
Neg logit contributions
 ruined-0.017
wy-0.017
ggy-0.017
 sharp-0.017
ggie-0.016
Token rh
Token ID9529
Feature activation+1.94e+00

Pos logit contributions
 Mill+0.042
 Alf+0.042
 Suz+0.042
 Sus+0.042
 Su+0.041
Neg logit contributions
wy-0.044
 ruined-0.042
istered-0.041
ggy-0.041
ggie-0.040
Tokenin
Token ID259
Feature activation+3.02e+00

Pos logit contributions
 Alf+0.043
 Suz+0.041
ress+0.040
 Su+0.040
 Mill+0.040
Neg logit contributions
istered-0.036
 ruined-0.036
wy-0.035
 burns-0.035
 sting-0.034
Tokenoc
Token ID420
Feature activation+1.02e+01

Pos logit contributions
 Suz+0.056
 Su+0.055
 Sus+0.054
 Mill+0.052
 Jos+0.049
Neg logit contributions
ggy-0.076
 ruined-0.076
 sharp-0.073
wy-0.073
ggie-0.073
Tokeneros
Token ID27498
Feature activation+2.39e+00

Pos logit contributions
 Suz+0.239
 Su+0.234
 Mill+0.228
 Sus+0.228
 Ally+0.220
Neg logit contributions
wy-0.211
ggy-0.206
 ruined-0.205
ps-0.204
ggie-0.202
Token,
Token ID11
Feature activation+4.09e+00

Pos logit contributions
 Suz+0.062
 Su+0.061
 Mill+0.060
 Sus+0.060
 Alf+0.059
Neg logit contributions
 ruined-0.042
wy-0.040
ggy-0.039
 sharp-0.038
ggie-0.038
Token but
Token ID475
Feature activation+5.13e+00

Pos logit contributions
 Suz+0.100
 Mill+0.096
 Su+0.096
 Alf+0.095
 Sus+0.094
Neg logit contributions
 ruined-0.077
 sharp-0.074
 hurt-0.071
 bad-0.070
 pain-0.070
Token it
Token ID340
Feature activation-2.49e+00

Pos logit contributions
 Suz+0.108
 Su+0.108
 Mill+0.104
 Sus+0.102
 Alf+0.101
Neg logit contributions
 ruined-0.113
 sharp-0.107
ggy-0.106
 hurt-0.106
 bad-0.105
Token was
Token ID373
Feature activation-5.61e+00

Pos logit contributions
wy+0.049
istered+0.047
arest+0.044
 ruined+0.044
uch+0.043
Neg logit contributions
 Suz-0.058
 Mill-0.058
 Sus-0.056
 Su-0.056
 Alf-0.056
Token and
Token ID290
Feature activation+5.95e+00

Pos logit contributions
 Suz+0.069
 Su+0.068
 Mill+0.067
 Sus+0.067
 Alf+0.066
Neg logit contributions
 ruined-0.050
wy-0.048
ggy-0.047
 sharp-0.047
ggie-0.045
Token took
Token ID1718
Feature activation+9.77e-01

Pos logit contributions
 Suz+0.157
 Su+0.155
 Mill+0.153
 Alf+0.153
 Sus+0.150
Neg logit contributions
 ruined-0.104
 hurt-0.093
 sharp-0.091
 burns-0.089
 sting-0.089
Token the
Token ID262
Feature activation+7.50e-01

Pos logit contributions
 Suz+0.023
 Su+0.023
 Mill+0.022
 Sus+0.022
 Alf+0.022
Neg logit contributions
 ruined-0.019
wy-0.018
 sharp-0.018
ggy-0.018
 pain-0.018
Token rh
Token ID9529
Feature activation+1.31e+00

Pos logit contributions
 Suz+0.016
 Su+0.016
 Mill+0.016
 Sus+0.016
 Alf+0.016
Neg logit contributions
wy-0.016
 ruined-0.016
ggy-0.015
istered-0.015
ggie-0.015
Tokenin
Token ID259
Feature activation+2.06e+00

Pos logit contributions
 Alf+0.031
 Suz+0.031
 Su+0.031
 Sus+0.031
 Mill+0.031
Neg logit contributions
 ruined-0.022
wy-0.022
 pain-0.021
 sharp-0.021
 sting-0.021
Tokenoc
Token ID420
Feature activation+1.02e+01

Pos logit contributions
 Suz+0.045
 Sus+0.044
 Su+0.044
 Mill+0.043
 Jan+0.041
Neg logit contributions
ggy-0.045
 sharp-0.045
wy-0.044
 hurt-0.044
 ruined-0.044
Tokeneros
Token ID27498
Feature activation+1.47e+00

Pos logit contributions
 Suz+0.238
 Su+0.230
 Mill+0.227
 Sus+0.226
 Ally+0.218
Neg logit contributions
wy-0.216
ggy-0.209
 ruined-0.208
ps-0.207
 burns-0.205
Token home
Token ID1363
Feature activation+9.59e-01

Pos logit contributions
 Suz+0.027
 Su+0.027
 Sus+0.026
 Mill+0.026
 Alf+0.025
Neg logit contributions
 ruined-0.037
 sharp-0.036
 hurt-0.035
ggy-0.035
 burns-0.035
Token with
Token ID351
Feature activation+1.36e+00

Pos logit contributions
 Suz+0.026
 Su+0.026
 Mill+0.026
 Sus+0.026
 Alf+0.025
Neg logit contributions
 ruined-0.015
wy-0.014
ggy-0.014
 sharp-0.014
istered-0.013
Token her
Token ID607
Feature activation-8.59e-02

Pos logit contributions
 Suz+0.029
 Mill+0.029
 Su+0.028
 Sus+0.028
 Alf+0.027
Neg logit contributions
wy-0.031
uch-0.029
ggy-0.029
 ruined-0.029
ggie-0.029
Token.
Token ID13
Feature activation+2.01e+00

Pos logit contributions
wy+0.002
ggie+0.002
istered+0.002
uch+0.002
ggy+0.002
Neg logit contributions
 Mill-0.002
 Suz-0.002
 Su-0.002
 Sus-0.002
 Alf-0.002
Token wait
Token ID4043
Feature activation+4.79e-01

Pos logit contributions
wy+0.018
istered+0.018
ching+0.016
arest+0.016
uch+0.016
Neg logit contributions
 Su-0.017
 Suz-0.017
 Sus-0.017
 Mill-0.016
 Alf-0.015
Token until
Token ID1566
Feature activation+4.52e+00

Pos logit contributions
 Suz+0.009
 Su+0.009
 Mill+0.009
 Sus+0.009
 Alf+0.009
Neg logit contributions
 ruined-0.011
wy-0.011
ggy-0.011
 sharp-0.011
istered-0.011
Token the
Token ID262
Feature activation+8.12e-01

Pos logit contributions
 Suz+0.091
 Su+0.090
 Mill+0.089
 Sus+0.088
 Alf+0.086
Neg logit contributions
wy-0.103
 ruined-0.102
ggy-0.099
istered-0.097
 sharp-0.097
Token rh
Token ID9529
Feature activation+1.01e+00

Pos logit contributions
 Suz+0.018
 Su+0.017
 Mill+0.017
 Sus+0.017
 Alf+0.016
Neg logit contributions
 ruined-0.018
wy-0.017
 sharp-0.017
ggy-0.017
 pain-0.016
Tokenin
Token ID259
Feature activation+1.76e+00

Pos logit contributions
 Suz+0.024
 Su+0.023
 Alf+0.023
 Sus+0.023
 Mill+0.023
Neg logit contributions
 ruined-0.017
istered-0.017
wy-0.017
 sharp-0.017
 pain-0.017
Tokenoc
Token ID420
Feature activation+1.02e+01

Pos logit contributions
 Suz+0.034
 Sus+0.034
 Su+0.034
 Mill+0.034
 Ally+0.031
Neg logit contributions
 ruined-0.043
ggy-0.043
wy-0.042
 burns-0.041
ggie-0.041
Tokeneros
Token ID27498
Feature activation+1.12e+00

Pos logit contributions
 Suz+0.240
 Su+0.236
 Mill+0.234
 Sus+0.232
 Ally+0.229
Neg logit contributions
ps-0.210
wy-0.205
ggy-0.202
 burns-0.201
 ruined-0.197
Token is
Token ID318
Feature activation-4.18e+00

Pos logit contributions
 Suz+0.030
 Su+0.030
 Mill+0.030
 Sus+0.029
 Alf+0.029
Neg logit contributions
wy-0.017
 ruined-0.017
ggy-0.016
istered-0.016
 sharp-0.016
Token gone
Token ID3750
Feature activation-1.43e+00

Pos logit contributions
arest+0.070
ggy+0.069
istered+0.068
ggie+0.067
wy+0.066
Neg logit contributions
 Su-0.101
 Suz-0.099
 Sus-0.099
 Mill-0.098
 Alf-0.096
Token."
Token ID526
Feature activation+9.26e-01

Pos logit contributions
wy+0.026
 ruined+0.025
ggy+0.025
ggie+0.025
istered+0.024
Neg logit contributions
 Suz-0.035
 Su-0.034
 Mill-0.034
 Sus-0.034
 Alf-0.033
Token
Token ID198
Feature activation-5.18e+00

Pos logit contributions
 Suz+0.024
 Alf+0.024
 Mill+0.024
 Su+0.024
 Sus+0.023
Neg logit contributions
 ruined-0.014
 pain-0.013
 bad-0.013
 sting-0.013
 sharp-0.013
Token care
Token ID1337
Feature activation-1.77e+00

Pos logit contributions
 Suz+0.004
 Su+0.004
 Mill+0.004
 Sus+0.004
 Alf+0.004
Neg logit contributions
wy-0.003
 ruined-0.003
ggy-0.003
istered-0.003
ggie-0.003
Token of
Token ID286
Feature activation+3.78e+00

Pos logit contributions
wy+0.032
 ruined+0.031
ggy+0.030
ggie+0.030
 sharp+0.029
Neg logit contributions
 Suz-0.045
 Su-0.044
 Sus-0.043
 Mill-0.043
 Alf-0.042
Token the
Token ID262
Feature activation+1.48e+00

Pos logit contributions
 Suz+0.074
 Su+0.073
 Mill+0.072
 Sus+0.071
 Alf+0.070
Neg logit contributions
 ruined-0.088
wy-0.087
ggy-0.085
 sharp-0.084
ggie-0.082
Token rh
Token ID9529
Feature activation+1.70e+00

Pos logit contributions
 Suz+0.034
 Su+0.034
 Mill+0.034
 Sus+0.034
 Alf+0.033
Neg logit contributions
wy-0.029
 ruined-0.028
ggy-0.028
ggie-0.027
istered-0.027
Tokenin
Token ID259
Feature activation+2.99e+00

Pos logit contributions
 Alf+0.038
 Suz+0.037
 Sus+0.037
 Su+0.036
 Mill+0.036
Neg logit contributions
 ruined-0.031
 sting-0.030
 pain-0.030
wy-0.030
 sharp-0.030
Tokenoc
Token ID420
Feature activation+1.01e+01

Pos logit contributions
 Suz+0.055
 Su+0.055
 Sus+0.053
 Mill+0.053
 Ally+0.050
Neg logit contributions
 ruined-0.075
ggy-0.074
wy-0.073
 sharp-0.073
ggie-0.071
Tokeneros
Token ID27498
Feature activation+2.07e+00

Pos logit contributions
 Suz+0.231
 Su+0.227
 Mill+0.221
 Sus+0.221
 Ally+0.217
Neg logit contributions
wy-0.217
 ruined-0.208
ggy-0.207
 burns-0.206
ps-0.206
Token and
Token ID290
Feature activation+5.75e+00

Pos logit contributions
 Suz+0.055
 Su+0.054
 Mill+0.053
 Sus+0.053
 Alf+0.052
Neg logit contributions
 ruined-0.036
wy-0.034
ggy-0.033
 sharp-0.033
ggie-0.032
Token it
Token ID340
Feature activation-1.90e+00

Pos logit contributions
 Suz+0.134
 Su+0.133
 Mill+0.131
 Sus+0.130
 Alf+0.128
Neg logit contributions
 ruined-0.113
wy-0.111
ggy-0.107
 sharp-0.106
istered-0.103
Token needed
Token ID2622
Feature activation-3.25e+00

Pos logit contributions
wy+0.038
ggie+0.036
ggy+0.036
arest+0.035
istered+0.034
Neg logit contributions
 Suz-0.044
 Mill-0.043
 Sus-0.043
 Su-0.042
 Alf-0.041
Token to
Token ID284
Feature activation-3.79e-01

Pos logit contributions
 ruined+0.073
wy+0.072
ggy+0.070
 sharp+0.069
istered+0.068
Neg logit contributions
 Suz-0.067
 Su-0.066
 Mill-0.065
 Sus-0.065
 Alf-0.063
Token store
Token ID3650
Feature activation+3.67e+00

Pos logit contributions
 Suz+0.044
 Su+0.043
 Mill+0.042
 Sus+0.042
 Alf+0.041
Neg logit contributions
 ruined-0.051
wy-0.050
ggy-0.048
 sharp-0.048
ggie-0.047
Token to
Token ID284
Feature activation+2.65e+00

Pos logit contributions
 Suz+0.108
 Su+0.104
 Mill+0.103
 Ally+0.102
 Alf+0.102
Neg logit contributions
 ruined-0.048
 big-0.046
 broken-0.044
 not-0.042
 sharp-0.042
Token get
Token ID651
Feature activation-1.60e+00

Pos logit contributions
 Suz+0.053
 Su+0.053
 Mill+0.052
 Sus+0.052
 Alf+0.050
Neg logit contributions
wy-0.061
 ruined-0.061
ggy-0.059
istered-0.058
 sharp-0.058
Token more
Token ID517
Feature activation+2.70e-01

Pos logit contributions
 ruined+0.028
wy+0.027
 sharp+0.026
 bad+0.025
 hurt+0.025
Neg logit contributions
 Suz-0.042
 Su-0.041
 Mill-0.041
 Alf-0.040
 Sus-0.040
Token av
Token ID1196
Feature activation+5.01e-02

Pos logit contributions
 Suz+0.007
 Sus+0.007
 Mill+0.007
 Su+0.006
 Alf+0.006
Neg logit contributions
ggy-0.005
ggie-0.005
wy-0.005
 ruined-0.005
istered-0.005
Tokenoc
Token ID420
Feature activation+1.01e+01

Pos logit contributions
 Suz+0.001
 Su+0.001
 Mill+0.001
 Sus+0.001
 Alf+0.001
Neg logit contributions
 ruined-0.001
wy-0.001
ggy-0.001
 sharp-0.001
istered-0.001
Tokenados
Token ID22484
Feature activation-4.02e-01

Pos logit contributions
 Suz+0.143
 Su+0.140
 Sus+0.135
 Mill+0.133
 Alf+0.127
Neg logit contributions
wy-0.300
 ruined-0.291
ggy-0.289
 sharp-0.285
ps-0.284
Token.
Token ID13
Feature activation+2.71e+00

Pos logit contributions
 ruined+0.008
wy+0.008
ggy+0.007
 sharp+0.007
istered+0.007
Neg logit contributions
 Suz-0.009
 Su-0.009
 Mill-0.009
 Sus-0.009
 Alf-0.009
Token Gary
Token ID10936
Feature activation+6.86e-01

Pos logit contributions
 Su+0.051
 Suz+0.051
 Sus+0.049
 Mill+0.048
 Alf+0.047
Neg logit contributions
 ruined-0.065
wy-0.064
 sharp-0.063
ggy-0.062
 burns-0.062
Token looked
Token ID3114
Feature activation-2.81e+00

Pos logit contributions
 Suz+0.018
 Su+0.018
 Mill+0.018
 Sus+0.017
 Alf+0.017
Neg logit contributions
 ruined-0.011
wy-0.011
ggy-0.011
 sharp-0.011
ggie-0.010
Token at
Token ID379
Feature activation+2.78e+00

Pos logit contributions
 ruined+0.059
wy+0.057
 sharp+0.056
 bad+0.053
istered+0.053
Neg logit contributions
 Suz-0.063
 Su-0.062
 Mill-0.061
 Sus-0.060
 Alf-0.060
Token had
Token ID550
Feature activation-3.07e+00

Pos logit contributions
inkle+0.031
wy+0.031
itching+0.030
arest+0.030
 sting+0.030
Neg logit contributions
 Su-0.033
 Sus-0.033
 Suz-0.032
 Mill-0.032
 Alf-0.032
Token never
Token ID1239
Feature activation+3.40e-01

Pos logit contributions
wy+0.047
istered+0.047
inkle+0.044
ching+0.043
arest+0.043
Neg logit contributions
 Su-0.083
 Sus-0.081
 Mill-0.081
 Suz-0.081
 Alf-0.078
Token seen
Token ID1775
Feature activation+2.46e-01

Pos logit contributions
 Su+0.008
 Suz+0.008
 Sus+0.008
 Mill+0.008
 Alf+0.007
Neg logit contributions
istered-0.006
wy-0.006
itch-0.006
inkle-0.006
ggy-0.006
Token the
Token ID262
Feature activation+1.07e+00

Pos logit contributions
 Suz+0.005
 Su+0.005
 Mill+0.005
 Sus+0.005
 Alf+0.005
Neg logit contributions
wy-0.005
 ruined-0.005
ggy-0.005
istered-0.005
uch-0.005
Token av
Token ID1196
Feature activation-2.17e-01

Pos logit contributions
 Mill+0.023
 Su+0.023
 Sus+0.023
 Suz+0.023
 Alf+0.023
Neg logit contributions
wy-0.022
ggy-0.021
 ruined-0.021
istered-0.021
ggie-0.021
Tokenoc
Token ID420
Feature activation+1.00e+01

Pos logit contributions
 ruined+0.007
wy+0.006
ggy+0.006
ggie+0.006
 burns+0.006
Neg logit contributions
 Suz-0.003
 Mill-0.003
 Su-0.003
 Alf-0.002
 Sus-0.002
Tokenados
Token ID22484
Feature activation-5.71e-01

Pos logit contributions
 Suz+0.160
 Su+0.156
 Sus+0.149
 Mill+0.146
 Alf+0.140
Neg logit contributions
wy-0.282
 ruined-0.276
ggy-0.267
ps-0.266
 sharp-0.266
Token.
Token ID13
Feature activation+2.39e+00

Pos logit contributions
wy+0.013
 ruined+0.013
ggy+0.013
istered+0.012
ggie+0.012
Neg logit contributions
 Su-0.011
 Suz-0.011
 Sus-0.011
 Mill-0.011
 Alf-0.010
Token They
Token ID1119
Feature activation-3.68e-01

Pos logit contributions
 Suz+0.048
 Mill+0.046
 Su+0.046
 Sus+0.045
ress+0.043
Neg logit contributions
 ruined-0.054
 sharp-0.051
 pain-0.051
 bad-0.050
 burns-0.050
Token wished
Token ID16555
Feature activation+1.76e+00

Pos logit contributions
wy+0.009
uch+0.008
arest+0.008
ggy+0.008
ggie+0.008
Neg logit contributions
 Alf-0.007
 Su-0.007
 Suz-0.007
 Sus-0.007
 Mill-0.007
Token they
Token ID484
Feature activation-1.24e+00

Pos logit contributions
 Suz+0.033
 Mill+0.032
 Su+0.032
ress+0.032
 Ally+0.031
Neg logit contributions
 ruined-0.040
 bad-0.039
 not-0.038
 sharp-0.038
ggy-0.038
Token to
Token ID284
Feature activation-6.89e-01

Pos logit contributions
wy+0.074
 ruined+0.073
ggy+0.069
 sharp+0.069
istered+0.069
Neg logit contributions
 Suz-0.076
 Su-0.075
 Sus-0.075
 Mill-0.074
 Alf-0.072
Token help
Token ID1037
Feature activation+2.79e+00

Pos logit contributions
wy+0.016
istered+0.016
 ruined+0.014
uch+0.014
ifying+0.014
Neg logit contributions
 Suz-0.015
 Sus-0.014
 Mill-0.014
 Su-0.014
 Alf-0.013
Token the
Token ID262
Feature activation+1.81e+00

Pos logit contributions
 Suz+0.072
 Su+0.072
 Mill+0.070
 Sus+0.069
 Alf+0.069
Neg logit contributions
 ruined-0.046
 sharp-0.045
 hurt-0.044
ggy-0.044
 sting-0.042
Token rh
Token ID9529
Feature activation+1.62e+00

Pos logit contributions
 Suz+0.044
 Su+0.044
 Mill+0.043
 Sus+0.043
 Alf+0.042
Neg logit contributions
 ruined-0.034
wy-0.033
ggy-0.032
 sharp-0.031
istered-0.031
Tokenin
Token ID259
Feature activation+2.86e+00

Pos logit contributions
 Alf+0.039
 Suz+0.039
 Su+0.038
 Sus+0.038
 Mill+0.037
Neg logit contributions
wy-0.028
 ruined-0.028
istered-0.026
 pain-0.026
 sharp-0.026
Tokenoc
Token ID420
Feature activation+1.00e+01

Pos logit contributions
 Suz+0.057
 Su+0.057
 Sus+0.057
 Mill+0.056
 Ally+0.050
Neg logit contributions
ggy-0.067
 ruined-0.066
 hurt-0.065
 sharp-0.064
ggie-0.064
Tokeneros
Token ID27498
Feature activation+2.26e+00

Pos logit contributions
 Suz+0.237
 Mill+0.232
 Su+0.231
 Sus+0.228
 Ally+0.223
Neg logit contributions
ggy-0.206
wy-0.205
ps-0.203
ggie-0.200
 ruined-0.200
Token.
Token ID13
Feature activation+2.38e+00

Pos logit contributions
 Su+0.063
 Suz+0.063
 Mill+0.062
 Sus+0.062
 Alf+0.061
Neg logit contributions
 ruined-0.034
ggy-0.032
wy-0.031
 sharp-0.031
 hurt-0.031
Token The
Token ID383
Feature activation+1.49e+00

Pos logit contributions
 cities+0.070
 forth+0.063
 oceans+0.063
line+0.063
 discovering+0.062
Neg logit contributions
 ruined-0.025
 big-0.025
 two-0.023
ggy-0.023
 not-0.023
Token zo
Token ID40565
Feature activation+1.49e+00

Pos logit contributions
 Suz+0.037
 Su+0.037
 Mill+0.036
 Sus+0.036
 Alf+0.036
Neg logit contributions
 ruined-0.027
wy-0.027
ggy-0.026
 sharp-0.025
istered-0.025
Tokenoke
Token ID2088
Feature activation+2.40e+00

Pos logit contributions
 Suz+0.033
 Su+0.033
 Mill+0.033
 Sus+0.032
 Alf+0.031
Neg logit contributions
 ruined-0.031
wy-0.030
ggy-0.030
 sharp-0.029
ggie-0.029
Token thanked
Token ID26280
Feature activation+4.45e+00

Pos logit contributions
 Suz+0.038
 Su+0.037
 Mill+0.037
 Alf+0.037
 Sus+0.037
Neg logit contributions
 ruined-0.029
wy-0.028
ggy-0.027
 sharp-0.026
 hurt-0.026
Token the
Token ID262
Feature activation+2.44e+00

Pos logit contributions
 Suz+0.093
 Su+0.090
ress+0.088
line+0.087
 Sus+0.086
Neg logit contributions
 sharp-0.089
ggie-0.089
ggy-0.087
 ruined-0.086
 bad-0.086
Token elderly
Token ID13830
Feature activation+5.02e+00

Pos logit contributions
 Suz+0.057
 Su+0.056
 Sus+0.054
 Mill+0.054
 Jan+0.052
Neg logit contributions
 ruined-0.049
 sharp-0.048
wy-0.048
ggy-0.047
 bad-0.046
Token rh
Token ID9529
Feature activation+1.94e+00

Pos logit contributions
 Suz+0.116
 Su+0.115
 Sus+0.109
 Jos+0.106
 Mill+0.105
Neg logit contributions
ggy-0.103
 sharp-0.099
ggie-0.097
 ruined-0.096
 hurt-0.096
Tokenin
Token ID259
Feature activation+3.02e+00

Pos logit contributions
 Suz+0.053
 Su+0.052
 Mill+0.052
 Sus+0.051
 Alf+0.051
Neg logit contributions
 ruined-0.030
wy-0.029
 sharp-0.028
istered-0.028
 burns-0.027
Tokenoc
Token ID420
Feature activation+1.00e+01

Pos logit contributions
 Su+0.067
 Sus+0.065
 Suz+0.064
 Jos+0.060
 Mill+0.059
Neg logit contributions
ggy-0.064
ggie-0.061
wy-0.061
 sharp-0.060
ery-0.060
Tokeneros
Token ID27498
Feature activation+2.75e+00

Pos logit contributions
 Suz+0.243
 Su+0.241
 Sus+0.233
 Mill+0.230
 Jos+0.224
Neg logit contributions
wy-0.196
ps-0.196
ggy-0.195
ggie-0.191
 ruined-0.180
Token for
Token ID329
Feature activation+1.55e+00

Pos logit contributions
 Su+0.067
 Suz+0.066
 Sus+0.064
 Mill+0.062
 Hil+0.061
Neg logit contributions
ggy-0.048
ggie-0.048
 sharp-0.047
 ruined-0.046
 bad-0.045
Token his
Token ID465
Feature activation+9.64e-01

Pos logit contributions
 Suz+0.034
 Su+0.033
 Mill+0.032
 Sus+0.032
 Alf+0.032
Neg logit contributions
 ruined-0.033
ggy-0.031
 sharp-0.031
wy-0.031
ggie-0.031
Token wonderful
Token ID7932
Feature activation+2.41e+00

Pos logit contributions
 Suz+0.025
 Mill+0.024
 Su+0.024
 Sus+0.024
 Alf+0.024
Neg logit contributions
wy-0.017
 ruined-0.016
istered-0.015
ggy-0.015
uch-0.015
Token surprise
Token ID5975
Feature activation+2.18e+00

Pos logit contributions
 Suz+0.046
 Su+0.045
 Mill+0.045
 Sus+0.045
 Alf+0.043
Neg logit contributions
wy-0.058
 ruined-0.057
istered-0.055
ggy-0.054
 sharp-0.054
Token net
Token ID2010
Feature activation-9.44e-01

Pos logit contributions
wy+0.002
istered+0.002
ggy+0.002
 ruined+0.002
ggie+0.002
Neg logit contributions
 Alf-0.002
 Suz-0.002
 Su-0.002
 Mill-0.002
 Sus-0.002
Token on
Token ID319
Feature activation+2.14e+00

Pos logit contributions
 ruined+0.018
wy+0.018
ggy+0.017
 sharp+0.017
ggie+0.017
Neg logit contributions
 Suz-0.022
 Su-0.022
 Mill-0.022
 Sus-0.022
 Alf-0.021
Token the
Token ID262
Feature activation+2.40e+00

Pos logit contributions
 Suz+0.050
 Su+0.048
 Mill+0.048
 Sus+0.048
 Alf+0.046
Neg logit contributions
 ruined-0.042
 sharp-0.042
wy-0.041
ggy-0.041
ggie-0.040
Token rh
Token ID9529
Feature activation+1.67e+00

Pos logit contributions
 Suz+0.049
 Su+0.048
 Mill+0.048
 Alf+0.048
 Sus+0.047
Neg logit contributions
wy-0.052
 ruined-0.051
istered-0.050
ggy-0.050
uch-0.049
Tokenin
Token ID259
Feature activation+2.97e+00

Pos logit contributions
 Alf+0.038
 Suz+0.037
 Su+0.036
 Sus+0.036
ress+0.036
Neg logit contributions
 ruined-0.030
 sting-0.029
 pain-0.029
wy-0.029
istered-0.029
Tokenoc
Token ID420
Feature activation+9.99e+00

Pos logit contributions
 Suz+0.054
 Su+0.054
 Sus+0.054
 Mill+0.052
 Alf+0.048
Neg logit contributions
ggy-0.074
wy-0.074
 ruined-0.074
 sharp-0.073
ggie-0.072
Tokeneros
Token ID27498
Feature activation+2.53e+00

Pos logit contributions
 Suz+0.229
 Su+0.226
 Mill+0.221
 Sus+0.221
 Ally+0.210
Neg logit contributions
wy-0.212
ggy-0.204
 ruined-0.204
 burns-0.202
ps-0.202
Token.
Token ID13
Feature activation+1.46e+00

Pos logit contributions
 Suz+0.077
 Su+0.076
 Sus+0.075
 Mill+0.075
 Alf+0.072
Neg logit contributions
 ruined-0.034
ggy-0.032
wy-0.032
 sharp-0.032
 burns-0.031
Token They
Token ID1119
Feature activation-9.66e-01

Pos logit contributions
 Suz+0.034
 Mill+0.034
 Sus+0.033
ress+0.033
ie+0.033
Neg logit contributions
A-0.023
 burns-0.023
 big-0.023
 sharp-0.022
ggy-0.022
Token put
Token ID1234
Feature activation+1.95e+00

Pos logit contributions
wy+0.019
ggy+0.019
ggie+0.019
uch+0.018
istered+0.018
Neg logit contributions
 Alf-0.021
 Suz-0.021
 Su-0.021
 Mill-0.021
 Sus-0.020
Token the
Token ID262
Feature activation+1.49e-01

Pos logit contributions
 Suz+0.045
 Mill+0.044
 Su+0.044
 Sus+0.043
 Alf+0.042
Neg logit contributions
 ruined-0.040
wy-0.039
 sharp-0.039
ps-0.037
 burns-0.037
Token and
Token ID290
Feature activation+5.31e+00

Pos logit contributions
 ruined+0.031
 sharp+0.031
wy+0.029
istered+0.029
ggy+0.029
Neg logit contributions
 Su-0.044
 Suz-0.044
 Mill-0.042
 Sus-0.042
 Alf-0.041
Token hugged
Token ID41130
Feature activation+3.36e+00

Pos logit contributions
 Suz+0.133
 Su+0.131
 Mill+0.129
 Sus+0.128
 Alf+0.128
Neg logit contributions
 ruined-0.095
wy-0.090
 sharp-0.090
ggy-0.089
 sting-0.086
Token the
Token ID262
Feature activation+2.57e+00

Pos logit contributions
 Suz+0.086
 Hil+0.084
 Su+0.081
 Mill+0.081
 Alf+0.081
Neg logit contributions
 sharp-0.054
 bad-0.050
 pain-0.050
 big-0.049
 hurt-0.047
Token rh
Token ID9529
Feature activation+1.96e+00

Pos logit contributions
 Suz+0.056
 Su+0.055
 Mill+0.054
 Sus+0.054
 Alf+0.053
Neg logit contributions
 ruined-0.055
wy-0.054
 sharp-0.053
ggy-0.052
 sting-0.051
Tokenin
Token ID259
Feature activation+2.92e+00

Pos logit contributions
 Suz+0.046
 Alf+0.045
 Sus+0.045
 Su+0.045
 Mill+0.044
Neg logit contributions
 ruined-0.036
 pain-0.034
wy-0.034
istered-0.033
 sting-0.033
Tokenoc
Token ID420
Feature activation+9.96e+00

Pos logit contributions
 Su+0.059
 Suz+0.058
 Sus+0.057
 Mill+0.056
 Hil+0.053
Neg logit contributions
 sharp-0.068
ggy-0.067
wy-0.066
ggie-0.064
 ruined-0.063
Tokeneros
Token ID27498
Feature activation+2.31e+00

Pos logit contributions
 Suz+0.243
 Su+0.241
 Mill+0.233
 Sus+0.232
 Ally+0.230
Neg logit contributions
wy-0.196
ps-0.193
ggy-0.183
 burns-0.182
ggie-0.178
Token.
Token ID13
Feature activation+2.69e+00

Pos logit contributions
 Su+0.065
 Suz+0.065
 Sus+0.063
 Mill+0.063
 Alf+0.061
Neg logit contributions
 sharp-0.033
ggy-0.033
 ruined-0.033
ggie-0.032
wy-0.032
Token He
Token ID679
Feature activation+1.67e-01

Pos logit contributions
 Suz+0.060
 Su+0.058
 Mill+0.057
 Hil+0.056
 Sus+0.055
Neg logit contributions
 two-0.046
 sharp-0.044
 Deal-0.043
 big-0.042
A-0.041
Token finally
Token ID3443
Feature activation-9.64e-01

Pos logit contributions
 Suz+0.004
 Su+0.004
 Mill+0.004
 Sus+0.004
 Alf+0.004
Neg logit contributions
wy-0.003
istered-0.003
 ruined-0.003
uch-0.003
ggy-0.003
Token understood
Token ID7247
Feature activation+1.88e+00

Pos logit contributions
istered+0.022
wy+0.021
 burns+0.020
uch+0.020
ggy+0.020
Neg logit contributions
 Su-0.020
 Suz-0.020
 Mill-0.020
 Sus-0.020
 Alf-0.019
Token trapped
Token ID13640
Feature activation-1.27e+00

Pos logit contributions
wy+0.098
uch+0.097
arest+0.090
ggy+0.086
ggie+0.085
Neg logit contributions
 Suz-0.123
 Alf-0.121
 Mill-0.120
 Su-0.120
 Sus-0.118
Token with
Token ID351
Feature activation+6.75e-01

Pos logit contributions
wy+0.024
 ruined+0.024
ggy+0.023
 sharp+0.022
ggie+0.022
Neg logit contributions
 Suz-0.031
 Su-0.030
 Mill-0.030
 Sus-0.030
 Alf-0.029
Token the
Token ID262
Feature activation+1.04e+00

Pos logit contributions
 Suz+0.013
 Su+0.013
 Mill+0.013
 Sus+0.013
 Alf+0.013
Neg logit contributions
wy-0.016
 ruined-0.016
ggy-0.015
uch-0.015
istered-0.015
Token rh
Token ID9529
Feature activation+1.25e+00

Pos logit contributions
 Alf+0.022
 Su+0.022
 Suz+0.022
 Mill+0.022
 Sus+0.021
Neg logit contributions
wy-0.022
 ruined-0.021
ggy-0.021
istered-0.021
ggie-0.021
Tokenin
Token ID259
Feature activation+2.37e+00

Pos logit contributions
 Alf+0.029
 Suz+0.028
 Su+0.028
 Sus+0.028
 Mill+0.027
Neg logit contributions
 ruined-0.022
wy-0.022
istered-0.022
 pain-0.021
 sting-0.021
Tokenoc
Token ID420
Feature activation+9.95e+00

Pos logit contributions
 Suz+0.038
 Su+0.037
 Sus+0.036
 Mill+0.036
 Alf+0.034
Neg logit contributions
 ruined-0.065
wy-0.064
ggy-0.064
 sharp-0.063
ggie-0.062
Tokeneros
Token ID27498
Feature activation+1.58e+00

Pos logit contributions
 Suz+0.223
 Su+0.218
 Sus+0.215
 Mill+0.214
 Ally+0.205
Neg logit contributions
wy-0.210
ps-0.208
 ruined-0.207
ggy-0.206
 burns-0.203
Token.
Token ID13
Feature activation+1.16e+00

Pos logit contributions
 Suz+0.041
 Su+0.040
 Sus+0.040
 Mill+0.040
 Alf+0.039
Neg logit contributions
 ruined-0.028
wy-0.027
ggy-0.026
 sharp-0.026
ggie-0.025
Token They
Token ID1119
Feature activation-1.32e+00

Pos logit contributions
 Suz+0.019
 Su+0.019
 Mill+0.018
 Sus+0.018
 Alf+0.018
Neg logit contributions
 ruined-0.031
wy-0.031
ggy-0.030
 sharp-0.030
istered-0.029
Token looked
Token ID3114
Feature activation-3.45e+00

Pos logit contributions
wy+0.028
uch+0.027
arest+0.026
ggie+0.026
istered+0.026
Neg logit contributions
 Suz-0.028
 Alf-0.028
 Su-0.028
 Sus-0.027
 Mill-0.027
Token for
Token ID329
Feature activation-7.42e-01

Pos logit contributions
wy+0.081
 ruined+0.081
ggy+0.078
ggie+0.076
 sharp+0.076
Neg logit contributions
 Suz-0.067
 Su-0.066
 Mill-0.066
 Sus-0.065
 Alf-0.064
Token will
Token ID481
Feature activation-2.59e+00

Pos logit contributions
ggy+0.037
wy+0.036
ggie+0.036
kin+0.035
uch+0.035
Neg logit contributions
 Su-0.053
 Alf-0.052
 Suz-0.052
 Sus-0.051
 Mill-0.051
Token visit
Token ID3187
Feature activation+2.60e+00

Pos logit contributions
wy+0.049
 ruined+0.046
istered+0.046
ggy+0.043
uch+0.043
Neg logit contributions
 Suz-0.063
 Su-0.063
 Mill-0.063
 Alf-0.062
 Sus-0.062
Token the
Token ID262
Feature activation+1.30e+00

Pos logit contributions
 Suz+0.065
 Su+0.062
 Mill+0.060
 Hil+0.059
 Sus+0.059
Neg logit contributions
 ruined-0.048
 sharp-0.047
 bad-0.046
 hurt-0.046
ggy-0.045
Token rh
Token ID9529
Feature activation+1.69e+00

Pos logit contributions
 Suz+0.028
 Su+0.028
 Mill+0.027
 Sus+0.027
 Alf+0.025
Neg logit contributions
 ruined-0.029
 sharp-0.028
wy-0.028
ggy-0.027
 bad-0.027
Tokenin
Token ID259
Feature activation+2.42e+00

Pos logit contributions
 Alf+0.041
 Suz+0.040
 Su+0.040
 Sus+0.039
 Mill+0.039
Neg logit contributions
 ruined-0.029
wy-0.028
 pain-0.028
istered-0.028
 sting-0.028
Tokenoc
Token ID420
Feature activation+9.92e+00

Pos logit contributions
 Suz+0.059
 Su+0.058
 Sus+0.058
 Mill+0.056
 Jan+0.052
Neg logit contributions
ggy-0.049
 ruined-0.048
ggie-0.047
wy-0.046
 hurt-0.046
Tokeneros
Token ID27498
Feature activation+2.03e+00

Pos logit contributions
 Suz+0.245
 Su+0.242
 Sus+0.235
 Mill+0.235
 Ally+0.227
Neg logit contributions
wy-0.195
ggy-0.190
ps-0.189
 ruined-0.186
ggie-0.185
Token at
Token ID379
Feature activation+2.92e+00

Pos logit contributions
 Suz+0.055
 Su+0.055
 Sus+0.053
 Mill+0.053
 Jan+0.050
Neg logit contributions
 ruined-0.034
ggy-0.033
wy-0.033
ggie-0.033
 sharp-0.032
Token the
Token ID262
Feature activation+8.46e-01

Pos logit contributions
 Suz+0.069
 Su+0.067
 Sus+0.065
 Mill+0.064
iked+0.062
Neg logit contributions
 ruined-0.057
 sharp-0.055
 bad-0.054
 big-0.054
 hurt-0.054
Token zoo
Token ID26626
Feature activation+3.04e+00

Pos logit contributions
 Suz+0.014
 Su+0.014
 Mill+0.014
 Sus+0.014
 Alf+0.013
Neg logit contributions
 ruined-0.022
wy-0.022
ggy-0.021
 sharp-0.021
ggie-0.021
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
 Suz+0.098
 Su+0.095
 Mill+0.095
 Sus+0.094
 Jan+0.089
Neg logit contributions
 ruined-0.037
ggy-0.037
ggie-0.035
 sharp-0.033
 bad-0.033
Token.
Token ID13
Feature activation+1.54e-01

Pos logit contributions
 Suz+0.010
 Su+0.010
 Sus+0.010
 Mill+0.010
 Alf+0.010
Neg logit contributions
 ruined-0.009
ggy-0.009
 sharp-0.009
wy-0.009
 hurt-0.009
Token He
Token ID679
Feature activation-1.75e+00

Pos logit contributions
 Suz+0.003
 Alf+0.003
line+0.003
 Su+0.003
 cities+0.003
Neg logit contributions
 pain-0.004
ggy-0.003
 ruined-0.003
ggie-0.003
 sharp-0.003
Token was
Token ID373
Feature activation-7.12e+00

Pos logit contributions
istered+0.040
wy+0.039
 Deal+0.038
arest+0.038
 ruined+0.037
Neg logit contributions
 Suz-0.033
 Su-0.032
 Sus-0.032
 Mill-0.032
 Alf-0.031
Token a
Token ID257
Feature activation-6.20e+00

Pos logit contributions
 ruined+0.086
wy+0.086
ggy+0.079
 sharp+0.077
istered+0.076
Neg logit contributions
 Suz-0.220
 Su-0.218
 Mill-0.216
 Sus-0.215
 Alf-0.212
Token mis
Token ID2984
Feature activation-3.93e+00

Pos logit contributions
wy+0.075
 ruined+0.072
ggy+0.067
ps+0.065
istered+0.065
Neg logit contributions
 Suz-0.191
 Su-0.190
 Mill-0.188
 Sus-0.188
 Alf-0.184
Tokenchie
Token ID3043
Feature activation-8.90e+00

Pos logit contributions
wy+0.066
 ruined+0.065
ggy+0.062
 sharp+0.062
istered+0.062
Neg logit contributions
 Suz-0.100
 Su-0.100
 Mill-0.099
 Sus-0.098
 Alf-0.098
Tokenvous
Token ID31222
Feature activation-2.89e+00

Pos logit contributions
ggy+0.112
wy+0.111
 ruined+0.110
ggie+0.105
 sharp+0.104
Neg logit contributions
 Suz-0.264
 Mill-0.262
 Su-0.261
 Sus-0.259
 Alf-0.259
Token little
Token ID1310
Feature activation+7.00e-01

Pos logit contributions
 ruined+0.054
 sharp+0.053
wy+0.051
ggy+0.051
 pain+0.051
Neg logit contributions
 Suz-0.069
 Su-0.067
 Mill-0.067
 Alf-0.066
 Sus-0.066
Token baby
Token ID5156
Feature activation+2.14e-01

Pos logit contributions
 Suz+0.015
 Su+0.015
 Mill+0.015
 Sus+0.014
 Alf+0.014
Neg logit contributions
 ruined-0.015
 sharp-0.015
wy-0.014
 hurt-0.014
 bad-0.014
Token and
Token ID290
Feature activation+4.00e+00

Pos logit contributions
 Suz+0.006
 Su+0.006
 Mill+0.006
 Alf+0.006
 Sus+0.006
Neg logit contributions
 ruined-0.003
ggy-0.003
 sharp-0.003
 hurt-0.003
wy-0.003
Token always
Token ID1464
Feature activation-6.96e-02

Pos logit contributions
 Suz+0.099
 Su+0.099
 Mill+0.097
 Sus+0.097
 Alf+0.095
Neg logit contributions
wy-0.072
 ruined-0.072
ggy-0.068
istered-0.068
 sharp-0.066
Token,
Token ID11
Feature activation+4.67e+00

Pos logit contributions
wy+0.023
 ruined+0.023
ggy+0.022
istered+0.021
uch+0.021
Neg logit contributions
 Suz-0.021
 Su-0.021
 Sus-0.020
 Mill-0.020
 Alf-0.020
Token but
Token ID475
Feature activation+5.73e+00

Pos logit contributions
 Suz+0.084
 Su+0.083
 Mill+0.082
 Sus+0.081
 Alf+0.079
Neg logit contributions
 ruined-0.117
wy-0.116
ggy-0.113
 sharp-0.111
istered-0.110
Token it
Token ID340
Feature activation-2.49e+00

Pos logit contributions
 Suz+0.109
 Su+0.108
 Mill+0.106
 Sus+0.104
 Alf+0.102
Neg logit contributions
 ruined-0.139
wy-0.135
 sharp-0.134
ggy-0.131
 burns-0.129
Token didn
Token ID1422
Feature activation-6.58e+00

Pos logit contributions
wy+0.053
istered+0.051
arest+0.050
 Deal+0.050
ggie+0.047
Neg logit contributions
 Suz-0.056
 Su-0.052
 Sus-0.052
 Mill-0.051
 Jan-0.051
Token't
Token ID470
Feature activation-4.45e+00

Pos logit contributions
wy+0.145
istered+0.132
 ruined+0.129
 tricked+0.120
aky+0.119
Neg logit contributions
 Suz-0.145
 Su-0.143
 Sus-0.142
 Alf-0.141
 Mill-0.141
Token seem
Token ID1283
Feature activation-8.65e+00

Pos logit contributions
wy+0.092
ggy+0.089
ggie+0.087
istered+0.087
 ruined+0.085
Neg logit contributions
 Suz-0.103
 Sus-0.100
 Su-0.099
 Mill-0.099
 Alf-0.098
Token to
Token ID284
Feature activation-2.34e+00

Pos logit contributions
wy+0.192
ggy+0.186
uch+0.183
ggie+0.180
 ruined+0.175
Neg logit contributions
 Su-0.184
 Suz-0.183
 Sus-0.183
 Mill-0.181
 Alf-0.172
Token work
Token ID670
Feature activation-3.47e+00

Pos logit contributions
wy+0.049
istered+0.048
ggy+0.045
ggie+0.044
 ruined+0.043
Neg logit contributions
 Suz-0.053
 Sus-0.052
 Mill-0.050
 Su-0.050
 Alf-0.048
Token.
Token ID13
Feature activation+1.73e+00

Pos logit contributions
wy+0.069
uch+0.068
 sting+0.068
ggy+0.068
istered+0.068
Neg logit contributions
 Sus-0.077
 Su-0.076
 Suz-0.073
 Mill-0.073
 Alf-0.072
Token He
Token ID679
Feature activation-8.98e-01

Pos logit contributions
 Suz+0.037
 Jos+0.037
 Su+0.036
 Hil+0.036
 Sus+0.036
Neg logit contributions
 sharp-0.034
ggy-0.034
ggie-0.033
 burns-0.032
 big-0.031
Token got
Token ID1392
Feature activation-3.51e+00

Pos logit contributions
istered+0.019
wy+0.018
arest+0.018
 Deal+0.017
vern+0.017
Neg logit contributions
 Suz-0.020
 Su-0.019
 Sus-0.019
 Alf-0.018
 Mill-0.018
Token,
Token ID11
Feature activation+4.26e+00

Pos logit contributions
 Suz+0.050
 Su+0.050
 Mill+0.048
 Sus+0.048
 Alf+0.048
Neg logit contributions
 ruined-0.032
 sharp-0.032
wy-0.031
ggy-0.030
 sting-0.030
Token but
Token ID475
Feature activation+5.31e+00

Pos logit contributions
 Su+0.105
 Suz+0.105
 Alf+0.105
 Mill+0.103
 Sus+0.100
Neg logit contributions
 ruined-0.078
 sharp-0.078
 hurt-0.073
 broken-0.072
 pain-0.071
Token it
Token ID340
Feature activation-2.56e+00

Pos logit contributions
 Suz+0.125
 Su+0.122
 Alf+0.122
 Mill+0.121
bank+0.118
Neg logit contributions
 ruined-0.110
 hurt-0.104
 bad-0.102
 sharp-0.100
 broken-0.097
Token didn
Token ID1422
Feature activation-6.86e+00

Pos logit contributions
wy+0.052
istered+0.048
arest+0.047
ggy+0.046
 ruined+0.046
Neg logit contributions
 Suz-0.060
 Su-0.057
 Mill-0.057
 Sus-0.057
 Alf-0.055
Token't
Token ID470
Feature activation-4.35e+00

Pos logit contributions
wy+0.154
istered+0.138
 ruined+0.131
 tricked+0.125
ery+0.125
Neg logit contributions
 Suz-0.153
 Su-0.153
 Sus-0.152
 Mill-0.151
 Alf-0.146
Token seem
Token ID1283
Feature activation-8.63e+00

Pos logit contributions
wy+0.077
ggy+0.073
 ruined+0.073
ggie+0.071
istered+0.071
Neg logit contributions
 Suz-0.113
 Mill-0.111
 Sus-0.111
 Su-0.111
 Alf-0.108
Token to
Token ID284
Feature activation-2.30e+00

Pos logit contributions
wy+0.157
ggy+0.150
 ruined+0.145
ggie+0.145
uch+0.145
Neg logit contributions
 Suz-0.218
 Su-0.217
 Mill-0.216
 Sus-0.216
 Alf-0.207
Token work
Token ID670
Feature activation-3.99e+00

Pos logit contributions
wy+0.045
istered+0.044
ggy+0.043
ggie+0.042
 ruined+0.040
Neg logit contributions
 Suz-0.056
 Mill-0.056
 Sus-0.055
 Su-0.054
 Alf-0.053
Token.
Token ID13
Feature activation+1.92e+00

Pos logit contributions
wy+0.077
ggy+0.073
 ruined+0.073
istered+0.072
uch+0.072
Neg logit contributions
 Sus-0.094
 Su-0.094
 Suz-0.093
 Mill-0.093
 Alf-0.089
Token The
Token ID383
Feature activation+1.56e+00

Pos logit contributions
 Alf+0.047
 Suz+0.046
 Su+0.045
 cities+0.045
aro+0.044
Neg logit contributions
 ruined-0.029
 sharp-0.028
A-0.028
 two-0.028
 ripped-0.028
Token star
Token ID3491
Feature activation-6.33e-01

Pos logit contributions
 Sus+0.036
 Alf+0.036
 Suz+0.035
 Mill+0.035
 Su+0.034
Neg logit contributions
wy-0.031
istered-0.030
 ruined-0.027
ggy-0.027
uch-0.026
Token didn
Token ID1422
Feature activation-6.49e+00

Pos logit contributions
 Suz+0.029
 Su+0.029
 Mill+0.028
 Sus+0.028
 Alf+0.028
Neg logit contributions
 ruined-0.026
wy-0.026
 sharp-0.025
ggy-0.025
 burns-0.024
Tokenâ
Token ID22940
Feature activation+1.36e+00

Pos logit contributions
wy+0.140
istered+0.126
 ruined+0.122
aky+0.114
 sting+0.113
Neg logit contributions
 Sus-0.149
 Su-0.148
 Suz-0.147
 Mill-0.146
 Alf-0.144
Token
Token ID26391
Feature activation-1.37e+00

Pos logit contributions
 Su+0.030
 Suz+0.030
 Mill+0.029
 Sus+0.029
 Alf+0.028
Neg logit contributions
 ruined-0.028
wy-0.027
 sharp-0.027
istered-0.027
ggy-0.026
Token
Token ID8151
Feature activation-2.55e+00

Pos logit contributions
 ruined+0.024
wy+0.023
ggy+0.022
 sharp+0.022
ggie+0.022
Neg logit contributions
 Suz-0.035
 Su-0.035
 Mill-0.034
 Sus-0.034
 Alf-0.033
Tokent
Token ID83
Feature activation-4.08e+00

Pos logit contributions
 ruined+0.032
wy+0.032
ggy+0.030
 sharp+0.029
istered+0.028
Neg logit contributions
 Suz-0.077
 Su-0.076
 Mill-0.075
 Sus-0.075
 Alf-0.074
Token seem
Token ID1283
Feature activation-8.61e+00

Pos logit contributions
 ruined+0.069
wy+0.069
ggy+0.065
 sharp+0.064
istered+0.063
Neg logit contributions
 Suz-0.107
 Su-0.105
 Mill-0.104
 Sus-0.104
 Alf-0.102
Token to
Token ID284
Feature activation-2.30e+00

Pos logit contributions
wy+0.162
ggy+0.155
uch+0.152
ggie+0.149
 ruined+0.148
Neg logit contributions
 Su-0.212
 Sus-0.211
 Suz-0.210
 Mill-0.209
 Alf-0.201
Token work
Token ID670
Feature activation-3.58e+00

Pos logit contributions
wy+0.047
istered+0.045
ggy+0.043
 ruined+0.041
ggie+0.041
Neg logit contributions
 Sus-0.054
 Suz-0.054
 Mill-0.054
 Su-0.053
 Alf-0.051
Token.
Token ID13
Feature activation+1.19e+00

Pos logit contributions
wy+0.067
 ruined+0.064
ggy+0.064
 sting+0.064
uch+0.063
Neg logit contributions
 Sus-0.085
 Su-0.085
 Suz-0.084
 Mill-0.083
 Alf-0.081
Token
Token ID198
Feature activation-5.63e+00

Pos logit contributions
 Suz+0.030
 Ally+0.029
 Mill+0.029
 Su+0.029
ho+0.028
Neg logit contributions
 two-0.017
A-0.016
 sharp-0.015
 Deal-0.015
 big-0.015
Token
Token ID198
Feature activation-4.69e+00

Pos logit contributions
ggy+0.105
 ruined+0.103
wy+0.101
ggie+0.100
 sharp+0.099
Neg logit contributions
 Suz-0.133
 Su-0.130
 Mill-0.130
 Sus-0.129
 Alf-0.126
Token,
Token ID11
Feature activation+4.27e+00

Pos logit contributions
 Suz+0.011
 Su+0.011
 Mill+0.011
 Sus+0.011
 Alf+0.011
Neg logit contributions
 ruined-0.009
wy-0.009
ggy-0.008
 sharp-0.008
istered-0.008
Token but
Token ID475
Feature activation+5.34e+00

Pos logit contributions
 Suz+0.090
 Su+0.089
 Mill+0.088
 Alf+0.087
 Sus+0.087
Neg logit contributions
 ruined-0.094
 sharp-0.090
wy-0.090
ggy-0.086
 sting-0.086
Token it
Token ID340
Feature activation-2.44e+00

Pos logit contributions
 Suz+0.093
 Su+0.092
 Alf+0.092
 Mill+0.090
 Sus+0.086
Neg logit contributions
 ruined-0.137
 sharp-0.128
wy-0.127
 hurt-0.126
ggy-0.125
Token didn
Token ID1422
Feature activation-6.65e+00

Pos logit contributions
arest+0.053
wy+0.051
istered+0.051
 Deal+0.050
ps+0.050
Neg logit contributions
 Suz-0.052
 Mill-0.050
 Su-0.050
 Sus-0.050
 Twe-0.047
Token't
Token ID470
Feature activation-4.69e+00

Pos logit contributions
wy+0.153
istered+0.141
 ruined+0.131
aky+0.129
ery+0.129
Neg logit contributions
 Su-0.138
 Suz-0.137
 Sus-0.137
 Twe-0.137
 Mill-0.136
Token seem
Token ID1283
Feature activation-8.61e+00

Pos logit contributions
wy+0.083
ggy+0.081
istered+0.080
ggie+0.079
 ruined+0.077
Neg logit contributions
 Suz-0.119
 Sus-0.117
 Mill-0.117
 Su-0.116
 Alf-0.111
Token tasty
Token ID25103
Feature activation-1.71e+00

Pos logit contributions
wy+0.154
ggy+0.151
uch+0.148
ggie+0.145
istered+0.140
Neg logit contributions
 Su-0.215
 Sus-0.214
 Mill-0.212
 Suz-0.211
 Alf-0.198
Token to
Token ID284
Feature activation-1.12e+00

Pos logit contributions
 ruined+0.032
wy+0.032
ggy+0.031
istered+0.030
 sharp+0.030
Neg logit contributions
 Su-0.041
 Suz-0.041
 Sus-0.040
 Mill-0.040
 Alf-0.039
Token her
Token ID607
Feature activation+1.46e+00

Pos logit contributions
istered+0.024
wy+0.023
 ruined+0.022
ps+0.022
ggy+0.022
Neg logit contributions
 Suz-0.025
 Su-0.024
 Mill-0.024
 Sus-0.024
 Twe-0.022
Token.
Token ID13
Feature activation+1.98e+00

Pos logit contributions
 Suz+0.036
 Su+0.036
 Mill+0.035
 Sus+0.035
 Alf+0.034
Neg logit contributions
wy-0.027
 ruined-0.026
ggy-0.024
istered-0.024
 sharp-0.024
Token She
Token ID1375
Feature activation-5.10e-01

Pos logit contributions
 Alf+0.045
 Suz+0.044
 cities+0.043
 Su+0.043
 Mill+0.043
Neg logit contributions
 big-0.033
 ruined-0.033
 two-0.031
 bad-0.031
 sharp-0.031
Token didn
Token ID1422
Feature activation-5.36e+00

Pos logit contributions
wy+0.036
istered+0.034
ggy+0.034
 ruined+0.034
ggie+0.033
Neg logit contributions
 Suz-0.047
 Mill-0.046
 Sus-0.046
 Su-0.045
 Alf-0.045
Tokenâ
Token ID22940
Feature activation+1.39e+00

Pos logit contributions
wy+0.090
 ruined+0.079
istered+0.077
ggy+0.073
ggie+0.072
Neg logit contributions
 Suz-0.152
 Sus-0.151
 Mill-0.150
 Su-0.150
 Alf-0.146
Token
Token ID26391
Feature activation-2.52e+00

Pos logit contributions
 Suz+0.032
 Su+0.032
 Mill+0.031
 Sus+0.031
 Alf+0.031
Neg logit contributions
 ruined-0.028
wy-0.027
ggy-0.026
 sharp-0.026
ggie-0.026
Token
Token ID8151
Feature activation-3.63e+00

Pos logit contributions
 ruined+0.053
wy+0.052
ggy+0.051
 sharp+0.049
ggie+0.049
Neg logit contributions
 Suz-0.056
 Su-0.055
 Mill-0.054
 Sus-0.054
 Alf-0.053
Tokent
Token ID83
Feature activation-5.05e+00

Pos logit contributions
 ruined+0.042
wy+0.041
ggy+0.039
uch+0.037
ggie+0.037
Neg logit contributions
 Suz-0.112
 Mill-0.111
 Su-0.110
 Alf-0.109
 Sus-0.109
Token seem
Token ID1283
Feature activation-8.58e+00

Pos logit contributions
 ruined+0.081
wy+0.078
 sharp+0.075
ggy+0.074
 pain+0.073
Neg logit contributions
 Suz-0.136
 Su-0.134
 Mill-0.133
 Sus-0.132
 Alf-0.131
Token to
Token ID284
Feature activation-1.47e+00

Pos logit contributions
wy+0.147
 ruined+0.140
ggy+0.138
istered+0.133
ggie+0.133
Neg logit contributions
 Suz-0.224
 Su-0.223
 Sus-0.221
 Mill-0.220
 Alf-0.212
Token be
Token ID307
Feature activation-4.41e+00

Pos logit contributions
wy+0.026
istered+0.025
 ruined+0.025
ggy+0.024
 sharp+0.023
Neg logit contributions
 Suz-0.038
 Su-0.038
 Sus-0.038
 Mill-0.037
 Alf-0.036
Token ending
Token ID7464
Feature activation-3.87e-01

Pos logit contributions
wy+0.072
uch+0.066
istered+0.066
ggy+0.065
 ruined+0.065
Neg logit contributions
 Su-0.120
 Suz-0.119
 Sus-0.118
 Mill-0.116
 Alf-0.110
Token.
Token ID13
Feature activation+1.18e+00

Pos logit contributions
wy+0.007
 ruined+0.007
ggy+0.007
 sharp+0.006
istered+0.006
Neg logit contributions
 Suz-0.010
 Su-0.010
 Mill-0.009
 Sus-0.009
 Alf-0.009
Token Diana
Token ID25752
Feature activation+1.19e-01

Pos logit contributions
 Suz+0.026
 cities+0.026
 Alf+0.025
 Mill+0.025
 Ally+0.024
Neg logit contributions
ggy-0.020
 ruined-0.019
ggie-0.019
A-0.018
 Deal-0.018
Token answer
Token ID3280
Feature activation+3.56e-01

Pos logit contributions
wy+0.078
istered+0.077
 ruined+0.076
uch+0.073
ggy+0.072
Neg logit contributions
 Suz-0.105
 Su-0.101
 Sus-0.101
 Mill-0.100
 Alf-0.097
Token,
Token ID11
Feature activation+2.91e+00

Pos logit contributions
 Suz+0.009
 Mill+0.009
 Su+0.009
 Sus+0.008
 Alf+0.008
Neg logit contributions
 ruined-0.006
 sharp-0.006
ggy-0.006
ggie-0.006
wy-0.006
Token but
Token ID475
Feature activation+4.05e+00

Pos logit contributions
 Suz+0.069
 Sus+0.067
 Mill+0.066
 Su+0.066
 Alf+0.065
Neg logit contributions
 sharp-0.054
 ruined-0.052
 bad-0.050
 pain-0.050
ggy-0.050
Token it
Token ID340
Feature activation-2.23e+00

Pos logit contributions
 Suz+0.062
 Su+0.061
 Sus+0.060
 Mill+0.059
 Alf+0.058
Neg logit contributions
 ruined-0.110
ggy-0.108
wy-0.108
 sharp-0.107
ggie-0.106
Token did
Token ID750
Feature activation-4.90e+00

Pos logit contributions
wy+0.045
istered+0.042
 ruined+0.041
arest+0.040
uch+0.040
Neg logit contributions
 Suz-0.053
 Su-0.050
 Mill-0.050
 Sus-0.050
 Alf-0.049
Token seem
Token ID1283
Feature activation-8.56e+00

Pos logit contributions
wy+0.070
istered+0.057
uch+0.054
 ruined+0.052
arest+0.052
Neg logit contributions
 Suz-0.149
 Mill-0.146
 Sus-0.146
 Su-0.146
 Alf-0.145
Token to
Token ID284
Feature activation-1.73e+00

Pos logit contributions
wy+0.137
 ruined+0.128
ggy+0.127
uch+0.126
istered+0.123
Neg logit contributions
 Suz-0.236
 Su-0.235
 Mill-0.231
 Sus-0.231
 Alf-0.224
Token move
Token ID1445
Feature activation+4.82e-01

Pos logit contributions
istered+0.037
wy+0.036
 ruined+0.033
uch+0.033
arest+0.033
Neg logit contributions
 Suz-0.040
 Mill-0.039
 Su-0.038
 Sus-0.038
 Ally-0.037
Token away
Token ID1497
Feature activation+1.86e+00

Pos logit contributions
 Suz+0.012
 Su+0.012
 Mill+0.012
 Sus+0.012
 Alf+0.012
Neg logit contributions
 ruined-0.009
wy-0.008
 sharp-0.008
ggy-0.008
 hurt-0.008
Token from
Token ID422
Feature activation+3.40e+00

Pos logit contributions
 Suz+0.044
 Su+0.044
 Mill+0.043
 Sus+0.043
 Alf+0.042
Neg logit contributions
 ruined-0.036
wy-0.035
 sharp-0.034
ggy-0.034
ggie-0.033
Token Bob
Token ID5811
Feature activation+2.55e+00

Pos logit contributions
 Suz+0.073
 Su+0.072
 Mill+0.071
 Sus+0.070
 Alf+0.069
Neg logit contributions
 ruined-0.073
wy-0.072
 sharp-0.071
ggy-0.070
 pain-0.068
Token,
Token ID11
Feature activation+3.75e+00

Pos logit contributions
 Su+0.050
 Suz+0.048
 Sus+0.048
 Alf+0.047
 Mill+0.046
Neg logit contributions
 ruined-0.030
 sharp-0.030
wy-0.028
ggy-0.028
 burns-0.028
Token but
Token ID475
Feature activation+5.13e+00

Pos logit contributions
 Suz+0.095
 Su+0.095
 Alf+0.093
 Sus+0.092
 Mill+0.092
Neg logit contributions
 ruined-0.068
 sharp-0.066
wy-0.062
 hurt-0.061
 sting-0.060
Token it
Token ID340
Feature activation-2.15e+00

Pos logit contributions
 Su+0.111
 Suz+0.110
 Mill+0.107
 Sus+0.105
 Alf+0.104
Neg logit contributions
 ruined-0.113
 sharp-0.108
 hurt-0.105
wy-0.103
 bad-0.102
Token didn
Token ID1422
Feature activation-6.53e+00

Pos logit contributions
wy+0.040
 ruined+0.038
istered+0.038
ggy+0.037
ggie+0.037
Neg logit contributions
 Suz-0.053
 Su-0.051
 Mill-0.051
 Sus-0.051
 Alf-0.050
Token't
Token ID470
Feature activation-4.24e+00

Pos logit contributions
wy+0.146
istered+0.132
 ruined+0.126
aky+0.119
 pain+0.118
Neg logit contributions
 Suz-0.147
 Su-0.146
 Sus-0.146
 Mill-0.146
 Alf-0.142
Token seem
Token ID1283
Feature activation-8.52e+00

Pos logit contributions
wy+0.077
ggy+0.073
 ruined+0.072
ggie+0.071
istered+0.071
Neg logit contributions
 Suz-0.109
 Mill-0.107
 Sus-0.106
 Su-0.106
 Alf-0.103
Token to
Token ID284
Feature activation-2.20e+00

Pos logit contributions
wy+0.191
ggy+0.185
ggie+0.180
uch+0.179
 ruined+0.178
Neg logit contributions
 Suz-0.178
 Su-0.178
 Mill-0.178
 Sus-0.177
 Alf-0.166
Token change
Token ID1487
Feature activation+1.77e-01

Pos logit contributions
wy+0.043
istered+0.041
ggy+0.039
ggie+0.039
 burns+0.037
Neg logit contributions
 Suz-0.055
 Mill-0.055
 Sus-0.054
 Su-0.053
 Alf-0.050
Token much
Token ID881
Feature activation-7.21e-01

Pos logit contributions
 Suz+0.004
 Su+0.004
 Mill+0.004
 Sus+0.004
 Alf+0.004
Neg logit contributions
wy-0.003
 ruined-0.003
ggy-0.003
ggie-0.003
 sharp-0.003
Token.
Token ID13
Feature activation+1.43e+00

Pos logit contributions
wy+0.014
ggy+0.014
ggie+0.014
uch+0.014
istered+0.013
Neg logit contributions
 Mill-0.017
 Suz-0.017
 Sus-0.017
 Su-0.017
 Alf-0.016
Token
Token ID198
Feature activation-5.46e+00

Pos logit contributions
 Suz+0.036
 Su+0.035
 Mill+0.035
 Ally+0.034
 Hil+0.033
Neg logit contributions
 two-0.022
A-0.021
 sharp-0.021
Luckily-0.020
 big-0.020
Token.
Token ID13
Feature activation+2.54e+00

Pos logit contributions
 Su+0.055
 Suz+0.055
 Sus+0.053
 Mill+0.052
 Cr+0.051
Neg logit contributions
 ruined-0.027
 sharp-0.027
ggy-0.026
 big-0.025
 hurt-0.025
Token<|endoftext|>
Token ID50256
Feature activation-4.93e+00

Pos logit contributions
 Suz+0.061
 Su+0.061
 Sus+0.060
 cities+0.060
 Jos+0.058
Neg logit contributions
ggy-0.035
ching-0.035
 two-0.033
ggie-0.033
 pain-0.033
TokenJoe
Token ID19585
Feature activation-6.59e-01

Pos logit contributions
 ruined+0.093
wy+0.091
ggy+0.089
 sharp+0.086
ggie+0.085
Neg logit contributions
 Suz-0.115
 Su-0.113
 Mill-0.112
 Sus-0.111
 Alf-0.109
Tokeny
Token ID88
Feature activation-1.28e+00

Pos logit contributions
 ruined+0.013
wy+0.012
 sharp+0.012
ggy+0.012
 burns+0.011
Neg logit contributions
 Suz-0.016
 Su-0.015
 Mill-0.015
 Sus-0.015
 Alf-0.015
Token had
Token ID550
Feature activation-5.45e+00

Pos logit contributions
 ruined+0.023
wy+0.021
ggy+0.021
 sharp+0.021
ggie+0.020
Neg logit contributions
 Suz-0.032
 Su-0.032
 Mill-0.031
 Sus-0.031
 Alf-0.031
Token been
Token ID587
Feature activation-8.49e+00

Pos logit contributions
wy+0.071
istered+0.067
 sting+0.066
ggy+0.065
 ruined+0.064
Neg logit contributions
 Su-0.169
 Sus-0.167
 Suz-0.165
 Mill-0.164
 Alf-0.158
Token a
Token ID257
Feature activation-6.88e+00

Pos logit contributions
 ruined+0.172
wy+0.169
ggy+0.163
 sharp+0.161
istered+0.158
Neg logit contributions
 Suz-0.193
 Su-0.191
 Mill-0.188
 Sus-0.187
 Alf-0.184
Token very
Token ID845
Feature activation-5.82e+00

Pos logit contributions
 ruined+0.107
wy+0.107
ggy+0.101
 sharp+0.098
istered+0.097
Neg logit contributions
 Suz-0.187
 Su-0.186
 Mill-0.184
 Sus-0.183
 Alf-0.180
Token obedient
Token ID41652
Feature activation+2.53e-01

Pos logit contributions
wy+0.093
 ruined+0.090
ps+0.085
ggy+0.084
istered+0.083
Neg logit contributions
 Suz-0.157
 Su-0.156
 Sus-0.156
 Mill-0.154
 Alf-0.147
Token boy
Token ID2933
Feature activation-2.79e+00

Pos logit contributions
 Suz+0.007
 Su+0.007
 Mill+0.006
 Alf+0.006
 Sus+0.006
Neg logit contributions
 ruined-0.004
 sharp-0.004
 pain-0.004
ggy-0.004
wy-0.004
Token yesterday
Token ID7415
Feature activation-1.65e+00

Pos logit contributions
ggie+0.035
ggy+0.035
 ruined+0.034
 sharp+0.032
wy+0.031
Neg logit contributions
 Suz-0.084
 Su-0.081
 Mill-0.081
 Alf-0.079
 Sus-0.079
Token,
Token ID11
Feature activation+4.67e+00

Pos logit contributions
wy+0.015
 ruined+0.014
ggy+0.014
istered+0.014
ggie+0.014
Neg logit contributions
 Suz-0.018
 Mill-0.018
 Sus-0.017
 Su-0.017
 Alf-0.017
Token but
Token ID475
Feature activation+5.63e+00

Pos logit contributions
 Suz+0.109
 Su+0.108
 Mill+0.106
 Sus+0.105
 Alf+0.104
Neg logit contributions
 ruined-0.092
 sharp-0.088
wy-0.086
ggy-0.084
 hurt-0.084
Token it
Token ID340
Feature activation-2.12e+00

Pos logit contributions
 Alf+0.113
 Mill+0.110
 Su+0.106
 Suz+0.104
 Ally+0.104
Neg logit contributions
 sharp-0.121
 ruined-0.120
 bad-0.114
 hurt-0.113
 naughty-0.113
Token didn
Token ID1422
Feature activation-6.52e+00

Pos logit contributions
wy+0.045
istered+0.043
arest+0.041
 Deal+0.041
ps+0.040
Neg logit contributions
 Suz-0.049
 Mill-0.046
 Sus-0.046
 Su-0.046
 Alf-0.045
Token't
Token ID470
Feature activation-4.13e+00

Pos logit contributions
wy+0.160
istered+0.142
 ruined+0.137
aky+0.134
kin+0.129
Neg logit contributions
 Suz-0.135
 Mill-0.135
 Su-0.133
 Sus-0.133
 Alf-0.127
Token seem
Token ID1283
Feature activation-8.48e+00

Pos logit contributions
wy+0.078
uch+0.072
istered+0.071
ggy+0.071
 ruined+0.070
Neg logit contributions
 Suz-0.108
 Mill-0.106
 Sus-0.105
 Su-0.104
 Alf-0.102
Token to
Token ID284
Feature activation-2.24e+00

Pos logit contributions
wy+0.190
ggy+0.180
uch+0.179
 ruined+0.176
ggie+0.175
Neg logit contributions
 Su-0.180
 Suz-0.179
 Mill-0.178
 Sus-0.177
 Alf-0.169
Token notice
Token ID4003
Feature activation+2.54e+00

Pos logit contributions
wy+0.046
istered+0.045
uch+0.041
ggy+0.041
 ruined+0.041
Neg logit contributions
 Suz-0.053
 Mill-0.052
 Sus-0.052
 Su-0.052
 Alf-0.050
Token anything
Token ID1997
Feature activation-3.04e+00

Pos logit contributions
 Suz+0.063
 Mill+0.062
 Su+0.062
 Alf+0.062
 Sus+0.061
Neg logit contributions
 ruined-0.045
 sharp-0.043
wy-0.041
ggy-0.040
 pain-0.040
Token.
Token ID13
Feature activation+1.31e+00

Pos logit contributions
wy+0.060
uch+0.055
 ruined+0.052
ggy+0.052
istered+0.052
Neg logit contributions
 Suz-0.073
 Sus-0.073
 Su-0.073
 Mill-0.073
 Alf-0.069
Token Sandy
Token ID17581
Feature activation-5.89e-01

Pos logit contributions
 cities+0.027
 Alf+0.027
 Mill+0.026
 Ally+0.025
stack+0.025
Neg logit contributions
 big-0.023
A-0.023
 two-0.023
 sharp-0.023
Luckily-0.022
Token "
Token ID366
Feature activation-5.13e-01

Pos logit contributions
 cities+0.073
iked+0.068
 Suz+0.068
 Su+0.068
ress+0.068
Neg logit contributions
 not-0.075
 sharp-0.075
 ruined-0.073
 hurt-0.073
 big-0.072
TokenYes
Token ID5297
Feature activation-1.54e-01

Pos logit contributions
 ruined+0.007
wy+0.007
ggy+0.007
ggie+0.007
uch+0.007
Neg logit contributions
 Alf-0.014
 Su-0.014
 Suz-0.014
 Mill-0.014
 Sus-0.014
Token,
Token ID11
Feature activation+2.09e+00

Pos logit contributions
 ruined+0.003
wy+0.003
ggy+0.003
 sharp+0.003
ggie+0.003
Neg logit contributions
 Suz-0.003
 Su-0.003
 Mill-0.003
 Sus-0.003
 Alf-0.003
Token it
Token ID340
Feature activation-2.79e+00

Pos logit contributions
 Suz+0.045
 Alf+0.045
 Su+0.045
 Mill+0.044
bank+0.044
Neg logit contributions
 ruined-0.042
 sharp-0.040
ggy-0.038
 bad-0.037
ggie-0.037
Token does
Token ID857
Feature activation-4.36e+00

Pos logit contributions
wy+0.052
istered+0.048
 ruined+0.047
 sharp+0.046
ggy+0.046
Neg logit contributions
 Suz-0.069
 Mill-0.067
 Sus-0.066
 Su-0.066
 Alf-0.064
Token seem
Token ID1283
Feature activation-8.47e+00

Pos logit contributions
wy+0.086
 ruined+0.080
istered+0.077
uch+0.073
 burns+0.072
Neg logit contributions
 Suz-0.108
 Su-0.106
 Mill-0.106
 Sus-0.106
 Alf-0.103
Token friendly
Token ID8030
Feature activation-1.80e-01

Pos logit contributions
wy+0.140
ggy+0.129
istered+0.128
uch+0.126
 ruined+0.126
Neg logit contributions
 Suz-0.230
 Su-0.229
 Mill-0.229
 Sus-0.228
 Alf-0.218
Token.
Token ID13
Feature activation+1.60e+00

Pos logit contributions
 ruined+0.003
wy+0.003
ggy+0.003
 sharp+0.003
ggie+0.003
Neg logit contributions
 Suz-0.005
 Su-0.005
 Mill-0.005
 Sus-0.005
 Alf-0.005
Token But
Token ID887
Feature activation+3.67e+00

Pos logit contributions
 Su+0.035
 Suz+0.034
 Mill+0.033
 Sus+0.033
 Alf+0.033
Neg logit contributions
ggy-0.027
ggie-0.027
 Deal-0.026
A-0.026
 sharp-0.026
Token we
Token ID356
Feature activation-2.28e+00

Pos logit contributions
 Su+0.094
 Suz+0.093
 Mill+0.091
 Alf+0.091
 Sus+0.090
Neg logit contributions
 ruined-0.063
 sharp-0.059
wy-0.058
ggy-0.057
 sting-0.057
Token have
Token ID423
Feature activation-5.22e+00

Pos logit contributions
istered+0.042
ggy+0.041
wy+0.041
ggie+0.040
 burns+0.037
Neg logit contributions
 Suz-0.056
 Mill-0.056
 Su-0.055
 Sus-0.054
 Alf-0.053
Token,
Token ID11
Feature activation+2.51e+00

Pos logit contributions
 ruined+0.032
 sharp+0.032
ggy+0.031
wy+0.031
ggie+0.030
Neg logit contributions
 Suz-0.038
 Su-0.037
 Mill-0.036
 Sus-0.036
 Alf-0.035
Token but
Token ID475
Feature activation+4.55e+00

Pos logit contributions
 Suz+0.063
 Mill+0.063
 Su+0.061
 Sus+0.060
 Ally+0.058
Neg logit contributions
 sharp-0.048
 ruined-0.045
 hurt-0.045
 bad-0.045
 pain-0.045
Token he
Token ID339
Feature activation-2.12e+00

Pos logit contributions
 Suz+0.098
 Mill+0.098
 Su+0.097
 Sus+0.093
 Ally+0.090
Neg logit contributions
 ruined-0.103
 sharp-0.099
 hurt-0.098
 bad-0.096
 pain-0.094
Token didn
Token ID1422
Feature activation-7.51e+00

Pos logit contributions
wy+0.042
istered+0.041
ps+0.039
 ruined+0.039
 burns+0.039
Neg logit contributions
 Suz-0.049
 Su-0.049
 Sus-0.047
 Mill-0.046
 Alf-0.046
Token't
Token ID470
Feature activation-4.44e+00

Pos logit contributions
wy+0.174
istered+0.160
 ruined+0.152
 sting+0.144
ery+0.143
Neg logit contributions
 Su-0.165
 Sus-0.159
 Suz-0.157
 Alf-0.154
 Jan-0.151
Token seem
Token ID1283
Feature activation-8.46e+00

Pos logit contributions
wy+0.076
 ruined+0.074
istered+0.073
ggy+0.071
 burns+0.070
Neg logit contributions
 Su-0.114
 Suz-0.113
 Sus-0.111
 Mill-0.110
 Alf-0.108
Token to
Token ID284
Feature activation-2.72e+00

Pos logit contributions
wy+0.192
ggy+0.183
uch+0.182
 ruined+0.182
istered+0.179
Neg logit contributions
 Su-0.173
 Suz-0.168
 Sus-0.168
 Mill-0.165
 Alf-0.159
Token win
Token ID1592
Feature activation-4.44e+00

Pos logit contributions
istered+0.052
wy+0.052
 burns+0.049
 ruined+0.047
ery+0.046
Neg logit contributions
 Su-0.062
 Sus-0.062
 Suz-0.060
 J-0.060
 Alf-0.059
Token very
Token ID845
Feature activation-1.54e+00

Pos logit contributions
wy+0.097
istered+0.093
 ruined+0.090
uch+0.090
 burns+0.089
Neg logit contributions
 Su-0.096
 Sus-0.094
 Suz-0.094
 Alf-0.091
 Mill-0.090
Token often
Token ID1690
Feature activation+8.81e-01

Pos logit contributions
wy+0.026
 ruined+0.024
istered+0.023
 burns+0.023
uch+0.023
Neg logit contributions
 Su-0.039
 Sus-0.039
 J-0.038
 Suz-0.038
 Alf-0.037
Token.
Token ID13
Feature activation+5.57e-01

Pos logit contributions
 Suz+0.024
 Su+0.024
 Mill+0.024
 Sus+0.023
 Alf+0.023
Neg logit contributions
 ruined-0.014
wy-0.014
ggy-0.013
 sharp-0.013
ggie-0.012
Token,
Token ID11
Feature activation+4.43e+00

Pos logit contributions
wy+0.005
 ruined+0.005
ggy+0.005
 burns+0.005
istered+0.005
Neg logit contributions
 Suz-0.005
 Su-0.005
 Mill-0.005
 Sus-0.005
 Alf-0.005
Token but
Token ID475
Feature activation+6.11e+00

Pos logit contributions
 Suz+0.120
 Su+0.120
 Sus+0.119
 Mill+0.118
 Alf+0.117
Neg logit contributions
 sharp-0.075
 hurt-0.072
 not-0.068
 sting-0.068
 ruined-0.068
Token it
Token ID340
Feature activation-2.11e+00

Pos logit contributions
 Alf+0.140
 Suz+0.138
 Mill+0.138
 Su+0.134
 Hil+0.131
Neg logit contributions
 ruined-0.127
 hurt-0.120
 bad-0.118
 sharp-0.115
 pain-0.112
Token didn
Token ID1422
Feature activation-6.52e+00

Pos logit contributions
wy+0.043
istered+0.041
arest+0.039
 Deal+0.038
 ruined+0.038
Neg logit contributions
 Suz-0.049
 Su-0.047
 Mill-0.046
 Sus-0.046
 Alf-0.045
Token't
Token ID470
Feature activation-3.99e+00

Pos logit contributions
wy+0.149
istered+0.130
 ruined+0.125
ery+0.123
aky+0.120
Neg logit contributions
 Su-0.152
 Suz-0.151
 Sus-0.148
 Mill-0.147
 Twe-0.142
Token seem
Token ID1283
Feature activation-8.40e+00

Pos logit contributions
wy+0.067
 ruined+0.065
ggy+0.062
istered+0.061
ggie+0.060
Neg logit contributions
 Suz-0.107
 Su-0.106
 Mill-0.105
 Sus-0.105
 Alf-0.102
Token to
Token ID284
Feature activation-2.21e+00

Pos logit contributions
wy+0.184
 ruined+0.179
ggy+0.176
istered+0.171
ggie+0.171
Neg logit contributions
 Suz-0.178
 Su-0.178
 Mill-0.174
 Sus-0.174
 Alf-0.167
Token work
Token ID670
Feature activation-3.69e+00

Pos logit contributions
wy+0.043
istered+0.042
 ruined+0.040
 burns+0.039
ggy+0.039
Neg logit contributions
 Suz-0.053
 Su-0.052
 Mill-0.052
 Sus-0.052
 Alf-0.050
Token.
Token ID13
Feature activation+2.05e+00

Pos logit contributions
wy+0.074
 ruined+0.071
istered+0.070
 burns+0.070
uch+0.069
Neg logit contributions
 Su-0.084
 Sus-0.084
 Suz-0.083
 Mill-0.082
 Alf-0.078
Token Lily
Token ID20037
Feature activation-5.82e-01

Pos logit contributions
 Alf+0.049
 cities+0.049
 ships+0.046
 Suz+0.046
 Mill+0.045
Neg logit contributions
 ruined-0.032
A-0.031
 big-0.031
 bad-0.030
Luckily-0.030
Token laughed
Token ID13818
Feature activation-1.18e+00

Pos logit contributions
wy+0.010
 ruined+0.010
istered+0.009
ggy+0.009
 sharp+0.009
Neg logit contributions
 Suz-0.015
 Su-0.015
 Mill-0.014
 Sus-0.014
 Alf-0.014
Token,
Token ID11
Feature activation+3.82e+00

Pos logit contributions
 Suz+0.058
 Mill+0.056
 Su+0.056
 Sus+0.055
 Alf+0.052
Neg logit contributions
ggy-0.025
ggie-0.024
 ruined-0.022
 big-0.021
 hurt-0.021
Token but
Token ID475
Feature activation+4.66e+00

Pos logit contributions
 Suz+0.082
 Mill+0.082
 Alf+0.081
bank+0.079
 Su+0.079
Neg logit contributions
 sharp-0.077
 ruined-0.077
 hurt-0.072
 bad-0.071
 big-0.071
Token she
Token ID673
Feature activation-2.08e+00

Pos logit contributions
 cities+0.106
 Suz+0.102
 Su+0.101
 Mill+0.101
 Alf+0.101
Neg logit contributions
 ruined-0.094
 hurt-0.089
 not-0.087
 bad-0.086
 sharp-0.084
Token said
Token ID531
Feature activation+1.97e-01

Pos logit contributions
ps+0.044
wy+0.043
istered+0.043
 burns+0.041
ching+0.041
Neg logit contributions
 Suz-0.046
 Su-0.045
 Sus-0.044
 Mill-0.044
 Alf-0.042
Token they
Token ID484
Feature activation-2.95e+00

Pos logit contributions
 Suz+0.006
 Mill+0.006
 Su+0.006
 Alf+0.006
 Sus+0.006
Neg logit contributions
 ruined-0.002
ggy-0.002
 sharp-0.002
ggie-0.002
wy-0.002
Token didn
Token ID1422
Feature activation-8.38e+00

Pos logit contributions
wy+0.066
ps+0.064
ggy+0.062
ggie+0.061
 sting+0.060
Neg logit contributions
 Sus-0.061
 Su-0.061
 Suz-0.061
 Mill-0.060
 Alf-0.059
Token't
Token ID470
Feature activation-4.73e+00

Pos logit contributions
wy+0.171
istered+0.156
 ruined+0.153
ery+0.144
 pain+0.143
Neg logit contributions
 Su-0.205
 Alf-0.199
 Suz-0.199
 Sus-0.199
 Mill-0.196
Token have
Token ID423
Feature activation-4.96e+00

Pos logit contributions
 ruined+0.073
wy+0.071
ggy+0.068
 sharp+0.068
ggie+0.066
Neg logit contributions
 Suz-0.131
 Su-0.129
 Mill-0.128
 Sus-0.127
 Alf-0.125
Token a
Token ID257
Feature activation-5.82e+00

Pos logit contributions
 ruined+0.083
wy+0.082
ggy+0.078
 sharp+0.077
istered+0.076
Neg logit contributions
 Suz-0.130
 Su-0.129
 Mill-0.127
 Sus-0.126
 Alf-0.124
Token plan
Token ID1410
Feature activation-4.54e+00

Pos logit contributions
 ruined+0.106
 sharp+0.101
 bad+0.098
ggy+0.095
 sting+0.093
Neg logit contributions
 Suz-0.151
 Mill-0.146
 Su-0.146
 Sus-0.145
 Alf-0.140
Token yet
Token ID1865
Feature activation-7.77e-01

Pos logit contributions
 ruined+0.071
ggy+0.067
wy+0.067
ggie+0.064
 sharp+0.064
Neg logit contributions
 Suz-0.126
 Mill-0.123
 Su-0.123
 Sus-0.121
 Alf-0.120
Token<|endoftext|>
Token ID50256
Feature activation-5.18e+00

Pos logit contributions
line+0.044
 Suz+0.044
 Su+0.044
 ships+0.044
 cities+0.044
Neg logit contributions
A-0.018
 two-0.018
ggy-0.017
 Deal-0.017
 big-0.017
TokenPeter
Token ID19727
Feature activation+1.73e-01

Pos logit contributions
 ruined+0.107
wy+0.105
ggy+0.102
 sharp+0.100
ggie+0.099
Neg logit contributions
 Suz-0.114
 Su-0.112
 Mill-0.111
 Sus-0.110
 Alf-0.108
Token was
Token ID373
Feature activation-6.41e+00

Pos logit contributions
 Suz+0.004
 Su+0.004
 Mill+0.004
 Sus+0.004
 Alf+0.004
Neg logit contributions
 ruined-0.003
wy-0.003
ggy-0.003
 sharp-0.003
istered-0.003
Token a
Token ID257
Feature activation-5.86e+00

Pos logit contributions
wy+0.131
 ruined+0.131
ggy+0.125
 sharp+0.123
istered+0.123
Neg logit contributions
 Suz-0.145
 Su-0.143
 Mill-0.141
 Sus-0.141
 Alf-0.137
Token mis
Token ID2984
Feature activation-3.41e+00

Pos logit contributions
 ruined+0.072
wy+0.069
 sharp+0.067
ggy+0.066
ggie+0.063
Neg logit contributions
 Suz-0.180
 Su-0.178
 Mill-0.176
 Sus-0.175
 Alf-0.173
Tokenchie
Token ID3043
Feature activation-8.38e+00

Pos logit contributions
wy+0.052
 ruined+0.051
ggy+0.049
istered+0.049
 sharp+0.049
Neg logit contributions
 Suz-0.091
 Su-0.091
 Mill-0.090
 Alf-0.089
 Sus-0.088
Tokenvous
Token ID31222
Feature activation-2.78e+00

Pos logit contributions
ggy+0.102
wy+0.101
 ruined+0.101
ggie+0.097
 sharp+0.095
Neg logit contributions
 Suz-0.250
 Mill-0.248
 Su-0.246
 Alf-0.245
 Sus-0.244
Token 3
Token ID513
Feature activation-3.20e+00

Pos logit contributions
 sharp+0.050
 ruined+0.049
 naughty+0.048
 bad+0.048
 pain+0.048
Neg logit contributions
 Suz-0.066
 Su-0.064
 Mill-0.064
 Alf-0.064
 Jan-0.062
Token year
Token ID614
Feature activation-2.74e-01

Pos logit contributions
 ruined+0.053
wy+0.052
ggy+0.052
 sharp+0.050
ggie+0.050
Neg logit contributions
 Suz-0.084
 Su-0.082
 Mill-0.082
 Sus-0.081
 Alf-0.080
Token old
Token ID1468
Feature activation-1.27e+00

Pos logit contributions
 sharp+0.003
 ruined+0.003
 bad+0.003
 naughty+0.003
 big+0.003
Neg logit contributions
 Suz-0.009
 Su-0.009
 Mill-0.009
 Alf-0.008
 Sus-0.008
Token who
Token ID508
Feature activation+1.71e+00

Pos logit contributions
 ruined+0.021
ggy+0.021
 sharp+0.021
ggie+0.020
 hurt+0.020
Neg logit contributions
 Suz-0.032
 Su-0.031
 Mill-0.031
 Alf-0.030
 Jan-0.030
Token her
Token ID607
Feature activation+1.29e+00

Pos logit contributions
 Suz+0.091
 Su+0.090
 Mill+0.088
 Sus+0.088
 Alf+0.085
Neg logit contributions
 ruined-0.106
wy-0.105
ggy-0.101
 sharp-0.100
istered-0.099
Token come
Token ID1282
Feature activation-7.34e-01

Pos logit contributions
 Suz+0.030
 Su+0.030
 Sus+0.029
 Mill+0.029
 Alf+0.029
Neg logit contributions
wy-0.026
 ruined-0.025
istered-0.024
ggy-0.024
 sharp-0.024
Token back
Token ID736
Feature activation+1.54e+00

Pos logit contributions
 ruined+0.014
wy+0.013
 sharp+0.013
ggy+0.013
 hurt+0.013
Neg logit contributions
 Suz-0.018
 Su-0.017
 Mill-0.017
 Sus-0.017
 Alf-0.017
Token.
Token ID13
Feature activation+2.52e+00

Pos logit contributions
 Suz+0.040
 Su+0.039
 Mill+0.039
 Sus+0.038
 Alf+0.038
Neg logit contributions
 ruined-0.026
 sharp-0.025
wy-0.025
ggy-0.024
 burns-0.024
Token You
Token ID921
Feature activation-3.72e+00

Pos logit contributions
 Suz+0.054
 Su+0.053
 Sus+0.052
 Mill+0.051
 Alf+0.051
Neg logit contributions
 Deal-0.047
 sharp-0.044
 burns-0.044
ggy-0.044
 pain-0.044
Token seem
Token ID1283
Feature activation-8.36e+00

Pos logit contributions
ggy+0.076
ggie+0.075
istered+0.075
wy+0.074
itching+0.070
Neg logit contributions
 Alf-0.085
 Mill-0.083
 Suz-0.081
 Sus-0.080
 Ally-0.078
Token like
Token ID588
Feature activation-6.14e-01

Pos logit contributions
wy+0.164
uch+0.154
ggy+0.149
istered+0.146
kin+0.144
Neg logit contributions
 Mill-0.203
 Sus-0.202
 Su-0.200
 Suz-0.196
 Ally-0.190
Token a
Token ID257
Feature activation-4.40e+00

Pos logit contributions
 ruined+0.013
wy+0.012
 sharp+0.012
ggy+0.012
 burns+0.012
Neg logit contributions
 Suz-0.014
 Su-0.014
 Mill-0.013
 Sus-0.013
 Alf-0.013
Token good
Token ID922
Feature activation-2.97e-01

Pos logit contributions
 ruined+0.060
wy+0.060
ggy+0.056
 sharp+0.054
istered+0.053
Neg logit contributions
 Suz-0.129
 Su-0.128
 Mill-0.126
 Sus-0.126
 Alf-0.124
Token boy
Token ID2933
Feature activation-1.05e+00

Pos logit contributions
 ruined+0.005
 pain+0.005
ggy+0.005
 sharp+0.005
wy+0.005
Neg logit contributions
 Suz-0.007
 Su-0.007
 Mill-0.007
 Alf-0.007
 Sus-0.007
Token.
Token ID13
Feature activation+1.73e+00

Pos logit contributions
 ruined+0.018
wy+0.018
ggy+0.017
 sharp+0.017
ggie+0.016
Neg logit contributions
 Suz-0.027
 Su-0.027
 Mill-0.027
 Sus-0.026
 Alf-0.026
Token.
Token ID13
Feature activation+2.10e+00

Pos logit contributions
 ruined+0.000
ggy+0.000
wy+0.000
ggie+0.000
 sharp+0.000
Neg logit contributions
 Suz-0.001
 Mill-0.001
 Su-0.001
 Sus-0.001
 Alf-0.001
Token But
Token ID887
Feature activation+4.16e+00

Pos logit contributions
 Suz+0.052
 Mill+0.049
 Su+0.049
 Sus+0.048
 Alf+0.046
Neg logit contributions
 ruined-0.038
 sharp-0.037
 bad-0.036
 big-0.035
 sting-0.035
Token Coco
Token ID48222
Feature activation-1.56e+00

Pos logit contributions
 Suz+0.094
 Su+0.091
 Mill+0.090
 Sus+0.089
 Alf+0.087
Neg logit contributions
 ruined-0.088
wy-0.084
ggy-0.083
 sharp-0.083
 hurt-0.081
Token did
Token ID750
Feature activation-6.22e+00

Pos logit contributions
arest+0.029
wy+0.029
istered+0.029
 Deal+0.028
ps+0.027
Neg logit contributions
 Su-0.034
 Suz-0.034
 Mill-0.033
 Sus-0.033
 Ally-0.032
Token not
Token ID407
Feature activation-4.06e+00

Pos logit contributions
wy+0.081
istered+0.067
arest+0.063
ery+0.063
 ruined+0.063
Neg logit contributions
 Suz-0.193
 Su-0.192
 Sus-0.190
 Mill-0.188
 Alf-0.187
Token seem
Token ID1283
Feature activation-8.35e+00

Pos logit contributions
wy+0.078
istered+0.075
 ruined+0.074
uch+0.072
ggy+0.071
Neg logit contributions
 Suz-0.098
 Su-0.096
 Mill-0.096
 Sus-0.096
 Alf-0.093
Token to
Token ID284
Feature activation-2.33e+00

Pos logit contributions
wy+0.177
 ruined+0.167
uch+0.167
istered+0.166
ggy+0.165
Neg logit contributions
 Su-0.185
 Suz-0.182
 Mill-0.180
 Sus-0.180
 Alf-0.171
Token understand
Token ID1833
Feature activation+6.59e-01

Pos logit contributions
wy+0.048
istered+0.048
ery+0.044
uch+0.043
 ruined+0.043
Neg logit contributions
 Suz-0.053
 Su-0.053
 Mill-0.052
 Sus-0.052
 Alf-0.050
Token.
Token ID13
Feature activation+2.10e+00

Pos logit contributions
 Suz+0.014
 Su+0.014
 Mill+0.013
 Sus+0.013
 Alf+0.013
Neg logit contributions
 ruined-0.015
wy-0.014
ggy-0.014
 sharp-0.014
istered-0.014
Token He
Token ID679
Feature activation-6.52e-01

Pos logit contributions
 Suz+0.043
 Su+0.042
 Mill+0.042
 Sus+0.041
 Alf+0.039
Neg logit contributions
 ruined-0.047
 sharp-0.045
 bad-0.045
ggy-0.044
 pain-0.044
Token would
Token ID561
Feature activation-2.72e+00

Pos logit contributions
arest+0.015
wy+0.014
istered+0.014
vern+0.014
 Deal+0.013
Neg logit contributions
 Su-0.013
 Suz-0.013
 K-0.013
 Alf-0.012
 Sus-0.012
Token it
Token ID340
Feature activation-1.94e+00

Pos logit contributions
 Suz+0.024
 Su+0.024
 Mill+0.023
 Sus+0.023
 Alf+0.023
Neg logit contributions
 ruined-0.020
wy-0.020
ggy-0.019
 sharp-0.019
istered-0.018
Token.
Token ID13
Feature activation+1.47e+00

Pos logit contributions
wy+0.036
 ruined+0.035
ggy+0.034
istered+0.034
 sting+0.033
Neg logit contributions
 Suz-0.047
 Su-0.047
 Mill-0.047
 Sus-0.047
 Alf-0.045
Token<|endoftext|>
Token ID50256
Feature activation-5.41e+00

Pos logit contributions
 cities+0.040
line+0.039
bank+0.039
ho+0.038
 vans+0.037
Neg logit contributions
 ruined-0.017
 big-0.017
A-0.016
ching-0.016
 sense-0.016
TokenSam
Token ID16305
Feature activation+5.37e-04

Pos logit contributions
 ruined+0.102
wy+0.099
ggy+0.098
 sharp+0.095
ggie+0.095
Neg logit contributions
 Suz-0.126
 Su-0.124
 Mill-0.122
 Sus-0.121
 Alf-0.119
Token had
Token ID550
Feature activation-5.13e+00

Pos logit contributions
 Suz+0.000
 Su+0.000
 Mill+0.000
 Alf+0.000
 Sus+0.000
Neg logit contributions
 ruined-0.000
wy-0.000
 sharp-0.000
 burns-0.000
ggy-0.000
Token been
Token ID587
Feature activation-8.35e+00

Pos logit contributions
wy+0.070
istered+0.066
ggy+0.065
 sting+0.065
 ruined+0.064
Neg logit contributions
 Su-0.156
 Sus-0.154
 Suz-0.152
 Mill-0.151
 Alf-0.145
Token playing
Token ID2712
Feature activation-2.13e+00

Pos logit contributions
wy+0.160
 ruined+0.160
ggy+0.153
 sharp+0.150
istered+0.149
Neg logit contributions
 Suz-0.198
 Su-0.196
 Mill-0.193
 Sus-0.193
 Alf-0.188
Token with
Token ID351
Feature activation+2.34e-01

Pos logit contributions
 ruined+0.040
wy+0.039
ggy+0.038
 sharp+0.038
ggie+0.037
Neg logit contributions
 Suz-0.051
 Su-0.051
 Mill-0.050
 Sus-0.050
 Alf-0.049
Token his
Token ID465
Feature activation-1.09e+00

Pos logit contributions
 Suz+0.005
 Su+0.004
 Sus+0.004
 Mill+0.004
 Alf+0.004
Neg logit contributions
wy-0.006
 ruined-0.006
istered-0.005
ggy-0.005
uch-0.005
Token friends
Token ID2460
Feature activation-1.03e+00

Pos logit contributions
wy+0.022
 ruined+0.021
istered+0.020
uch+0.020
 sting+0.020
Neg logit contributions
 Suz-0.025
 Sus-0.025
 Su-0.025
 Mill-0.025
 Alf-0.024
Token all
Token ID477
Feature activation+9.66e-01

Pos logit contributions
 ruined+0.018
ggie+0.018
wy+0.018
ggy+0.018
 sharp+0.017
Neg logit contributions
 Suz-0.026
 Su-0.025
 Mill-0.025
 Sus-0.024
 Alf-0.024
Token,
Token ID11
Feature activation+3.87e+00

Pos logit contributions
wy+0.048
 ruined+0.047
uch+0.045
istered+0.045
ggy+0.045
Neg logit contributions
 Suz-0.054
 Su-0.054
 Sus-0.053
 Mill-0.052
 Alf-0.050
Token but
Token ID475
Feature activation+5.13e+00

Pos logit contributions
 Suz+0.079
 Mill+0.078
 Su+0.078
 Alf+0.075
 Sus+0.075
Neg logit contributions
 ruined-0.087
 sharp-0.086
 hurt-0.082
 pain-0.082
ggy-0.081
Token he
Token ID339
Feature activation-1.87e+00

Pos logit contributions
 Suz+0.103
 Su+0.101
 Mill+0.099
 Alf+0.098
 Sus+0.097
Neg logit contributions
 ruined-0.120
 sharp-0.114
wy-0.113
 hurt-0.111
 bad-0.111
Token didn
Token ID1422
Feature activation-7.27e+00

Pos logit contributions
wy+0.040
istered+0.040
arest+0.040
ps+0.039
 ruined+0.038
Neg logit contributions
 Suz-0.039
 Su-0.038
 Sus-0.037
 Alf-0.036
 Mill-0.036
Token't
Token ID470
Feature activation-4.43e+00

Pos logit contributions
wy+0.171
istered+0.156
 ruined+0.151
aky+0.145
kin+0.145
Neg logit contributions
 Su-0.153
 Suz-0.149
 Sus-0.145
 Twe-0.145
 Cr-0.143
Token seem
Token ID1283
Feature activation-8.34e+00

Pos logit contributions
wy+0.088
 ruined+0.085
istered+0.083
uch+0.082
ggy+0.081
Neg logit contributions
 Suz-0.104
 Su-0.103
 Sus-0.101
 Mill-0.100
 Alf-0.098
Token to
Token ID284
Feature activation-2.19e+00

Pos logit contributions
wy+0.216
ggy+0.207
uch+0.206
ggie+0.203
 ruined+0.202
Neg logit contributions
 Su-0.145
 Suz-0.141
 Sus-0.140
 Mill-0.140
 Alf-0.131
Token be
Token ID307
Feature activation-4.45e+00

Pos logit contributions
wy+0.046
istered+0.046
arest+0.044
 ruined+0.044
ery+0.043
Neg logit contributions
 Suz-0.047
 Su-0.046
 Mill-0.046
 Sus-0.046
 Cr-0.045
Token getting
Token ID1972
Feature activation-2.73e+00

Pos logit contributions
arest+0.081
wy+0.077
uch+0.076
istered+0.076
 Deal+0.073
Neg logit contributions
 Su-0.110
 Suz-0.108
 Sus-0.105
 Cr-0.102
 Mill-0.102
Token bigger
Token ID5749
Feature activation+9.05e-01

Pos logit contributions
wy+0.043
ggy+0.043
ggie+0.042
 ruined+0.041
uch+0.040
Neg logit contributions
 Suz-0.073
 Su-0.073
 Sus-0.072
 Mill-0.071
 Alf-0.070
Token or
Token ID393
Feature activation+4.76e+00

Pos logit contributions
 Suz+0.022
 Su+0.022
 Sus+0.022
 Mill+0.022
 Alf+0.022
Neg logit contributions
wy-0.016
 ruined-0.016
ggy-0.015
ggie-0.015
uch-0.015
Token little
Token ID1310
Feature activation+4.89e-01

Pos logit contributions
 ruined+0.060
wy+0.059
 burns+0.053
ggy+0.053
istered+0.052
Neg logit contributions
 Suz-0.166
 Su-0.165
 Mill-0.163
 Sus-0.163
 Alf-0.160
Token boy
Token ID2933
Feature activation-2.45e+00

Pos logit contributions
 Suz+0.011
 Su+0.011
 Alf+0.010
 Mill+0.010
 Sus+0.010
Neg logit contributions
 sharp-0.010
 ruined-0.010
wy-0.010
 bad-0.009
 pain-0.009
Token named
Token ID3706
Feature activation+4.09e+00

Pos logit contributions
 ruined+0.057
ggy+0.056
 hurt+0.054
 burns+0.053
wy+0.053
Neg logit contributions
 Alf-0.047
 Mill-0.047
 Suz-0.046
 Su-0.046
 Sus-0.046
Token Joe
Token ID5689
Feature activation-7.15e-01

Pos logit contributions
 Suz+0.044
 Mill+0.043
 Su+0.041
 Sus+0.040
ress+0.040
Neg logit contributions
 ruined-0.128
 sharp-0.127
wy-0.127
 big-0.122
 burns-0.121
Token had
Token ID550
Feature activation-5.61e+00

Pos logit contributions
wy+0.014
 ruined+0.014
istered+0.014
ggy+0.014
ggie+0.014
Neg logit contributions
 Suz-0.016
 Su-0.016
 Sus-0.016
 Mill-0.016
 Alf-0.015
Token been
Token ID587
Feature activation-8.33e+00

Pos logit contributions
wy+0.077
istered+0.069
 sting+0.068
ps+0.067
ggy+0.067
Neg logit contributions
 Su-0.170
 Sus-0.167
 Suz-0.167
 Mill-0.164
 Alf-0.160
Token feeling
Token ID4203
Feature activation-6.32e+00

Pos logit contributions
 ruined+0.183
wy+0.177
ggy+0.173
 sharp+0.173
ggie+0.169
Neg logit contributions
 Suz-0.177
 Su-0.173
 Mill-0.173
 Sus-0.169
 Alf-0.168
Token restless
Token ID42537
Feature activation-2.19e+00

Pos logit contributions
wy+0.116
 ruined+0.114
ggy+0.114
ggie+0.110
uch+0.109
Neg logit contributions
 Sus-0.152
 Suz-0.152
 Su-0.151
 Mill-0.148
 Alf-0.145
Token.
Token ID13
Feature activation+7.86e-01

Pos logit contributions
 ruined+0.038
wy+0.038
ggy+0.036
 sharp+0.035
istered+0.035
Neg logit contributions
 Suz-0.056
 Su-0.056
 Mill-0.055
 Sus-0.055
 Alf-0.054
Token His
Token ID2399
Feature activation-1.73e-01

Pos logit contributions
 Ally+0.019
ress+0.018
 Mill+0.018
 Hil+0.018
 Suz+0.018
Neg logit contributions
 big-0.013
 sharp-0.012
 burns-0.011
 not-0.011
 funny-0.011
Token mom
Token ID1995
Feature activation-1.10e-01

Pos logit contributions
wy+0.004
 ruined+0.004
istered+0.004
arest+0.004
ching+0.004
Neg logit contributions
 Suz-0.003
 Su-0.003
 Sus-0.003
 Alf-0.003
 Mill-0.003
Token Things
Token ID11597
Feature activation-2.01e+00

Pos logit contributions
 Su+0.052
 Suz+0.051
 Mill+0.051
line+0.051
 Sus+0.050
Neg logit contributions
 ruined-0.048
 burns-0.048
 sharp-0.046
ggy-0.045
 pain-0.045
Token had
Token ID550
Feature activation-3.19e+00

Pos logit contributions
wy+0.039
 ruined+0.038
ggy+0.037
istered+0.037
ggie+0.036
Neg logit contributions
 Suz-0.047
 Su-0.047
 Mill-0.047
 Sus-0.046
 Alf-0.045
Token been
Token ID587
Feature activation-5.41e+00

Pos logit contributions
wy+0.054
istered+0.052
uch+0.049
ggy+0.048
 Deal+0.048
Neg logit contributions
 Su-0.086
 Suz-0.086
 Sus-0.085
 Mill-0.084
 Alf-0.081
Token moved
Token ID3888
Feature activation+2.42e-01

Pos logit contributions
wy+0.107
istered+0.102
uch+0.100
ggy+0.100
 sting+0.098
Neg logit contributions
 Su-0.130
 Sus-0.129
 Suz-0.128
 Mill-0.125
 Alf-0.118
Token around
Token ID1088
Feature activation+2.39e+00

Pos logit contributions
 Suz+0.005
 Su+0.005
 Mill+0.005
 Sus+0.005
 Alf+0.005
Neg logit contributions
 ruined-0.005
wy-0.005
 sharp-0.005
ggy-0.005
istered-0.005
Token and
Token ID290
Feature activation+6.33e+00

Pos logit contributions
 Suz+0.058
 Su+0.058
 Alf+0.057
 Mill+0.056
 Sus+0.055
Neg logit contributions
 ruined-0.044
 sharp-0.041
 pain-0.039
 bad-0.039
wy-0.038
Token the
Token ID262
Feature activation+1.93e+00

Pos logit contributions
 Su+0.140
 Suz+0.140
 Alf+0.138
 Mill+0.137
 Sus+0.133
Neg logit contributions
 ruined-0.131
 sharp-0.121
 hurt-0.118
 bad-0.114
 pain-0.113
Token sand
Token ID6450
Feature activation+4.36e-01

Pos logit contributions
 Sus+0.038
 Suz+0.038
 Mill+0.038
 Su+0.038
 Alf+0.035
Neg logit contributions
wy-0.046
ggy-0.044
istered-0.044
 ruined-0.043
ggie-0.043
Token was
Token ID373
Feature activation-4.09e+00

Pos logit contributions
 Suz+0.011
 Su+0.011
 Mill+0.011
 Sus+0.011
 Alf+0.010
Neg logit contributions
 ruined-0.008
wy-0.008
ggy-0.007
 sharp-0.007
istered-0.007
Token in
Token ID287
Feature activation+1.24e+00

Pos logit contributions
wy+0.082
ggy+0.077
uch+0.077
istered+0.076
ggie+0.075
Neg logit contributions
 Suz-0.097
 Su-0.097
 Sus-0.096
 Mill-0.095
 Alf-0.091
Token different
Token ID1180
Feature activation+1.57e+00

Pos logit contributions
 Suz+0.026
 Sus+0.026
 Su+0.026
 Mill+0.026
 Alf+0.024
Neg logit contributions
wy-0.030
uch-0.029
ggy-0.028
istered-0.027
ggie-0.027
Token kids
Token ID3988
Feature activation-1.56e+00

Pos logit contributions
 Suz+0.083
 Su+0.082
 Mill+0.081
 Sus+0.080
 Alf+0.079
Neg logit contributions
 ruined-0.068
wy-0.067
ggy-0.064
 sharp-0.064
ggie-0.062
Token learned
Token ID4499
Feature activation-2.32e+00

Pos logit contributions
 ruined+0.030
 hurt+0.027
wy+0.026
 sharp+0.026
ggy+0.025
Neg logit contributions
 Suz-0.039
 Su-0.038
 Mill-0.037
 Alf-0.037
 Sus-0.037
Token about
Token ID546
Feature activation+3.67e-02

Pos logit contributions
 ruined+0.040
wy+0.039
ggy+0.038
 sharp+0.038
ggie+0.037
Neg logit contributions
 Suz-0.060
 Su-0.059
 Mill-0.058
 Sus-0.058
 Alf-0.057
Token the
Token ID262
Feature activation+8.83e-01

Pos logit contributions
 Suz+0.001
 Su+0.001
 Sus+0.001
 Mill+0.001
 Alf+0.001
Neg logit contributions
 sharp-0.001
 ruined-0.001
ggy-0.001
 bad-0.001
 hurt-0.001
Token jewel
Token ID16927
Feature activation-8.75e-01

Pos logit contributions
 Mill+0.022
 Sus+0.021
 Alf+0.021
 Suz+0.021
 Su+0.020
Neg logit contributions
wy-0.016
istered-0.015
ggy-0.015
 ruined-0.015
 burns-0.014
Token and
Token ID290
Feature activation+5.58e+00

Pos logit contributions
 ruined+0.015
wy+0.014
ggy+0.014
 sharp+0.014
ggie+0.013
Neg logit contributions
 Suz-0.023
 Su-0.023
 Mill-0.023
 Sus-0.023
 Alf-0.022
Token asked
Token ID1965
Feature activation+3.66e+00

Pos logit contributions
 Suz+0.130
 Su+0.127
 Mill+0.125
 Sus+0.123
 Alf+0.120
Neg logit contributions
 ruined-0.114
 sharp-0.106
 hurt-0.105
 bad-0.102
ggy-0.099
Token to
Token ID284
Feature activation+8.81e-01

Pos logit contributions
 Suz+0.090
 Su+0.087
 Mill+0.084
 Hil+0.084
ress+0.083
Neg logit contributions
 bad-0.066
 sharp-0.062
 big-0.060
 naughty-0.059
 funny-0.059
Token come
Token ID1282
Feature activation-1.60e+00

Pos logit contributions
 Suz+0.021
 Su+0.021
 Mill+0.021
 Sus+0.021
 Alf+0.020
Neg logit contributions
wy-0.017
 ruined-0.016
istered-0.016
ggy-0.016
 sharp-0.015
Token and
Token ID290
Feature activation+4.45e+00

Pos logit contributions
 ruined+0.026
ggy+0.026
 sharp+0.026
 hurt+0.025
wy+0.025
Neg logit contributions
 Su-0.040
 Suz-0.039
 Mill-0.038
 Sus-0.038
 Alf-0.037
Token see
Token ID766
Feature activation+1.43e+00

Pos logit contributions
 Suz+0.108
 Su+0.106
 Mill+0.106
 Sus+0.105
 Alf+0.103
Neg logit contributions
wy-0.084
 ruined-0.083
ggy-0.079
istered-0.078
 sharp-0.077
Token She
Token ID1375
Feature activation-3.43e-01

Pos logit contributions
 Alf+0.049
 Suz+0.046
reating+0.046
 cities+0.046
 Cr+0.046
Neg logit contributions
 big-0.026
A-0.025
 sharp-0.023
 two-0.023
 a-0.022
Token walked
Token ID6807
Feature activation+3.59e-01

Pos logit contributions
 ruined+0.007
wy+0.007
ggy+0.006
 sharp+0.006
istered+0.006
Neg logit contributions
 Suz-0.008
 Su-0.008
 Mill-0.008
 Sus-0.008
 Alf-0.008
Token up
Token ID510
Feature activation+2.09e+00

Pos logit contributions
 Su+0.009
 Suz+0.009
 Alf+0.009
 Mill+0.008
 Sus+0.008
Neg logit contributions
 sharp-0.006
 big-0.006
 ruined-0.006
 hurt-0.006
 naughty-0.006
Token to
Token ID284
Feature activation+4.23e+00

Pos logit contributions
 Alf+0.050
 Su+0.050
 Suz+0.049
 Cr+0.049
 Hil+0.048
Neg logit contributions
 sharp-0.037
 big-0.036
 ruined-0.035
 hurt-0.035
 broken-0.033
Token it
Token ID340
Feature activation-3.75e-01

Pos logit contributions
 Suz+0.098
 Su+0.096
 Alf+0.094
 Mill+0.093
 Sus+0.092
Neg logit contributions
 sharp-0.079
 ruined-0.078
 hurt-0.075
 pain-0.074
 bad-0.074
Token and
Token ID290
Feature activation+6.93e+00

Pos logit contributions
 sharp+0.005
 ruined+0.005
 hurt+0.005
ggy+0.005
 big+0.005
Neg logit contributions
 Su-0.011
 Suz-0.011
 Alf-0.010
 Sus-0.010
 Mill-0.010
Token knocked
Token ID13642
Feature activation+4.15e+00

Pos logit contributions
 Suz+0.190
 Su+0.189
 Alf+0.185
 Mill+0.182
 Sus+0.180
Neg logit contributions
 ruined-0.105
 sharp-0.101
 hurt-0.098
 naughty-0.090
 broken-0.088
Token on
Token ID319
Feature activation+2.86e+00

Pos logit contributions
 Alf+0.116
bank+0.113
 Suz+0.113
 Cr+0.112
 Mill+0.112
Neg logit contributions
 ruined-0.057
 sharp-0.056
 hurt-0.054
 pain-0.054
wy-0.053
Token the
Token ID262
Feature activation+2.62e+00

Pos logit contributions
 Suz+0.070
 Cr+0.069
 Alf+0.068
 Su+0.068
bank+0.067
Neg logit contributions
 sharp-0.051
 ruined-0.049
 big-0.047
 hurt-0.046
 bad-0.046
Token door
Token ID3420
Feature activation+1.59e+00

Pos logit contributions
 Suz+0.059
 Su+0.058
 Mill+0.057
 Sus+0.057
 Alf+0.056
Neg logit contributions
 ruined-0.055
 sharp-0.052
wy-0.052
ggy-0.051
 burns-0.051
Token.
Token ID13
Feature activation+2.30e+00

Pos logit contributions
 Cr+0.048
 Suz+0.047
 Mill+0.047
 Alf+0.047
 Su+0.047
Neg logit contributions
 ruined-0.018
 sharp-0.017
 hurt-0.016
 burns-0.016
ggy-0.016
Token flower
Token ID15061
Feature activation+1.13e+00

Pos logit contributions
 Mill+0.016
 Sus+0.015
 Suz+0.015
 Ally+0.015
 cities+0.014
Neg logit contributions
wy-0.017
istered-0.017
ggy-0.016
ggie-0.016
uch-0.016
Token was
Token ID373
Feature activation-5.02e+00

Pos logit contributions
 Suz+0.029
 Mill+0.028
 Su+0.028
 Sus+0.028
 Alf+0.027
Neg logit contributions
wy-0.020
 ruined-0.019
istered-0.019
ggy-0.018
ggie-0.018
Token growing
Token ID3957
Feature activation-2.58e+00

Pos logit contributions
wy+0.088
arest+0.080
istered+0.079
uch+0.079
itch+0.079
Neg logit contributions
 Sus-0.132
 Suz-0.132
 Mill-0.132
 Su-0.130
 Jan-0.120
Token even
Token ID772
Feature activation+1.21e+00

Pos logit contributions
ggy+0.051
wy+0.050
ggie+0.049
istered+0.047
 ruined+0.047
Neg logit contributions
 Suz-0.061
 Mill-0.060
 Sus-0.060
 Su-0.060
 Jan-0.054
Token bigger
Token ID5749
Feature activation+1.12e+00

Pos logit contributions
 Suz+0.030
 Sus+0.030
 Su+0.030
 Mill+0.030
 Alf+0.028
Neg logit contributions
ggy-0.022
ggie-0.021
wy-0.021
istered-0.021
uch-0.020
Token and
Token ID290
Feature activation+5.97e+00

Pos logit contributions
 Suz+0.028
 Su+0.027
 Mill+0.027
 Sus+0.027
 Alf+0.026
Neg logit contributions
 ruined-0.020
wy-0.020
ggy-0.019
 sharp-0.019
istered-0.019
Token brighter
Token ID26083
Feature activation+3.18e-01

Pos logit contributions
 Suz+0.166
 Su+0.164
 Mill+0.162
 Sus+0.161
 Alf+0.159
Neg logit contributions
 ruined-0.091
wy-0.089
ggy-0.084
 sharp-0.083
istered-0.081
Token.
Token ID13
Feature activation+2.05e+00

Pos logit contributions
 Suz+0.008
 Su+0.008
 Mill+0.008
 Sus+0.008
 Alf+0.008
Neg logit contributions
 ruined-0.006
wy-0.006
ggy-0.005
 sharp-0.005
istered-0.005
Token The
Token ID383
Feature activation+1.59e+00

Pos logit contributions
 forth+0.043
iked+0.042
 ships+0.041
 Su+0.041
line+0.041
Neg logit contributions
 two-0.034
A-0.032
 Deal-0.031
 sharp-0.031
 big-0.030
Token comet
Token ID31733
Feature activation-1.79e-01

Pos logit contributions
 Mill+0.033
 cities+0.033
 Sus+0.032
 Suz+0.032
 Ally+0.031
Neg logit contributions
istered-0.033
ggy-0.032
wy-0.032
uch-0.031
ggie-0.030
Token was
Token ID373
Feature activation-5.02e+00

Pos logit contributions
 ruined+0.003
wy+0.003
ggy+0.003
 sharp+0.003
istered+0.003
Neg logit contributions
 Suz-0.005
 Su-0.005
 Mill-0.005
 Sus-0.004
 Alf-0.004
Token!
Token ID0
Feature activation+2.70e+00

Pos logit contributions
 Su+0.006
 Suz+0.006
 Alf+0.006
 Mill+0.006
 Ally+0.005
Neg logit contributions
ggy-0.003
 ruined-0.003
 sharp-0.003
ggie-0.003
 hurt-0.003
Token She
Token ID1375
Feature activation+8.22e-01

Pos logit contributions
 Suz+0.062
 Mill+0.060
 Alf+0.060
 Su+0.059
 cities+0.059
Neg logit contributions
 sharp-0.042
 ruined-0.041
 big-0.040
 pain-0.039
ggy-0.039
Token thanked
Token ID26280
Feature activation+4.78e+00

Pos logit contributions
 Suz+0.020
 Su+0.019
 Mill+0.019
 Sus+0.019
 Alf+0.019
Neg logit contributions
wy-0.016
 ruined-0.015
istered-0.015
ggy-0.015
ggie-0.015
Token the
Token ID262
Feature activation+2.74e+00

Pos logit contributions
bank+0.121
iked+0.117
line+0.114
 Suz+0.113
ress+0.113
Neg logit contributions
 sharp-0.068
 big-0.066
 bad-0.066
 hurt-0.062
 two-0.062
Token man
Token ID582
Feature activation+2.25e+00

Pos logit contributions
 Suz+0.064
 Su+0.063
 Mill+0.062
 Sus+0.062
 Alf+0.060
Neg logit contributions
 ruined-0.055
 sharp-0.054
wy-0.052
 pain-0.052
 hurt-0.052
Token and
Token ID290
Feature activation+6.56e+00

Pos logit contributions
 Suz+0.067
 Su+0.066
 Sus+0.064
 Mill+0.063
 Hil+0.063
Neg logit contributions
 sharp-0.028
a-0.027
ggy-0.027
ggie-0.027
ching-0.025
Token sailed
Token ID33835
Feature activation+1.75e+00

Pos logit contributions
 Suz+0.155
 Su+0.154
 Mill+0.151
 Alf+0.151
 Sus+0.149
Neg logit contributions
 ruined-0.117
 hurt-0.109
 sharp-0.108
ggy-0.103
 bad-0.100
Token away
Token ID1497
Feature activation+2.16e+00

Pos logit contributions
 Suz+0.046
 Su+0.045
 Mill+0.044
 Alf+0.044
 Sus+0.043
Neg logit contributions
 sharp-0.028
 ruined-0.027
 big-0.027
 bad-0.026
 hurt-0.026
Token.
Token ID13
Feature activation+2.48e+00

Pos logit contributions
 Suz+0.054
 Su+0.053
 Mill+0.052
 Alf+0.051
 Sus+0.051
Neg logit contributions
 ruined-0.039
 sharp-0.037
 hurt-0.036
ggy-0.036
 sting-0.035
Token It
Token ID632
Feature activation-2.05e+00

Pos logit contributions
 cities+0.049
 Suz+0.049
 Alf+0.048
 Su+0.048
ho+0.047
Neg logit contributions
 two-0.043
 sharp-0.041
 pain-0.041
ching-0.041
 ruined-0.040
Token was
Token ID373
Feature activation-5.10e+00

Pos logit contributions
wy+0.038
istered+0.037
 ruined+0.035
ggy+0.035
ggie+0.035
Neg logit contributions
 Suz-0.051
 Mill-0.050
 Su-0.050
 Sus-0.049
 Alf-0.049
TokenPeter
Token ID19727
Feature activation-3.01e-01

Pos logit contributions
wy+0.091
 ruined+0.088
istered+0.085
 sting+0.084
ggy+0.084
Neg logit contributions
 Mill-0.095
 Suz-0.095
 Alf-0.092
 Sus-0.092
 Su-0.092
Token was
Token ID373
Feature activation-5.63e+00

Pos logit contributions
wy+0.006
istered+0.006
 ruined+0.006
uch+0.006
ggy+0.006
Neg logit contributions
 Suz-0.007
 Su-0.007
 Sus-0.007
 Mill-0.007
 Alf-0.006
Token sad
Token ID6507
Feature activation-5.96e-01

Pos logit contributions
wy+0.125
istered+0.112
 ruined+0.111
uch+0.110
ggy+0.110
Neg logit contributions
 Suz-0.127
 Su-0.127
 Sus-0.125
 Mill-0.123
 Alf-0.118
Token that
Token ID326
Feature activation+2.50e+00

Pos logit contributions
 ruined+0.013
wy+0.013
 sharp+0.012
ggy+0.012
istered+0.012
Neg logit contributions
 Suz-0.013
 Su-0.013
 Mill-0.012
 Sus-0.012
 Alf-0.012
Token the
Token ID262
Feature activation+1.25e+00

Pos logit contributions
 Suz+0.058
ress+0.058
iked+0.058
 Ally+0.058
 Hil+0.058
Neg logit contributions
 bad-0.046
 hurt-0.046
 pain-0.045
 ruined-0.044
 sharp-0.043
Token ot
Token ID30972
Feature activation+3.43e+00

Pos logit contributions
 Suz+0.016
 Su+0.016
 Mill+0.015
 Sus+0.015
 Alf+0.014
Neg logit contributions
 ruined-0.038
wy-0.037
 sharp-0.037
 hurt-0.036
 pain-0.036
Tokenter
Token ID353
Feature activation+6.95e-01

Pos logit contributions
 Suz+0.057
 Su+0.057
 Mill+0.056
 Sus+0.056
 Alf+0.054
Neg logit contributions
 ruined-0.090
wy-0.088
ggy-0.085
 sharp-0.085
uch-0.084
Token was
Token ID373
Feature activation-4.51e+00

Pos logit contributions
 Suz+0.018
 Su+0.018
 Mill+0.018
 Sus+0.017
 Alf+0.017
Neg logit contributions
wy-0.012
 ruined-0.012
ggy-0.011
 sharp-0.011
istered-0.011
Token gone
Token ID3750
Feature activation-8.55e-01

Pos logit contributions
wy+0.084
istered+0.077
uch+0.076
ggy+0.074
arest+0.073
Neg logit contributions
 Sus-0.114
 Su-0.114
 Suz-0.113
 Mill-0.112
 Alf-0.106
Token,
Token ID11
Feature activation+3.77e+00

Pos logit contributions
wy+0.018
 ruined+0.017
ggy+0.017
ggie+0.017
istered+0.017
Neg logit contributions
 Suz-0.019
 Su-0.019
 Mill-0.019
 Sus-0.018
 Alf-0.018
Token but
Token ID475
Feature activation+4.69e+00

Pos logit contributions
 Suz+0.088
 Alf+0.084
 Su+0.084
 Mill+0.083
 Jan+0.081
Neg logit contributions
 ruined-0.076
 sharp-0.074
 hurt-0.072
 pain-0.070
 bad-0.070
Token.
Token ID13
Feature activation+1.34e+00

Pos logit contributions
 Su+0.019
 Suz+0.019
 Mill+0.018
 Alf+0.018
 Sus+0.018
Neg logit contributions
 ruined-0.009
 sharp-0.008
ggy-0.008
 burns-0.008
 hurt-0.008
Token
Token ID220
Feature activation-5.15e+00

Pos logit contributions
ho+0.031
 Suz+0.031
 Su+0.030
ress+0.030
iked+0.030
Neg logit contributions
 two-0.019
A-0.018
 ruined-0.018
 Deal-0.018
 big-0.018
Token
Token ID198
Feature activation-4.75e+00

Pos logit contributions
 ruined+0.098
ggy+0.096
wy+0.096
ggie+0.092
 sharp+0.092
Neg logit contributions
 Suz-0.118
 Su-0.117
 Mill-0.116
 Sus-0.114
 Alf-0.112
Token
Token ID198
Feature activation-3.95e+00

Pos logit contributions
ggy+0.088
 ruined+0.088
wy+0.088
ggie+0.085
 sharp+0.084
Neg logit contributions
 Suz-0.112
 Su-0.110
 Mill-0.109
 Sus-0.108
 Alf-0.107
TokenOn
Token ID2202
Feature activation-1.56e+00

Pos logit contributions
 ruined+0.048
wy+0.048
ggy+0.047
ggie+0.045
 sharp+0.044
Neg logit contributions
 Suz-0.120
 Su-0.119
 Mill-0.119
 Sus-0.117
 Alf-0.116
Token Monday
Token ID3321
Feature activation+4.16e+00

Pos logit contributions
 ruined+0.035
wy+0.035
ggy+0.034
 sharp+0.033
ggie+0.033
Neg logit contributions
 Suz-0.032
 Su-0.031
 Mill-0.031
 Sus-0.031
 Alf-0.030
Token morning
Token ID3329
Feature activation+1.92e+00

Pos logit contributions
 Suz+0.109
 Cr+0.105
 Su+0.104
 Alf+0.102
 Jan+0.099
Neg logit contributions
 big-0.058
ggie-0.056
ggy-0.056
 two-0.055
 time-0.055
Token,
Token ID11
Feature activation+4.29e+00

Pos logit contributions
 Suz+0.040
 Su+0.040
 Mill+0.039
 Alf+0.039
 Sus+0.038
Neg logit contributions
 ruined-0.041
ggy-0.040
wy-0.039
 sharp-0.039
ggie-0.039
Token the
Token ID262
Feature activation+6.72e-01

Pos logit contributions
 Suz+0.087
 Su+0.085
 Mill+0.084
 Alf+0.083
 Sus+0.081
Neg logit contributions
 ruined-0.090
 sharp-0.087
ggy-0.086
ggie-0.084
 bad-0.084
Token family
Token ID1641
Feature activation+6.76e-01

Pos logit contributions
 Su+0.016
 Suz+0.016
 Sus+0.015
 Mill+0.015
 Alf+0.015
Neg logit contributions
 ruined-0.013
 sharp-0.013
wy-0.013
 pain-0.012
 naughty-0.012
Token gathered
Token ID9272
Feature activation+2.07e+00

Pos logit contributions
 Suz+0.017
 Su+0.017
 Mill+0.016
 Sus+0.016
 Alf+0.016
Neg logit contributions
 ruined-0.012
wy-0.012
 sharp-0.011
 burns-0.011
ggy-0.011
Token,
Token ID11
Feature activation+2.55e+00

Pos logit contributions
 sharp+0.001
 ruined+0.001
 bad+0.001
 pain+0.001
 hurt+0.001
Neg logit contributions
 Suz-0.002
 Alf-0.002
 Su-0.002
 Mill-0.002
 Sus-0.002
Token but
Token ID475
Feature activation+4.21e+00

Pos logit contributions
 Suz+0.064
ress+0.064
 Sus+0.062
 Alf+0.062
 Su+0.061
Neg logit contributions
 sharp-0.047
 hurt-0.045
 bad-0.044
 ruined-0.043
 not-0.043
Token she
Token ID673
Feature activation-1.36e+00

Pos logit contributions
 Suz+0.091
 Su+0.090
 Alf+0.089
 Sus+0.089
 Mill+0.088
Neg logit contributions
 ruined-0.090
 sharp-0.089
 hurt-0.086
ggy-0.084
 bad-0.083
Token was
Token ID373
Feature activation-5.06e+00

Pos logit contributions
wy+0.032
istered+0.031
ps+0.030
arest+0.029
 burns+0.029
Neg logit contributions
 Suz-0.027
 Su-0.026
 Mill-0.026
 Sus-0.026
 Alf-0.025
Token brave
Token ID14802
Feature activation-1.35e-01

Pos logit contributions
wy+0.097
uch+0.090
istered+0.086
 burns+0.084
itch+0.083
Neg logit contributions
 Suz-0.127
 Su-0.126
 Mill-0.125
 Sus-0.124
 K-0.118
Token and
Token ID290
Feature activation+3.73e+00

Pos logit contributions
 ruined+0.002
wy+0.002
ggy+0.002
 sharp+0.002
istered+0.002
Neg logit contributions
 Suz-0.003
 Su-0.003
 Mill-0.003
 Sus-0.003
 Alf-0.003
Token decided
Token ID3066
Feature activation+1.54e+00

Pos logit contributions
 Suz+0.097
 Su+0.096
 Sus+0.095
 Mill+0.095
 Alf+0.095
Neg logit contributions
 ruined-0.064
 sharp-0.062
ggy-0.060
wy-0.059
 hurt-0.058
Token to
Token ID284
Feature activation-3.13e-01

Pos logit contributions
 Suz+0.036
 Alf+0.036
 Su+0.034
 Jos+0.034
 Mill+0.034
Neg logit contributions
 sharp-0.031
 hurt-0.031
 ruined-0.030
ggy-0.030
 bad-0.030
Token go
Token ID467
Feature activation+8.08e-01

Pos logit contributions
wy+0.006
 ruined+0.006
istered+0.006
ggy+0.005
 sharp+0.005
Neg logit contributions
 Suz-0.008
 Mill-0.007
 Su-0.007
 Sus-0.007
 Alf-0.007
Token in
Token ID287
Feature activation+1.26e+00

Pos logit contributions
 Suz+0.019
 Su+0.018
 Mill+0.018
 Sus+0.018
 Alf+0.018
Neg logit contributions
 ruined-0.016
wy-0.016
 sharp-0.015
ggy-0.015
 hurt-0.015
Token anyway
Token ID6949
Feature activation+8.17e-01

Pos logit contributions
 Suz+0.035
 Su+0.035
 Mill+0.034
 Alf+0.034
 Sus+0.034
Neg logit contributions
 ruined-0.018
 sharp-0.017
ggy-0.017
 pain-0.016
 hurt-0.016
Token was
Token ID373
Feature activation-5.58e+00

Pos logit contributions
 ruined+0.054
wy+0.053
ggy+0.050
 sharp+0.050
istered+0.049
Neg logit contributions
 Suz-0.088
 Su-0.087
 Mill-0.086
 Sus-0.086
 Alf-0.085
Token messy
Token ID24097
Feature activation-8.85e-01

Pos logit contributions
wy+0.083
arest+0.080
istered+0.078
uch+0.078
ggy+0.076
Neg logit contributions
 Suz-0.158
 Su-0.157
 Mill-0.156
 Sus-0.154
 Alf-0.150
Token,
Token ID11
Feature activation+3.38e+00

Pos logit contributions
wy+0.017
 ruined+0.017
ggy+0.016
 sharp+0.016
ggie+0.016
Neg logit contributions
 Suz-0.021
 Su-0.021
 Mill-0.021
 Sus-0.020
 Alf-0.020
Token sticks
Token ID16461
Feature activation-8.37e-02

Pos logit contributions
 Suz+0.081
 Mill+0.081
 Alf+0.080
 Su+0.079
 Sus+0.079
Neg logit contributions
 ruined-0.066
 sharp-0.064
 bad-0.060
 hurt-0.060
 pain-0.059
Token poking
Token ID39048
Feature activation+3.26e+00

Pos logit contributions
wy+0.002
 ruined+0.002
ggy+0.002
ggie+0.002
 sharp+0.002
Neg logit contributions
 Suz-0.002
 Su-0.002
 Mill-0.002
 Sus-0.002
 Alf-0.002
Token out
Token ID503
Feature activation+2.37e+00

Pos logit contributions
 Suz+0.075
 Su+0.075
 Mill+0.073
 Sus+0.073
 Alf+0.072
Neg logit contributions
 sharp-0.065
 ruined-0.065
wy-0.061
 burns-0.060
 bad-0.060
Token and
Token ID290
Feature activation+6.28e+00

Pos logit contributions
 Suz+0.063
 Su+0.063
 Mill+0.063
 Sus+0.062
 Alf+0.061
Neg logit contributions
 ruined-0.038
 sharp-0.036
wy-0.035
 burns-0.034
 pain-0.033
Token leaves
Token ID5667
Feature activation+3.07e-01

Pos logit contributions
 Su+0.154
 Suz+0.152
 Mill+0.151
 Alf+0.151
 Sus+0.149
Neg logit contributions
 ruined-0.122
 sharp-0.114
 hurt-0.113
 sting-0.109
 burns-0.108
Token all
Token ID477
Feature activation+2.75e+00

Pos logit contributions
 Suz+0.008
 Su+0.008
 Mill+0.008
 Sus+0.008
 Alf+0.007
Neg logit contributions
wy-0.005
 ruined-0.005
ggy-0.005
 sharp-0.005
ggie-0.005
Token over
Token ID625
Feature activation+4.12e+00

Pos logit contributions
 Alf+0.058
 Su+0.057
 Mill+0.057
 Suz+0.057
ress+0.055
Neg logit contributions
 ruined-0.063
 hurt-0.057
 sharp-0.056
wy-0.056
 bad-0.056
Token the
Token ID262
Feature activation+3.42e+00

Pos logit contributions
 Suz+0.095
 Su+0.094
 Alf+0.094
 Mill+0.094
 Sus+0.092
Neg logit contributions
 ruined-0.080
 sharp-0.078
 hurt-0.073
 pain-0.073
 bad-0.073
Token,
Token ID11
Feature activation+3.32e+00

Pos logit contributions
 ruined+0.017
wy+0.017
ggy+0.016
 sharp+0.016
istered+0.016
Neg logit contributions
 Suz-0.014
 Su-0.014
 Mill-0.014
 Sus-0.014
 Alf-0.014
Token her
Token ID607
Feature activation+1.43e-01

Pos logit contributions
 Suz+0.054
 Su+0.054
 Mill+0.053
 Alf+0.053
 Sus+0.051
Neg logit contributions
 ruined-0.088
 sharp-0.084
ggy-0.083
wy-0.083
 hurt-0.082
Token mom
Token ID1995
Feature activation+6.57e-01

Pos logit contributions
 Suz+0.003
 Su+0.003
 Sus+0.003
 Jan+0.003
 Alf+0.003
Neg logit contributions
wy-0.004
arest-0.003
istered-0.003
ery-0.003
uch-0.003
Tokenmy
Token ID1820
Feature activation-1.19e+00

Pos logit contributions
 Suz+0.015
 Su+0.015
 Mill+0.015
 Sus+0.014
 Alf+0.014
Neg logit contributions
 ruined-0.013
wy-0.013
ggy-0.012
 sharp-0.012
 hurt-0.012
Token helped
Token ID4193
Feature activation+4.56e+00

Pos logit contributions
 ruined+0.021
wy+0.021
ggy+0.020
 sharp+0.019
ggie+0.019
Neg logit contributions
 Suz-0.030
 Su-0.029
 Mill-0.029
 Sus-0.029
 Alf-0.029
Token her
Token ID607
Feature activation+1.19e+00

Pos logit contributions
 Suz+0.085
 Su+0.084
 Mill+0.082
 Alf+0.081
 Sus+0.081
Neg logit contributions
 ruined-0.111
wy-0.109
ggy-0.106
 sharp-0.106
 sting-0.104
Token get
Token ID651
Feature activation-2.57e+00

Pos logit contributions
 Su+0.028
 Suz+0.028
 Sus+0.027
 Mill+0.027
 Alf+0.026
Neg logit contributions
wy-0.025
 ruined-0.023
istered-0.023
uch-0.022
 sharp-0.022
Token ready
Token ID3492
Feature activation+1.26e+00

Pos logit contributions
 ruined+0.045
wy+0.044
 sharp+0.042
ggy+0.042
istered+0.041
Neg logit contributions
 Suz-0.066
 Su-0.065
 Mill-0.065
 Sus-0.064
 Alf-0.063
Token for
Token ID329
Feature activation-4.65e-02

Pos logit contributions
 Suz+0.025
 Su+0.024
 Mill+0.024
 Sus+0.023
 Alf+0.023
Neg logit contributions
 ruined-0.029
wy-0.029
 sharp-0.028
ggy-0.028
 burns-0.027
Token class
Token ID1398
Feature activation-1.64e+00

Pos logit contributions
wy+0.001
 ruined+0.001
ggy+0.001
istered+0.001
 sharp+0.001
Neg logit contributions
 Suz-0.001
 Su-0.001
 Sus-0.001
 Mill-0.001
 Alf-0.001
Token by
Token ID416
Feature activation+7.28e-01

Pos logit contributions
 ruined+0.026
wy+0.026
ggy+0.025
 sharp+0.024
ggie+0.024
Neg logit contributions
 Suz-0.044
 Su-0.043
 Mill-0.043
 Sus-0.043
 Alf-0.042
Token big
Token ID1263
Feature activation-2.39e-01

Pos logit contributions
wy+0.053
 ruined+0.048
istered+0.046
ps+0.045
 burns+0.045
Neg logit contributions
 Suz-0.107
 Su-0.106
 Mill-0.105
 Sus-0.105
 Ally-0.100
Token k
Token ID479
Feature activation+1.44e+00

Pos logit contributions
 ruined+0.005
 sharp+0.005
wy+0.005
 pain+0.005
ggy+0.005
Neg logit contributions
 Suz-0.005
 Su-0.005
 Alf-0.005
 Mill-0.005
 Sus-0.005
Tokenite
Token ID578
Feature activation+1.47e-01

Pos logit contributions
 Suz+0.026
 Su+0.026
 Mill+0.025
 Sus+0.025
 Alf+0.024
Neg logit contributions
 ruined-0.036
wy-0.036
ggy-0.035
 sharp-0.035
istered-0.034
Token with
Token ID351
Feature activation+6.11e-01

Pos logit contributions
 Suz+0.004
 Su+0.004
 Mill+0.004
 Sus+0.004
 Alf+0.004
Neg logit contributions
 ruined-0.002
wy-0.002
ggy-0.002
 sharp-0.002
istered-0.002
Token a
Token ID257
Feature activation-3.69e+00

Pos logit contributions
 Suz+0.017
 Su+0.016
 Mill+0.016
 Sus+0.016
 Alf+0.016
Neg logit contributions
wy-0.010
 ruined-0.010
ggy-0.009
istered-0.009
ggie-0.009
Token colorful
Token ID20239
Feature activation-7.36e-01

Pos logit contributions
wy+0.070
istered+0.056
 ruined+0.056
 burns+0.056
ggy+0.056
Neg logit contributions
 Mill-0.096
 Suz-0.095
 Su-0.095
 Sus-0.095
 Alf-0.094
Token tail
Token ID7894
Feature activation-9.20e-02

Pos logit contributions
wy+0.012
 ruined+0.012
ggy+0.011
istered+0.011
ggie+0.011
Neg logit contributions
 Suz-0.019
 Su-0.019
 Mill-0.019
 Sus-0.019
 Alf-0.019
Token.
Token ID13
Feature activation+2.53e+00

Pos logit contributions
wy+0.002
 ruined+0.002
istered+0.002
ggy+0.002
uch+0.002
Neg logit contributions
 Suz-0.002
 Su-0.002
 Mill-0.002
 Sus-0.002
 Alf-0.002
Token Anna
Token ID11735
Feature activation-9.40e-01

Pos logit contributions
 Suz+0.061
 Su+0.060
 Mill+0.059
 Sus+0.058
 Alf+0.058
Neg logit contributions
 ruined-0.047
wy-0.045
ggy-0.045
ggie-0.044
 sharp-0.044
Token and
Token ID290
Feature activation+5.65e+00

Pos logit contributions
wy+0.018
 ruined+0.017
istered+0.017
ggy+0.016
 burns+0.016
Neg logit contributions
 Suz-0.023
 Su-0.022
 Mill-0.022
 Sus-0.022
 Alf-0.022
Token her
Token ID607
Feature activation+6.48e-01

Pos logit contributions
 Suz+0.106
 Su+0.104
 Mill+0.103
 Sus+0.101
 Alf+0.099
Neg logit contributions
 ruined-0.139
wy-0.137
ggy-0.133
 sharp-0.132
ggie-0.131
Token do
Token ID466
Feature activation-4.27e+00

Pos logit contributions
wy+0.080
istered+0.074
ps+0.073
 sting+0.072
itching+0.071
Neg logit contributions
 Su-0.103
 Sus-0.102
 Suz-0.101
 Mill-0.100
 Jan-0.100
Token you
Token ID345
Feature activation-4.09e+00

Pos logit contributions
wy+0.090
 ruined+0.089
istered+0.086
ps+0.082
 sharp+0.081
Neg logit contributions
 Suz-0.096
 Mill-0.095
 Su-0.094
 Sus-0.094
 Alf-0.091
Token have
Token ID423
Feature activation-5.20e+00

Pos logit contributions
istered+0.077
ggy+0.076
wy+0.075
ggie+0.074
 burns+0.070
Neg logit contributions
 Suz-0.102
 Mill-0.100
 Su-0.099
 Sus-0.098
 Alf-0.095
Token in
Token ID287
Feature activation-2.67e-01

Pos logit contributions
wy+0.108
 ruined+0.105
istered+0.103
ggy+0.102
 sharp+0.100
Neg logit contributions
 Suz-0.117
 Su-0.116
 Mill-0.115
 Sus-0.115
 Alf-0.111
Token the
Token ID262
Feature activation+9.70e-01

Pos logit contributions
wy+0.007
istered+0.006
 ruined+0.006
ggy+0.006
ggie+0.006
Neg logit contributions
 Su-0.005
 Suz-0.005
 Mill-0.005
 Sus-0.005
 Alf-0.005
Token jar
Token ID17379
Feature activation-2.03e+00

Pos logit contributions
 Suz+0.025
 Su+0.024
 Sus+0.024
 Mill+0.024
 Alf+0.023
Neg logit contributions
wy-0.017
 ruined-0.016
ggy-0.016
ggie-0.016
ps-0.016
Token?"
Token ID1701
Feature activation+1.63e+00

Pos logit contributions
wy+0.034
 ruined+0.033
istered+0.032
ggy+0.032
 sharp+0.032
Neg logit contributions
 Suz-0.053
 Mill-0.052
 Su-0.052
 Sus-0.052
 Alf-0.050
Token he
Token ID339
Feature activation-1.30e+00

Pos logit contributions
 Suz+0.039
 Su+0.037
 Mill+0.035
 Hil+0.035
 Jan+0.034
Neg logit contributions
 ruined-0.031
 hurt-0.031
 sharp-0.030
 bad-0.029
ggy-0.028
Token asked
Token ID1965
Feature activation+3.49e+00

Pos logit contributions
 ruined+0.028
wy+0.027
 sharp+0.026
ggy+0.026
ggie+0.026
Neg logit contributions
 Suz-0.028
 Su-0.028
 Mill-0.027
 Sus-0.027
 Alf-0.027
Token.
Token ID13
Feature activation+2.63e+00

Pos logit contributions
 Suz+0.092
 Su+0.088
 Mill+0.085
 Hil+0.085
 Ally+0.084
Neg logit contributions
 ruined-0.056
 hurt-0.054
 sharp-0.053
ggy-0.052
 bad-0.052
Token
Token ID220
Feature activation-4.28e+00

Pos logit contributions
 Suz+0.065
 Su+0.060
 Hil+0.058
 cities+0.058
 Ally+0.057
Neg logit contributions
 hurt-0.042
 big-0.042
 sharp-0.042
 ruined-0.042
A-0.041
Token It
Token ID632
Feature activation-3.02e+00

Pos logit contributions
 Suz+0.034
 Su+0.033
 Mill+0.032
 Sus+0.032
 Alf+0.032
Neg logit contributions
 ruined-0.044
wy-0.044
ggy-0.042
 sharp-0.041
ggie-0.041
Token hurts
Token ID20406
Feature activation+2.00e-01

Pos logit contributions
arest+0.051
wy+0.051
ggie+0.049
istered+0.049
kin+0.048
Neg logit contributions
 Suz-0.073
 Mill-0.069
 Alf-0.068
 Su-0.068
 Sus-0.067
Token my
Token ID616
Feature activation+1.32e-01

Pos logit contributions
 Suz+0.005
 Su+0.005
 Sus+0.005
 Mill+0.005
 Alf+0.004
Neg logit contributions
wy-0.004
 ruined-0.004
istered-0.004
ggy-0.004
ggie-0.004
Token mouth
Token ID5422
Feature activation-1.78e+00

Pos logit contributions
 Suz+0.003
 Su+0.003
 Sus+0.003
 Alf+0.003
 Mill+0.003
Neg logit contributions
wy-0.002
 ruined-0.002
ching-0.002
arest-0.002
ggy-0.002
Token.
Token ID13
Feature activation+1.47e+00

Pos logit contributions
wy+0.041
ggie+0.040
ggy+0.040
arest+0.039
Jeremy+0.038
Neg logit contributions
 Suz-0.030
 Su-0.030
 Sus-0.029
line-0.028
 Mill-0.027
Token It
Token ID632
Feature activation-3.30e+00

Pos logit contributions
 Suz+0.028
 Su+0.027
 Mill+0.027
 Sus+0.026
 Alf+0.026
Neg logit contributions
 ruined-0.036
wy-0.036
ggy-0.034
 sharp-0.034
ggie-0.034
Token is
Token ID318
Feature activation-5.62e+00

Pos logit contributions
arest+0.058
ggie+0.057
wy+0.056
kin+0.055
ggy+0.054
Neg logit contributions
 Suz-0.074
 Alf-0.071
bank-0.071
 Twe-0.070
 Mill-0.069
Token not
Token ID407
Feature activation-5.31e+00

Pos logit contributions
arest+0.089
uch+0.079
wy+0.079
ggie+0.079
ggy+0.079
Neg logit contributions
 Suz-0.151
 Su-0.150
 Mill-0.146
 Sus-0.145
 Alf-0.142
Token tasty
Token ID25103
Feature activation-1.72e+00

Pos logit contributions
ggy+0.070
wy+0.070
uch+0.070
istered+0.069
ggie+0.069
Neg logit contributions
 Suz-0.152
 Su-0.151
 Mill-0.149
 Sus-0.149
 Alf-0.145
Token.
Token ID13
Feature activation+1.32e+00

Pos logit contributions
 ruined+0.033
wy+0.033
ggy+0.032
uch+0.031
istered+0.031
Neg logit contributions
 Suz-0.039
 Su-0.039
 Sus-0.039
 Mill-0.038
 Alf-0.037
Token It
Token ID632
Feature activation-3.30e+00

Pos logit contributions
 Suz+0.024
 Su+0.023
 Mill+0.023
 Sus+0.023
 Alf+0.022
Neg logit contributions
 ruined-0.034
wy-0.033
ggy-0.032
 sharp-0.031
ggie-0.031
Token wise
Token ID10787
Feature activation+3.70e+00

Pos logit contributions
 Suz+0.028
 Su+0.028
 Mill+0.028
 Sus+0.027
 Alf+0.027
Neg logit contributions
 ruined-0.023
wy-0.023
ggy-0.022
 sharp-0.021
istered-0.021
Token owl
Token ID39610
Feature activation+5.66e-01

Pos logit contributions
 Suz+0.087
 Su+0.086
 Sus+0.083
 Mill+0.082
 Alf+0.082
Neg logit contributions
 sharp-0.074
 ruined-0.072
 pain-0.070
 hurt-0.070
 bad-0.069
Token knew
Token ID2993
Feature activation+6.25e-01

Pos logit contributions
 Suz+0.014
 Su+0.014
 Mill+0.014
 Sus+0.014
 Alf+0.014
Neg logit contributions
 ruined-0.010
wy-0.010
ggy-0.009
 sharp-0.009
istered-0.009
Token what
Token ID644
Feature activation-8.83e-01

Pos logit contributions
 Suz+0.014
 Su+0.014
 Mill+0.014
 Alf+0.014
 Sus+0.014
Neg logit contributions
 ruined-0.012
 sharp-0.012
ggy-0.012
 bad-0.011
ggie-0.011
Token to
Token ID284
Feature activation+1.16e-01

Pos logit contributions
 ruined+0.019
ggy+0.018
wy+0.018
 sharp+0.018
ggie+0.018
Neg logit contributions
 Suz-0.019
 Su-0.019
 Mill-0.019
 Sus-0.019
 Alf-0.018
Token do
Token ID466
Feature activation-2.87e+00

Pos logit contributions
 Suz+0.003
 Mill+0.003
 Su+0.003
 Sus+0.003
 Ally+0.003
Neg logit contributions
wy-0.002
istered-0.002
ifying-0.002
obb-0.002
ider-0.002
Token.
Token ID13
Feature activation+2.40e+00

Pos logit contributions
wy+0.056
 ruined+0.054
istered+0.053
ggy+0.051
 sting+0.051
Neg logit contributions
 Suz-0.067
 Sus-0.066
 Su-0.066
 Mill-0.066
 Alf-0.063
Token He
Token ID679
Feature activation-3.29e-01

Pos logit contributions
 Suz+0.058
 Su+0.056
 Hil+0.055
 Mill+0.054
 Alf+0.054
Neg logit contributions
 sharp-0.039
 ruined-0.034
 big-0.033
Luckily-0.033
A-0.033
Token took
Token ID1718
Feature activation+1.41e+00

Pos logit contributions
wy+0.007
istered+0.007
uch+0.007
ggy+0.007
 ruined+0.007
Neg logit contributions
 Suz-0.007
 Mill-0.007
 Su-0.007
 Alf-0.007
 Sus-0.007
Token the
Token ID262
Feature activation+1.40e+00

Pos logit contributions
 Suz+0.034
 Su+0.034
 Mill+0.033
 Sus+0.033
 Alf+0.032
Neg logit contributions
 ruined-0.027
 sharp-0.026
wy-0.026
 pain-0.025
ggy-0.025
Token nail
Token ID17864
Feature activation+1.89e+00

Pos logit contributions
 Suz+0.028
 Mill+0.028
 Su+0.028
 Sus+0.027
 Alf+0.027
Neg logit contributions
wy-0.032
istered-0.030
ggy-0.030
ggie-0.030
 ruined-0.029
Token with
Token ID351
Feature activation+3.94e-01

Pos logit contributions
 Suz+0.004
 Su+0.004
 Mill+0.004
 Sus+0.004
 Alf+0.004
Neg logit contributions
 ruined-0.003
wy-0.003
ggy-0.003
 sharp-0.003
ggie-0.002
Token her
Token ID607
Feature activation+9.12e-01

Pos logit contributions
 Suz+0.007
 Su+0.007
 Mill+0.007
 Sus+0.007
 Alf+0.007
Neg logit contributions
 ruined-0.009
wy-0.009
ggy-0.009
 sharp-0.009
ggie-0.009
Token new
Token ID649
Feature activation+2.25e+00

Pos logit contributions
 Suz+0.024
 Su+0.024
 Mill+0.023
 Sus+0.023
 Alf+0.023
Neg logit contributions
wy-0.015
 ruined-0.015
ggy-0.014
istered-0.014
 sharp-0.014
Token friend
Token ID1545
Feature activation+2.16e+00

Pos logit contributions
 Suz+0.057
 Su+0.056
 Sus+0.056
 Mill+0.056
 Alf+0.055
Neg logit contributions
wy-0.041
 ruined-0.040
istered-0.038
ggy-0.037
 burns-0.036
Token.
Token ID13
Feature activation+2.31e+00

Pos logit contributions
 Suz+0.062
 Su+0.061
 Mill+0.060
 Sus+0.060
 Alf+0.059
Neg logit contributions
 ruined-0.030
wy-0.029
ggy-0.029
ggie-0.028
 sharp-0.028
Token They
Token ID1119
Feature activation-6.60e-01

Pos logit contributions
 Suz+0.052
 Su+0.050
 Mill+0.050
 Sus+0.049
 Alf+0.048
Neg logit contributions
ggy-0.043
 ruined-0.043
ggie-0.042
 burns-0.041
 sharp-0.040
Token would
Token ID561
Feature activation-2.25e+00

Pos logit contributions
 ruined+0.012
wy+0.012
 sharp+0.011
ggy+0.011
 hurt+0.010
Neg logit contributions
 Suz-0.017
 Su-0.017
 Sus-0.016
 Mill-0.016
 Alf-0.016
Token play
Token ID711
Feature activation-9.40e-01

Pos logit contributions
 ruined+0.041
wy+0.040
ggy+0.039
 sharp+0.039
ggie+0.038
Neg logit contributions
 Suz-0.055
 Su-0.055
 Mill-0.054
 Sus-0.054
 Alf-0.053
Token games
Token ID1830
Feature activation+3.70e-01

Pos logit contributions
 ruined+0.022
ggy+0.022
wy+0.021
 sharp+0.021
ggie+0.021
Neg logit contributions
 Suz-0.018
 Su-0.018
 Mill-0.018
 Sus-0.018
 Alf-0.017
Token,
Token ID11
Feature activation+4.02e+00

Pos logit contributions
 Su+0.009
 Suz+0.009
 Mill+0.009
 Sus+0.008
 Alf+0.008
Neg logit contributions
 ruined-0.007
ggy-0.007
wy-0.007
 sharp-0.007
ggie-0.007
Token tell
Token ID1560
Feature activation+3.10e+00

Pos logit contributions
 Mill+0.103
 Suz+0.102
 Su+0.101
 Sus+0.100
 Alf+0.098
Neg logit contributions
 ruined-0.066
 sharp-0.065
 big-0.061
ggy-0.060
 hurt-0.059
Token vine
Token ID17793
Feature activation+2.65e+00

Pos logit contributions
 Suz+0.014
 Su+0.013
 Mill+0.013
 Sus+0.013
 Alf+0.013
Neg logit contributions
wy-0.023
 ruined-0.023
istered-0.022
ggy-0.022
ggie-0.021
Token too
Token ID1165
Feature activation-3.21e+00

Pos logit contributions
 Su+0.072
 Suz+0.071
 Mill+0.070
 Sus+0.070
 Alf+0.068
Neg logit contributions
 ruined-0.044
wy-0.041
ggy-0.040
 sharp-0.040
 hurt-0.039
Token,
Token ID11
Feature activation+3.75e+00

Pos logit contributions
wy+0.067
 ruined+0.064
istered+0.063
ggy+0.062
ggie+0.061
Neg logit contributions
 Suz-0.071
 Mill-0.071
 Su-0.070
 Sus-0.070
 Alf-0.067
Token but
Token ID475
Feature activation+4.78e+00

Pos logit contributions
 Mill+0.083
 Sus+0.079
 Suz+0.078
bank+0.078
 Alf+0.077
Neg logit contributions
 sharp-0.074
 ruined-0.071
 bad-0.070
 hurt-0.069
 big-0.069
Token I
Token ID314
Feature activation-3.07e+00

Pos logit contributions
 Su+0.119
 Suz+0.119
 Mill+0.117
 Sus+0.116
 Alf+0.114
Neg logit contributions
 ruined-0.086
 sharp-0.082
wy-0.079
ggy-0.079
 hurt-0.077
Token am
Token ID716
Feature activation-6.54e+00

Pos logit contributions
wy+0.067
ps+0.064
ggie+0.063
arest+0.062
ggy+0.061
Neg logit contributions
 Suz-0.066
 Sus-0.064
 Su-0.061
 Mill-0.061
 Alf-0.059
Token too
Token ID1165
Feature activation-7.46e+00

Pos logit contributions
wy+0.110
ggy+0.101
istered+0.099
ggie+0.099
uch+0.098
Neg logit contributions
 Suz-0.179
 Sus-0.176
 Mill-0.176
 Su-0.174
 Alf-0.169
Token small
Token ID1402
Feature activation-2.54e+00

Pos logit contributions
wy+0.119
ggie+0.108
ggy+0.103
ps+0.101
istered+0.100
Neg logit contributions
 Suz-0.211
 Su-0.210
 Mill-0.207
 Sus-0.206
 Jan-0.197
Token."
Token ID526
Feature activation+2.03e+00

Pos logit contributions
wy+0.052
 ruined+0.052
ggy+0.050
 sharp+0.048
istered+0.048
Neg logit contributions
 Suz-0.056
 Su-0.056
 Mill-0.055
 Sus-0.055
 Alf-0.054
Token Bob
Token ID5811
Feature activation-3.16e-01

Pos logit contributions
 cities+0.042
ress+0.038
reating+0.037
spe+0.037
line+0.037
Neg logit contributions
ggy-0.045
 hurt-0.040
ggie-0.040
 sharp-0.040
A-0.039
Tokeno
Token ID78
Feature activation-1.94e+00

Pos logit contributions
 ruined+0.009
wy+0.009
ggy+0.009
 sharp+0.009
ggie+0.009
Neg logit contributions
 Suz-0.004
 Su-0.004
 Mill-0.004
 Sus-0.004
 Alf-0.004
Token ways
Token ID2842
Feature activation+1.63e+00

Pos logit contributions
ggie+0.025
ggy+0.025
uch+0.024
istered+0.024
wy+0.023
Neg logit contributions
 Suz-0.024
 Sus-0.023
 Mill-0.023
 Alf-0.023
 Su-0.022
Token to
Token ID284
Feature activation+3.69e-01

Pos logit contributions
 Suz+0.030
 Su+0.030
 Mill+0.029
 Sus+0.029
 Alf+0.028
Neg logit contributions
wy-0.040
 ruined-0.039
ggy-0.038
istered-0.038
 sharp-0.038
Token enjoy
Token ID2883
Feature activation+2.39e-01

Pos logit contributions
 Suz+0.007
 Sus+0.007
 Mill+0.007
 Su+0.006
 Alf+0.006
Neg logit contributions
istered-0.008
wy-0.008
ggie-0.008
 ruined-0.008
ggy-0.008
Token broccoli
Token ID44653
Feature activation-4.98e-01

Pos logit contributions
 Suz+0.005
 Su+0.005
 Mill+0.005
 Sus+0.005
 Alf+0.005
Neg logit contributions
 ruined-0.005
wy-0.005
ggy-0.005
istered-0.005
ggie-0.005
Token."
Token ID526
Feature activation+6.41e-01

Pos logit contributions
 ruined+0.011
wy+0.011
ggy+0.010
istered+0.010
ggie+0.010
Neg logit contributions
 Mill-0.010
 Suz-0.010
 Sus-0.009
 Alf-0.009
 Su-0.009
Token
Token ID198
Feature activation-5.44e+00

Pos logit contributions
 Suz+0.017
 Su+0.017
 cities+0.017
 Alf+0.017
 Mill+0.017
Neg logit contributions
ggy-0.009
 hurt-0.008
 pain-0.008
 bad-0.008
 sting-0.008
Token
Token ID198
Feature activation-4.73e+00

Pos logit contributions
 ruined+0.111
wy+0.110
ggy+0.109
 sharp+0.106
ggie+0.105
Neg logit contributions
 Suz-0.121
 Su-0.120
 Mill-0.118
 Sus-0.118
 Alf-0.115
TokenL
Token ID43
Feature activation-1.38e+00

Pos logit contributions
 ruined+0.067
wy+0.066
ggy+0.063
 sharp+0.062
ggie+0.060
Neg logit contributions
 Suz-0.137
 Su-0.135
 Mill-0.134
 Sus-0.133
 Alf-0.131
Tokenily
Token ID813
Feature activation-1.86e+00

Pos logit contributions
 ruined+0.022
 sharp+0.021
wy+0.021
istered+0.021
 sting+0.020
Neg logit contributions
 Su-0.038
 Suz-0.038
 Sus-0.037
 Alf-0.036
 Mill-0.036
Token was
Token ID373
Feature activation-5.91e+00

Pos logit contributions
wy+0.041
istered+0.041
arest+0.041
ggy+0.039
 ruined+0.039
Neg logit contributions
 Suz-0.037
 Su-0.037
 Sus-0.036
 Mill-0.035
 Alf-0.034
Token still
Token ID991
Feature activation-3.81e+00

Pos logit contributions
wy+0.138
arest+0.129
uch+0.126
itch+0.124
istered+0.122
Neg logit contributions
 Su-0.124
 Suz-0.120
 Sus-0.117
 Mill-0.111
 K-0.107
Token rabbit
Token ID22746
Feature activation-8.48e-01

Pos logit contributions
 ruined+0.058
wy+0.058
ggy+0.052
 burns+0.051
istered+0.051
Neg logit contributions
 Suz-0.156
 Su-0.156
 Mill-0.153
 Sus-0.153
 Alf-0.151
Token named
Token ID3706
Feature activation+4.06e+00

Pos logit contributions
ggy+0.017
 ruined+0.016
 sharp+0.016
 hurt+0.016
ggie+0.016
Neg logit contributions
 Su-0.020
 Suz-0.020
 Sus-0.019
 Mill-0.019
 Alf-0.019
Token Peter
Token ID5613
Feature activation-9.67e-01

Pos logit contributions
ress+0.055
 cities+0.052
line+0.052
iked+0.052
 Su+0.051
Neg logit contributions
 sharp-0.114
ggy-0.110
wy-0.108
 ruined-0.107
 big-0.106
Token.
Token ID13
Feature activation+1.10e+00

Pos logit contributions
 ruined+0.016
wy+0.015
ggy+0.015
 sharp+0.014
istered+0.014
Neg logit contributions
 Suz-0.026
 Su-0.026
 Mill-0.025
 Sus-0.025
 Alf-0.025
Token He
Token ID679
Feature activation-1.53e+00

Pos logit contributions
 Su+0.019
ress+0.019
line+0.017
iked+0.017
 Suz+0.016
Neg logit contributions
 sharp-0.026
 big-0.025
 funny-0.024
 ruined-0.024
 burns-0.024
Token was
Token ID373
Feature activation-6.94e+00

Pos logit contributions
istered+0.036
wy+0.036
arest+0.035
 Deal+0.035
ps+0.034
Neg logit contributions
 Suz-0.028
 Mill-0.028
 Su-0.027
 Twe-0.027
 Alf-0.027
Token a
Token ID257
Feature activation-6.11e+00

Pos logit contributions
wy+0.094
 ruined+0.092
istered+0.085
ggy+0.083
uch+0.083
Neg logit contributions
 Suz-0.209
 Su-0.206
 Mill-0.205
 Sus-0.203
 Alf-0.202
Token spoiled
Token ID34781
Feature activation-9.86e-01

Pos logit contributions
wy+0.075
 ruined+0.074
ggy+0.067
ps+0.067
 burns+0.066
Neg logit contributions
 Suz-0.188
 Su-0.186
 Mill-0.185
 Sus-0.183
 Alf-0.181
Token rabbit
Token ID22746
Feature activation-8.37e-01

Pos logit contributions
 sharp+0.020
 ruined+0.019
ggy+0.018
 bad+0.018
wy+0.018
Neg logit contributions
 Suz-0.023
 Su-0.022
 Alf-0.022
 Mill-0.022
 Sus-0.022
Token,
Token ID11
Feature activation+2.81e+00

Pos logit contributions
 ruined+0.014
ggy+0.014
 sharp+0.013
ggie+0.013
wy+0.013
Neg logit contributions
 Suz-0.022
 Su-0.022
 Sus-0.022
 Mill-0.022
 Alf-0.021
Token living
Token ID2877
Feature activation-2.15e-01

Pos logit contributions
 Suz+0.063
 Su+0.063
 Mill+0.062
 Sus+0.061
 Alf+0.061
Neg logit contributions
 ruined-0.057
 sharp-0.055
ggy-0.055
 hurt-0.053
ggie-0.052
Token the
Token ID262
Feature activation+8.27e-01

Pos logit contributions
 Suz+0.023
 Su+0.023
 Sus+0.022
 Mill+0.022
 Alf+0.021
Neg logit contributions
wy-0.031
uch-0.030
ggy-0.030
 ruined-0.030
istered-0.029
Token garden
Token ID11376
Feature activation+2.79e+00

Pos logit contributions
 Suz+0.018
 Su+0.018
 Mill+0.018
 Sus+0.017
 Alf+0.017
Neg logit contributions
 ruined-0.017
wy-0.017
ggy-0.017
 sharp-0.016
ggie-0.016
Token.
Token ID13
Feature activation+1.41e+00

Pos logit contributions
 Suz+0.081
 Su+0.080
 Mill+0.080
 Sus+0.079
 Alf+0.078
Neg logit contributions
 ruined-0.041
wy-0.038
 sharp-0.037
ggy-0.037
 burns-0.036
Token They
Token ID1119
Feature activation-1.21e+00

Pos logit contributions
 Suz+0.028
 Mill+0.028
 Alf+0.027
 Su+0.027
ress+0.027
Neg logit contributions
 ruined-0.030
 burns-0.029
 pain-0.029
 sharp-0.028
 bad-0.028
Token are
Token ID389
Feature activation-5.43e+00

Pos logit contributions
wy+0.025
ggie+0.024
ggy+0.024
istered+0.024
uch+0.023
Neg logit contributions
 Suz-0.027
 Su-0.027
 Alf-0.027
 Sus-0.026
 Mill-0.026
Token not
Token ID407
Feature activation-5.03e+00

Pos logit contributions
wy+0.104
uch+0.100
arest+0.098
itch+0.093
ggie+0.091
Neg logit contributions
 Su-0.131
 Suz-0.131
 Sus-0.125
 Mill-0.124
 Alf-0.122
Token happy
Token ID3772
Feature activation-4.83e-01

Pos logit contributions
wy+0.093
 ruined+0.090
ggy+0.088
ggie+0.086
uch+0.086
Neg logit contributions
 Suz-0.124
 Su-0.124
 Sus-0.121
 Mill-0.121
 Alf-0.118
Token.
Token ID13
Feature activation+6.01e-01

Pos logit contributions
 ruined+0.008
wy+0.007
ggy+0.007
 sharp+0.007
 burns+0.007
Neg logit contributions
 Suz-0.013
 Su-0.013
 Mill-0.013
 Sus-0.013
 Alf-0.013
Token
Token ID198
Feature activation-5.90e+00

Pos logit contributions
 Suz+0.012
 Mill+0.012
 Su+0.012
 Sus+0.011
 Alf+0.011
Neg logit contributions
 ruined-0.014
 burns-0.013
ggy-0.013
 sharp-0.013
 pain-0.013
Token
Token ID198
Feature activation-4.76e+00

Pos logit contributions
wy+0.131
 ruined+0.131
ggy+0.123
 sharp+0.123
istered+0.122
Neg logit contributions
 Suz-0.123
 Su-0.122
 Mill-0.120
 Sus-0.119
 Alf-0.117
Token"
Token ID1
Feature activation-2.74e-01

Pos logit contributions
 ruined+0.077
wy+0.077
istered+0.071
 sharp+0.071
ggy+0.070
Neg logit contributions
 Suz-0.128
 Su-0.128
 Mill-0.124
 Sus-0.124
 Alf-0.122
Token kept
Token ID4030
Feature activation+5.53e-01

Pos logit contributions
wy+0.012
istered+0.012
 ruined+0.012
uch+0.011
 pain+0.011
Neg logit contributions
 Suz-0.013
 Su-0.013
 Sus-0.013
 Mill-0.012
 Alf-0.012
Token playing
Token ID2712
Feature activation-4.69e-01

Pos logit contributions
 Suz+0.013
 Mill+0.012
 Su+0.012
 Sus+0.012
 Alf+0.012
Neg logit contributions
 ruined-0.012
 sharp-0.011
 hurt-0.011
ggy-0.011
 pain-0.011
Token the
Token ID262
Feature activation+8.44e-01

Pos logit contributions
 ruined+0.008
ggy+0.008
 sharp+0.008
 pain+0.008
ggie+0.008
Neg logit contributions
 Suz-0.012
 Mill-0.012
 Su-0.012
 Sus-0.012
 Alf-0.012
Token drum
Token ID13026
Feature activation+1.78e+00

Pos logit contributions
 Suz+0.014
 Su+0.013
 Sus+0.013
 Mill+0.013
 Alf+0.013
Neg logit contributions
wy-0.022
istered-0.022
 ruined-0.021
ggy-0.021
ggie-0.020
Token.
Token ID13
Feature activation+1.84e+00

Pos logit contributions
 Su+0.047
 Suz+0.046
 Mill+0.046
 Sus+0.045
 Alf+0.043
Neg logit contributions
 ruined-0.031
 sharp-0.030
ggy-0.029
 hurt-0.029
wy-0.028
Token
Token ID198
Feature activation-4.78e+00

Pos logit contributions
ress+0.040
 cities+0.039
 Mill+0.039
 Ally+0.039
 Su+0.038
Neg logit contributions
 sharp-0.029
 two-0.029
ggy-0.028
 big-0.028
 burns-0.028
Token
Token ID198
Feature activation-3.91e+00

Pos logit contributions
 ruined+0.094
ggy+0.094
wy+0.093
 sharp+0.090
ggie+0.090
Neg logit contributions
 Suz-0.107
 Su-0.106
 Mill-0.106
 Sus-0.105
 Alf-0.103
TokenJoe
Token ID19585
Feature activation-1.73e-01

Pos logit contributions
 ruined+0.071
wy+0.070
ggy+0.069
 sharp+0.067
ggie+0.066
Neg logit contributions
 Suz-0.096
 Su-0.095
 Mill-0.095
 Sus-0.094
 Alf-0.092
Token kept
Token ID4030
Feature activation+6.66e-01

Pos logit contributions
 ruined+0.003
wy+0.003
ggy+0.003
 sharp+0.003
istered+0.003
Neg logit contributions
 Suz-0.004
 Su-0.004
 Mill-0.004
 Sus-0.004
 Alf-0.004
Token playing
Token ID2712
Feature activation-1.76e-01

Pos logit contributions
 Suz+0.016
 Mill+0.016
 Su+0.015
 Sus+0.015
 Alf+0.015
Neg logit contributions
 ruined-0.013
 sharp-0.013
 hurt-0.013
 pain-0.012
 broken-0.012
Token his
Token ID465
Feature activation+1.34e+00

Pos logit contributions
 sharp+0.003
 ruined+0.003
ggy+0.003
 pain+0.003
 bad+0.003
Neg logit contributions
 Suz-0.005
 Mill-0.005
 Su-0.005
 Sus-0.004
 Alf-0.004