TOP ACTIVATIONS
MAX = 0.088

the stars that kept her son safe as he n apped
and the mum gave her daughter lots of hugs .
was important and made her mother happy . She showed her
very relieved and hugged her daughter tightly . The
she wanted to make her daughter happy .
she smiled and gave her daughter a big hug .
The mom my hugged her daughter and looked around to find
, the man showed the woman a pistol . He said
jug . She hugged her daughter and said : " It
dad wanted to make his daughter laugh . The
The mom hugged her daughter and said , " You
sad . She hugged her daughter and hoped that she had
been bad and made their mom angry . They quickly apologized
!" and quickly made her daughter her favourite dish - a
longer and she made her mom proud by being calm and
so happy and gave her son a big hug .
woman . She asked the woman if she wanted help and
wanted to make her little girl happy again . Mom decided
very curious and asked the woman , " What is that
she decided to give her daughter a teaspoon . The little

MIN ACTIVATIONS
MIN = -0.105

ball that was just as boun cy as the red one
sign ' happy ', ' birth day ', and ' you
. The basketball was not boun cy anymore . It was
found . It 's really boun cy !" L
. It was shiny and boun cy and fun . But
It is very pretty and boun cy ." The girl said
cave . You are not en vious . You are adventurous
is big and round and boun cy . Can I hold
is shiny and round and boun cy . I like it
It was still round and boun cy and colorful . They
round , and ever so boun cy . Every day ,
. It is big and boun cy . They grab it
is fun . It is boun cy and w obb ly
is red and shiny and boun cy . "
is red and shiny and boun cy . They want to
. It was big and boun cy and shiny .
doll . They were not en vious anymore . They were
ball was purple and very boun cy . One day ,
't have dinner until you bat he ." So
understand . They are not en vious anymore . They hug

INTERVAL 0.039 - 0.088
CONTAINS 2.243%

. The girl was very happy . She shouted
was warm and the water was cool , making it the
S ara said , " This is a book
Tom and Lily asked their mom if they could go outside
thought about it and said , " You 're right ,

INTERVAL -0.009 - 0.039
CONTAINS 63.277%

I want to own it ." " No ,
to take something that doesn 't belong to you . <|endoftext|>
just the way she wanted it . The little
Lily . Sometimes , a little gift can make someone feel
give my re ind eer some carrots and water . They

INTERVAL -0.057 - -0.009
CONTAINS 33.867%

, two friends named John and Sarah were playing in the
Tom look at Ben . They are still sad . They
Her mom asked her why she was scared . Lily said
the lady said she would take care of it . She
surprise , it was raining ! Rose grabbed her

INTERVAL -0.105 - -0.057
CONTAINS 0.612%

be mindful of others . <|endoftext|> Once upon a time ,
feel comfortable and happy . <|endoftext|> Once upon a time ,
enjoy her shiny home . <|endoftext|> Once upon a time ,
hand or a cane when you can . <|endoftext|> Once upon
have some ice cream ." <|endoftext|> Tom was a boy who
Token the
Token ID262
Feature activation+2.30e-02

Pos logit contributions
ache+0.048
 badly+0.044
 spe+0.042
 severe+0.042
 gen+0.041
Neg logit contributions
 recess-0.030
ips-0.030
olls-0.030
ashes-0.030
les-0.030
Token stars
Token ID5788
Feature activation+1.54e-02

Pos logit contributions
ache+0.041
 badly+0.038
 spe+0.036
 severe+0.035
 gen+0.035
Neg logit contributions
ashes-0.038
olls-0.037
ips-0.037
 recess-0.036
les-0.036
Token that
Token ID326
Feature activation-1.93e-02

Pos logit contributions
ache+0.032
 badly+0.030
 severe+0.028
Mill+0.028
 spe+0.028
Neg logit contributions
ashes-0.021
ips-0.021
les-0.021
olls-0.020
 recess-0.019
Token kept
Token ID4030
Feature activation+1.19e-02

Pos logit contributions
ashes+0.031
ips+0.030
olls+0.030
 recess+0.028
olphins+0.028
Neg logit contributions
ache-0.036
 badly-0.034
 spe-0.033
 gen-0.032
 severe-0.032
Token her
Token ID607
Feature activation+2.40e-02

Pos logit contributions
ache+0.023
 badly+0.021
 spe+0.019
 severe+0.019
 gen+0.019
Neg logit contributions
ashes-0.019
ips-0.018
olls-0.018
 recess-0.018
les-0.017
Token son
Token ID3367
Feature activation+8.19e-02

Pos logit contributions
ache+0.046
Mill+0.041
Am+0.040
Jean+0.040
Sad+0.039
Neg logit contributions
 day-0.036
 morning-0.036
ashes-0.036
 afternoon-0.033
les-0.033
Token safe
Token ID3338
Feature activation-8.55e-03

Pos logit contributions
ache+0.144
 badly+0.128
 spe+0.126
 gen+0.124
Mill+0.123
Neg logit contributions
ashes-0.136
ips-0.128
les-0.127
olls-0.127
 scores-0.125
Token as
Token ID355
Feature activation+2.41e-02

Pos logit contributions
ashes+0.012
ips+0.011
olls+0.011
les+0.011
 recess+0.011
Neg logit contributions
ache-0.017
 badly-0.016
 gen-0.015
 spe-0.015
 severe-0.015
Token he
Token ID339
Feature activation-3.97e-02

Pos logit contributions
ache+0.050
 badly+0.045
 gen+0.043
 severe+0.043
Sad+0.043
Neg logit contributions
ashes-0.031
 recess-0.031
ips-0.030
les-0.030
olls-0.030
Token n
Token ID299
Feature activation-2.93e-02

Pos logit contributions
ashes+0.062
olls+0.061
ips+0.061
 recess+0.058
les+0.057
Neg logit contributions
ache-0.076
 badly-0.071
 spe-0.066
 severe-0.065
 gen-0.065
Tokenapped
Token ID6320
Feature activation+2.40e-03

Pos logit contributions
ips+0.040
ashes+0.038
acked+0.035
olls+0.035
oom+0.035
Neg logit contributions
ache-0.065
 spe-0.058
 severe-0.057
 gen-0.056
 mercy-0.056
Token and
Token ID290
Feature activation+1.35e-02

Pos logit contributions
ashes+0.007
ips+0.007
olls+0.007
 recess+0.007
les+0.007
Neg logit contributions
ache-0.012
 badly-0.010
 gen-0.010
 severe-0.010
Sad-0.010
Token the
Token ID262
Feature activation+2.99e-02

Pos logit contributions
ache+0.027
 badly+0.024
Am+0.023
 gen+0.023
Mill+0.022
Neg logit contributions
 day-0.020
ashes-0.019
 morning-0.019
 recess-0.018
 afternoon-0.018
Token mum
Token ID25682
Feature activation+3.54e-02

Pos logit contributions
ache+0.044
 badly+0.040
 severe+0.037
 spe+0.036
 gen+0.036
Neg logit contributions
ashes-0.061
ips-0.061
olls-0.060
les-0.057
 scores-0.057
Token gave
Token ID2921
Feature activation-1.23e-02

Pos logit contributions
ache+0.070
 badly+0.067
 severe+0.063
Mill+0.063
 mercy+0.062
Neg logit contributions
les-0.049
ashes-0.048
ips-0.048
ops-0.047
olls-0.045
Token her
Token ID607
Feature activation+3.89e-02

Pos logit contributions
ashes+0.022
ips+0.022
olls+0.022
les+0.021
 recess+0.021
Neg logit contributions
ache-0.021
 badly-0.019
 spe-0.017
 gen-0.017
 severe-0.017
Token daughter
Token ID4957
Feature activation+8.10e-02

Pos logit contributions
ache+0.067
 badly+0.059
 spe+0.058
 gen+0.057
Mill+0.055
Neg logit contributions
ashes-0.067
olls-0.065
ips-0.065
les-0.064
 recess-0.064
Token lots
Token ID6041
Feature activation+7.98e-03

Pos logit contributions
ache+0.140
 badly+0.122
 spe+0.121
 gen+0.120
Mill+0.115
Neg logit contributions
ashes-0.141
ips-0.136
olls-0.135
 recess-0.132
 scores-0.131
Token of
Token ID286
Feature activation+8.42e-03

Pos logit contributions
ache+0.017
 badly+0.016
 spe+0.015
 gen+0.015
Mill+0.015
Neg logit contributions
les-0.010
ashes-0.010
olls-0.010
ips-0.009
 recess-0.009
Token hugs
Token ID40657
Feature activation-1.89e-02

Pos logit contributions
ache+0.017
 badly+0.016
 spe+0.015
 severe+0.015
 gen+0.014
Neg logit contributions
ashes-0.013
ips-0.012
olls-0.012
 recess-0.012
les-0.012
Token.
Token ID13
Feature activation-1.06e-02

Pos logit contributions
ashes+0.027
olls+0.026
ips+0.026
les+0.026
 recess+0.025
Neg logit contributions
ache-0.038
 badly-0.035
 spe-0.034
 gen-0.034
 severe-0.033
Token
Token ID198
Feature activation+1.94e-02

Pos logit contributions
ashes+0.015
olls+0.014
ips+0.014
 recess+0.014
les+0.014
Neg logit contributions
ache-0.022
 badly-0.021
 spe-0.020
 severe-0.020
Mill-0.019
Token was
Token ID373
Feature activation+4.60e-02

Pos logit contributions
ashes+0.022
ips+0.022
olls+0.022
 recess+0.021
olphins+0.020
Neg logit contributions
ache-0.024
 badly-0.023
 severe-0.020
 spe-0.020
 gen-0.020
Token important
Token ID1593
Feature activation-1.66e-02

Pos logit contributions
ache+0.074
 spe+0.065
 gen+0.064
 badly+0.063
Am+0.061
Neg logit contributions
ips-0.080
ashes-0.079
 day-0.079
olls-0.078
 recess-0.078
Token and
Token ID290
Feature activation+1.04e-02

Pos logit contributions
ashes+0.023
olls+0.023
ips+0.022
 recess+0.021
les+0.021
Neg logit contributions
ache-0.034
 badly-0.031
 spe-0.031
 gen-0.031
 severe-0.031
Token made
Token ID925
Feature activation+1.51e-02

Pos logit contributions
ache+0.018
 badly+0.016
 spe+0.015
Am+0.015
 gen+0.015
Neg logit contributions
ashes-0.018
olls-0.018
ips-0.018
 recess-0.017
 scores-0.017
Token her
Token ID607
Feature activation+3.11e-02

Pos logit contributions
ache+0.023
 spe+0.020
 badly+0.019
 gen+0.018
comb+0.018
Neg logit contributions
ashes-0.030
les-0.030
ips-0.029
olls-0.029
 recess-0.028
Token mother
Token ID2802
Feature activation+8.06e-02

Pos logit contributions
ache+0.064
 spe+0.058
Am+0.057
Mill+0.057
 gen+0.056
Neg logit contributions
 day-0.045
ashes-0.043
 morning-0.042
 scores-0.040
 afternoon-0.039
Token happy
Token ID3772
Feature activation-1.35e-02

Pos logit contributions
ache+0.146
Am+0.131
Mill+0.131
 spe+0.130
 badly+0.127
Neg logit contributions
ashes-0.127
 day-0.120
les-0.119
 scores-0.119
ips-0.116
Token.
Token ID13
Feature activation-3.72e-03

Pos logit contributions
ashes+0.020
ips+0.020
olls+0.020
les+0.019
 recess+0.019
Neg logit contributions
ache-0.027
 badly-0.024
 spe-0.024
 severe-0.023
Mill-0.023
Token She
Token ID1375
Feature activation+4.17e-04

Pos logit contributions
ashes+0.005
olls+0.005
ips+0.005
 recess+0.005
les+0.005
Neg logit contributions
ache-0.008
 badly-0.007
 spe-0.007
 severe-0.007
 gen-0.007
Token showed
Token ID3751
Feature activation-2.82e-03

Pos logit contributions
ache+0.001
 badly+0.001
 spe+0.001
 mercy+0.001
 severe+0.001
Neg logit contributions
les-0.001
ashes-0.001
ips-0.001
ops-0.001
 scores-0.001
Token her
Token ID607
Feature activation+3.51e-02

Pos logit contributions
ashes+0.005
les+0.005
olls+0.005
ips+0.005
 recess+0.005
Neg logit contributions
ache-0.005
 badly-0.005
 spe-0.005
 severe-0.004
 gen-0.004
Token very
Token ID845
Feature activation+4.11e-02

Pos logit contributions
ache+0.086
bul+0.070
 spe+0.070
comb+0.069
 mercy+0.068
Neg logit contributions
ips-0.083
 day-0.076
acking-0.076
 morning-0.076
ashes-0.075
Token relieved
Token ID22598
Feature activation-3.76e-03

Pos logit contributions
ache+0.069
 gen+0.058
bul+0.058
 spe+0.058
comb+0.057
Neg logit contributions
ashes-0.074
ips-0.068
acking-0.066
 scores-0.065
asher-0.065
Token and
Token ID290
Feature activation+1.37e-02

Pos logit contributions
ashes+0.005
ips+0.005
olls+0.005
les+0.005
olphins+0.005
Neg logit contributions
ache-0.008
 badly-0.007
 spe-0.007
 severe-0.007
 gen-0.007
Token hugged
Token ID41130
Feature activation-2.10e-03

Pos logit contributions
ache+0.027
 badly+0.024
Sad+0.023
 gen+0.022
Am+0.022
Neg logit contributions
ashes-0.019
 day-0.019
 morning-0.018
les-0.018
ips-0.018
Token her
Token ID607
Feature activation+3.69e-02

Pos logit contributions
ashes+0.003
olls+0.003
ips+0.003
les+0.003
 recess+0.003
Neg logit contributions
ache-0.004
 badly-0.004
 gen-0.003
 spe-0.003
 severe-0.003
Token daughter
Token ID4957
Feature activation+8.00e-02

Pos logit contributions
ache+0.067
 badly+0.059
 spe+0.057
 gen+0.057
Mill+0.057
Neg logit contributions
ashes-0.061
olls-0.060
les-0.058
ips-0.058
olphins-0.057
Token tightly
Token ID17707
Feature activation-8.38e-04

Pos logit contributions
ache+0.153
 spe+0.135
 gen+0.134
 badly+0.133
Mill+0.132
Neg logit contributions
ashes-0.125
olls-0.119
ips-0.118
les-0.115
 scores-0.115
Token.
Token ID13
Feature activation-4.59e-03

Pos logit contributions
ashes+0.001
ips+0.001
olls+0.001
les+0.001
 scores+0.001
Neg logit contributions
ache-0.002
 gen-0.002
Mill-0.002
 spe-0.002
 badly-0.002
Token
Token ID198
Feature activation+2.24e-02

Pos logit contributions
ashes+0.007
olls+0.007
ips+0.007
 recess+0.007
les+0.006
Neg logit contributions
ache-0.009
 badly-0.008
 spe-0.008
Mill-0.008
 severe-0.008
Token
Token ID198
Feature activation+3.07e-02

Pos logit contributions
ache+0.052
 badly+0.047
 spe+0.047
 gen+0.045
 mercy+0.044
Neg logit contributions
ashes-0.027
ips-0.026
olls-0.026
 recess-0.024
les-0.024
TokenThe
Token ID464
Feature activation+3.14e-02

Pos logit contributions
ache+0.048
 badly+0.043
 spe+0.041
 gen+0.040
 mercy+0.039
Neg logit contributions
ashes-0.059
ips-0.058
olls-0.057
 recess-0.055
olphins-0.054
Token she
Token ID673
Feature activation+3.37e-03

Pos logit contributions
ache+0.069
 gen+0.060
 badly+0.059
 mercy+0.058
 severe+0.058
Neg logit contributions
ashes-0.072
ips-0.068
les-0.068
olls-0.068
 morning-0.067
Token wanted
Token ID2227
Feature activation-5.21e-03

Pos logit contributions
ache+0.007
 badly+0.006
 spe+0.006
 gen+0.006
 severe+0.006
Neg logit contributions
ashes-0.005
olls-0.005
les-0.005
ips-0.005
 scores-0.005
Token to
Token ID284
Feature activation+2.66e-02

Pos logit contributions
 recess+0.007
ashes+0.006
 morning+0.006
 day+0.006
ips+0.006
Neg logit contributions
ache-0.011
 badly-0.010
 spe-0.010
 gen-0.009
Mill-0.009
Token make
Token ID787
Feature activation+2.54e-03

Pos logit contributions
ache+0.061
 badly+0.056
 spe+0.056
 severe+0.054
Mill+0.054
Neg logit contributions
ashes-0.030
 recess-0.028
 scores-0.028
olls-0.028
 Win-0.027
Token her
Token ID607
Feature activation+3.43e-02

Pos logit contributions
ache+0.005
 badly+0.004
 spe+0.004
 gen+0.004
 severe+0.004
Neg logit contributions
ashes-0.004
ips-0.004
les-0.004
 recess-0.004
 scores-0.004
Token daughter
Token ID4957
Feature activation+7.97e-02

Pos logit contributions
ache+0.068
Mill+0.063
 spe+0.061
Am+0.060
Sad+0.060
Neg logit contributions
ashes-0.053
 day-0.049
 morning-0.047
 scores-0.047
 recess-0.046
Token happy
Token ID3772
Feature activation-1.80e-02

Pos logit contributions
ache+0.156
 spe+0.143
Mill+0.142
Am+0.140
 gen+0.138
Neg logit contributions
ashes-0.120
 scores-0.109
ips-0.107
les-0.104
olls-0.103
Token.
Token ID13
Feature activation-3.92e-03

Pos logit contributions
ashes+0.026
ips+0.025
olls+0.025
 recess+0.024
les+0.024
Neg logit contributions
ache-0.036
 badly-0.033
 spe-0.032
 severe-0.032
Mill-0.032
Token
Token ID220
Feature activation-3.33e-02

Pos logit contributions
ashes+0.005
ips+0.005
olls+0.004
olphins+0.004
les+0.004
Neg logit contributions
ache-0.009
 badly-0.008
 gen-0.008
 spe-0.008
 severe-0.008
Token
Token ID198
Feature activation+2.03e-02

Pos logit contributions
ips+0.039
ashes+0.039
olls+0.038
olphins+0.034
les+0.034
Neg logit contributions
ache-0.077
 badly-0.071
 spe-0.071
 gen-0.069
 severe-0.068
Token
Token ID198
Feature activation+3.11e-02

Pos logit contributions
ache+0.050
 badly+0.046
 spe+0.046
 gen+0.044
 mercy+0.044
Neg logit contributions
ips-0.020
ashes-0.020
olls-0.019
olphins-0.019
les-0.018
Token she
Token ID673
Feature activation-2.51e-02

Pos logit contributions
ache+0.050
 badly+0.043
 gen+0.043
 spe+0.042
 severe+0.042
Neg logit contributions
olls-0.038
ips-0.037
 recess-0.037
ashes-0.037
les-0.036
Token smiled
Token ID13541
Feature activation-1.36e-02

Pos logit contributions
les+0.036
ashes+0.035
ips+0.034
olls+0.034
ops+0.034
Neg logit contributions
ache-0.049
 badly-0.048
 gen-0.044
 spe-0.044
 mercy-0.043
Token and
Token ID290
Feature activation+1.36e-03

Pos logit contributions
les+0.012
ashes+0.012
ips+0.011
 morning+0.011
 day+0.011
Neg logit contributions
ache-0.033
Jean-0.031
 spe-0.031
 gen-0.030
Mill-0.030
Token gave
Token ID2921
Feature activation-4.15e-03

Pos logit contributions
ache+0.003
 badly+0.003
 gen+0.003
 spe+0.003
 severe+0.003
Neg logit contributions
ashes-0.002
ips-0.002
les-0.002
olls-0.002
 recess-0.001
Token her
Token ID607
Feature activation+3.28e-02

Pos logit contributions
ips+0.007
olls+0.007
les+0.007
ashes+0.007
 recess+0.007
Neg logit contributions
ache-0.008
 badly-0.007
 severe-0.007
 spe-0.006
 gen-0.006
Token daughter
Token ID4957
Feature activation+7.91e-02

Pos logit contributions
ache+0.058
 badly+0.053
 spe+0.051
 gen+0.049
Mill+0.049
Neg logit contributions
ashes-0.055
ips-0.054
olls-0.054
 recess-0.053
les-0.052
Token a
Token ID257
Feature activation+2.52e-02

Pos logit contributions
ache+0.135
 badly+0.121
 spe+0.119
 gen+0.114
Mill+0.112
Neg logit contributions
ashes-0.139
ips-0.134
olls-0.133
 recess-0.131
les-0.130
Token big
Token ID1263
Feature activation+1.10e-02

Pos logit contributions
ache+0.048
 badly+0.047
 spe+0.043
Mill+0.043
Am+0.042
Neg logit contributions
ashes-0.036
olls-0.034
les-0.034
 recess-0.033
 morning-0.033
Token hug
Token ID16225
Feature activation-2.51e-03

Pos logit contributions
ache+0.021
 badly+0.020
 spe+0.019
 gen+0.019
 severe+0.019
Neg logit contributions
ashes-0.017
ips-0.016
olls-0.016
 recess-0.016
olphins-0.016
Token.
Token ID13
Feature activation-2.83e-03

Pos logit contributions
ashes+0.003
olls+0.003
ips+0.003
les+0.003
 recess+0.003
Neg logit contributions
ache-0.005
 badly-0.005
 spe-0.005
Mill-0.005
 severe-0.005
Token
Token ID220
Feature activation-2.88e-02

Pos logit contributions
ashes+0.004
ips+0.003
olls+0.003
 recess+0.003
olphins+0.003
Neg logit contributions
ache-0.006
 badly-0.006
 spe-0.006
 severe-0.006
 gen-0.006
Token The
Token ID383
Feature activation+2.76e-02

Pos logit contributions
ache+0.020
 badly+0.018
 spe+0.017
 severe+0.017
 gen+0.017
Neg logit contributions
ashes-0.012
olls-0.012
ips-0.012
les-0.011
 recess-0.011
Token mom
Token ID1995
Feature activation+5.05e-02

Pos logit contributions
ache+0.047
 badly+0.044
 spe+0.043
Mill+0.040
 gen+0.040
Neg logit contributions
ashes-0.048
olls-0.047
 recess-0.046
les-0.045
ips-0.045
Tokenmy
Token ID1820
Feature activation+2.34e-02

Pos logit contributions
ache+0.141
 spe+0.141
 badly+0.139
 mercy+0.134
 gen+0.133
Neg logit contributions
les-0.031
olls-0.023
ips-0.023
acking-0.023
acked-0.022
Token hugged
Token ID41130
Feature activation-4.02e-03

Pos logit contributions
 reality+0.051
 badly+0.051
ache+0.050
 spe+0.050
 mercy+0.049
Neg logit contributions
les-0.027
acking-0.021
acked-0.021
ashed-0.020
ops-0.020
Token her
Token ID607
Feature activation+3.30e-02

Pos logit contributions
olls+0.007
les+0.007
ips+0.007
ashes+0.007
 recess+0.006
Neg logit contributions
ache-0.007
 badly-0.006
 spe-0.006
 gen-0.006
 severe-0.006
Token daughter
Token ID4957
Feature activation+7.84e-02

Pos logit contributions
ache+0.074
 spe+0.071
Mill+0.070
 gen+0.068
Jess+0.068
Neg logit contributions
olls-0.037
ashes-0.037
les-0.037
 day-0.033
ips-0.033
Token and
Token ID290
Feature activation-4.72e-03

Pos logit contributions
ache+0.177
 spe+0.167
 gen+0.164
Mill+0.161
Am+0.153
Neg logit contributions
ashes-0.091
les-0.085
olls-0.084
ips-0.081
 scores-0.080
Token looked
Token ID3114
Feature activation+1.09e-02

Pos logit contributions
les+0.003
ashed+0.003
 Ben+0.003
olls+0.003
 morning+0.003
Neg logit contributions
ache-0.012
 badly-0.012
 spe-0.011
vern-0.011
 prope-0.011
Token around
Token ID1088
Feature activation+5.21e-03

Pos logit contributions
ache+0.025
 badly+0.022
 spe+0.022
 gen+0.022
Am+0.022
Neg logit contributions
ashes-0.013
olls-0.013
les-0.013
ips-0.012
 scores-0.012
Token to
Token ID284
Feature activation+3.68e-02

Pos logit contributions
ache+0.011
 badly+0.010
 severe+0.010
 gen+0.010
 spe+0.009
Neg logit contributions
ashes-0.007
ips-0.007
olls-0.007
 recess-0.007
les-0.007
Token find
Token ID1064
Feature activation+2.16e-02

Pos logit contributions
ache+0.103
 badly+0.091
 spe+0.087
comb+0.086
 gen+0.086
Neg logit contributions
 recess-0.034
ashes-0.031
 Win-0.029
 morning-0.028
 play-0.027
Token,
Token ID11
Feature activation+2.18e-02

Pos logit contributions
ashes+0.024
olls+0.024
ips+0.023
 recess+0.023
les+0.023
Neg logit contributions
ache-0.032
 badly-0.030
 severe-0.028
 spe-0.028
 gen-0.028
Token the
Token ID262
Feature activation+3.19e-02

Pos logit contributions
ache+0.045
 badly+0.042
 spe+0.039
 severe+0.039
 gen+0.039
Neg logit contributions
ashes-0.031
olls-0.030
ips-0.030
 recess-0.029
les-0.029
Token man
Token ID582
Feature activation+3.47e-02

Pos logit contributions
ache+0.063
 badly+0.055
 spe+0.054
 gen+0.054
 severe+0.052
Neg logit contributions
ips-0.052
ashes-0.051
olls-0.050
acks-0.048
 recess-0.046
Token showed
Token ID3751
Feature activation-5.22e-03

Pos logit contributions
ache+0.070
 badly+0.067
 spe+0.063
 severe+0.063
 gen+0.062
Neg logit contributions
ashes-0.047
les-0.046
ips-0.046
olls-0.045
 scores-0.044
Token the
Token ID262
Feature activation+2.70e-02

Pos logit contributions
les+0.007
ashes+0.006
olls+0.006
ips+0.006
olphins+0.006
Neg logit contributions
ache-0.012
 badly-0.011
 spe-0.010
 severe-0.010
 gen-0.010
Token woman
Token ID2415
Feature activation+7.84e-02

Pos logit contributions
ache+0.055
 badly+0.051
 gen+0.048
 spe+0.048
 severe+0.048
Neg logit contributions
ips-0.040
ashes-0.040
olls-0.039
 recess-0.037
les-0.036
Token a
Token ID257
Feature activation+2.76e-02

Pos logit contributions
ache+0.150
 spe+0.136
 gen+0.128
 badly+0.128
Sad+0.126
Neg logit contributions
les-0.117
ashes-0.113
 scores-0.113
ips-0.111
olls-0.111
Token pistol
Token ID16790
Feature activation+9.46e-03

Pos logit contributions
ache+0.049
 badly+0.045
 spe+0.042
Sad+0.042
Mill+0.042
Neg logit contributions
ashes-0.043
olls-0.042
 scores-0.042
olphins-0.040
les-0.040
Token.
Token ID13
Feature activation-5.79e-03

Pos logit contributions
ache+0.017
 badly+0.016
 spe+0.015
 gen+0.015
 severe+0.015
Neg logit contributions
ashes-0.016
ips-0.015
olls-0.015
 recess-0.015
les-0.015
Token He
Token ID679
Feature activation-4.92e-03

Pos logit contributions
ashes+0.009
ips+0.009
olls+0.008
 recess+0.008
les+0.008
Neg logit contributions
ache-0.011
 badly-0.011
 spe-0.010
 gen-0.010
Mill-0.010
Token said
Token ID531
Feature activation+2.98e-02

Pos logit contributions
les+0.006
ashes+0.006
olls+0.006
 scores+0.006
ips+0.006
Neg logit contributions
ache-0.010
 badly-0.010
 severe-0.009
 spe-0.009
Mill-0.009
Token jug
Token ID45808
Feature activation-7.38e-03

Pos logit contributions
ashes+0.014
olls+0.013
ips+0.013
 recess+0.013
les+0.013
Neg logit contributions
ache-0.018
 badly-0.017
 spe-0.016
 severe-0.016
 gen-0.015
Token.
Token ID13
Feature activation-1.62e-02

Pos logit contributions
ashes+0.012
olls+0.012
ips+0.012
 recess+0.012
olphins+0.012
Neg logit contributions
ache-0.013
 badly-0.013
 severe-0.011
 spe-0.011
 able-0.011
Token She
Token ID1375
Feature activation-5.41e-03

Pos logit contributions
ashes+0.025
ips+0.025
les+0.024
olls+0.024
 recess+0.024
Neg logit contributions
ache-0.030
 badly-0.029
Mill-0.027
Am-0.027
 spe-0.027
Token hugged
Token ID41130
Feature activation+1.16e-03

Pos logit contributions
ashes+0.008
olls+0.008
ips+0.007
les+0.007
 scores+0.007
Neg logit contributions
ache-0.011
 badly-0.010
 spe-0.010
 severe-0.010
Mill-0.009
Token her
Token ID607
Feature activation+2.67e-02

Pos logit contributions
ache+0.002
 badly+0.002
 spe+0.002
 severe+0.002
 gen+0.002
Neg logit contributions
ashes-0.002
olls-0.002
ips-0.002
 recess-0.002
les-0.002
Token daughter
Token ID4957
Feature activation+7.81e-02

Pos logit contributions
ache+0.049
 badly+0.044
Mill+0.043
 spe+0.043
 severe+0.042
Neg logit contributions
ashes-0.042
les-0.042
olls-0.042
ips-0.040
olphins-0.040
Token and
Token ID290
Feature activation-5.79e-03

Pos logit contributions
ache+0.165
 badly+0.150
 spe+0.149
Mill+0.146
 gen+0.146
Neg logit contributions
ashes-0.106
olls-0.101
les-0.099
ips-0.099
 scores-0.096
Token said
Token ID531
Feature activation+3.84e-02

Pos logit contributions
les+0.005
 recess+0.004
ashed+0.004
 day+0.004
 morning+0.004
Neg logit contributions
ache-0.014
Am-0.013
 badly-0.013
 spe-0.013
Sad-0.013
Token:
Token ID25
Feature activation+5.18e-02

Pos logit contributions
ache+0.088
 severe+0.082
Am+0.081
Sad+0.080
Mill+0.080
Neg logit contributions
olls-0.041
ips-0.039
ashes-0.037
oom-0.036
ops-0.036
Token "
Token ID366
Feature activation+1.25e-02

Pos logit contributions
ache+0.095
 badly+0.088
 spe+0.082
 severe+0.081
 gen+0.081
Neg logit contributions
ashes-0.085
olls-0.083
ips-0.083
 recess-0.079
les-0.079
TokenIt
Token ID1026
Feature activation-2.51e-02

Pos logit contributions
ache+0.025
 badly+0.023
Mill+0.022
 spe+0.022
 severe+0.022
Neg logit contributions
ashes-0.019
olls-0.018
ips-0.018
 recess-0.018
les-0.017
Token dad
Token ID9955
Feature activation+3.05e-02

Pos logit contributions
ache+0.031
 badly+0.028
 severe+0.026
 gen+0.025
Am+0.024
Neg logit contributions
ashes-0.051
ips-0.051
olls-0.049
 scores-0.047
acks-0.047
Token wanted
Token ID2227
Feature activation-4.95e-03

Pos logit contributions
ache+0.059
 badly+0.056
 severe+0.052
 spe+0.052
Mill+0.051
Neg logit contributions
ashes-0.046
ips-0.045
olls-0.044
les-0.044
 recess-0.043
Token to
Token ID284
Feature activation+2.40e-02

Pos logit contributions
 recess+0.007
ashes+0.007
ips+0.007
olls+0.007
 scores+0.007
Neg logit contributions
ache-0.010
 badly-0.009
 spe-0.009
 severe-0.009
 gen-0.009
Token make
Token ID787
Feature activation+5.45e-03

Pos logit contributions
ache+0.057
 badly+0.051
 severe+0.050
 spe+0.050
Am+0.049
Neg logit contributions
ashes-0.027
 recess-0.026
 scores-0.025
 Win-0.024
olls-0.024
Token his
Token ID465
Feature activation+2.11e-02

Pos logit contributions
ache+0.010
 badly+0.009
 spe+0.009
 severe+0.008
 gen+0.008
Neg logit contributions
ashes-0.009
les-0.009
ips-0.009
olls-0.009
 recess-0.009
Token daughter
Token ID4957
Feature activation+7.79e-02

Pos logit contributions
ache+0.034
 badly+0.031
 spe+0.028
 severe+0.028
Mill+0.028
Neg logit contributions
ashes-0.040
olls-0.039
ips-0.039
 recess-0.038
les-0.037
Token laugh
Token ID6487
Feature activation-1.74e-02

Pos logit contributions
ache+0.149
 badly+0.133
 spe+0.132
Mill+0.130
Am+0.128
Neg logit contributions
ashes-0.122
ips-0.114
 scores-0.113
olls-0.112
 recess-0.111
Token.
Token ID13
Feature activation-9.49e-03

Pos logit contributions
ashes+0.025
olls+0.025
ips+0.024
les+0.024
 recess+0.023
Neg logit contributions
ache-0.035
 badly-0.032
 spe-0.031
 severe-0.031
Mill-0.031
Token
Token ID198
Feature activation+1.09e-02

Pos logit contributions
ashes+0.016
ips+0.015
olls+0.015
les+0.015
 recess+0.015
Neg logit contributions
ache-0.015
 badly-0.015
Am-0.014
Sad-0.014
Mill-0.014
Token
Token ID198
Feature activation+2.62e-02

Pos logit contributions
ache+0.024
 badly+0.022
 spe+0.021
 severe+0.021
 gen+0.021
Neg logit contributions
ashes-0.014
ips-0.014
olls-0.014
 recess-0.013
les-0.013
TokenThe
Token ID464
Feature activation+3.08e-02

Pos logit contributions
ache+0.040
 badly+0.037
 severe+0.034
 spe+0.033
Mill+0.033
Neg logit contributions
ashes-0.052
ips-0.051
olls-0.050
 recess-0.049
les-0.049
Token
Token ID198
Feature activation+3.71e-03

Pos logit contributions
ashes+0.002
olls+0.002
ips+0.002
les+0.002
olphins+0.002
Neg logit contributions
ache-0.002
 badly-0.002
Mill-0.002
Am-0.002
Sad-0.002
TokenThe
Token ID464
Feature activation+1.29e-02

Pos logit contributions
ache+0.006
 badly+0.006
Mill+0.005
Am+0.005
Sad+0.005
Neg logit contributions
ashes-0.007
ips-0.007
olls-0.007
les-0.007
 recess-0.006
Token mom
Token ID1995
Feature activation+3.90e-02

Pos logit contributions
ache+0.024
 badly+0.022
 spe+0.021
 severe+0.021
 gen+0.020
Neg logit contributions
ashes-0.021
ips-0.020
olls-0.020
 recess-0.020
les-0.019
Token hugged
Token ID41130
Feature activation+7.54e-04

Pos logit contributions
ache+0.076
 badly+0.071
 spe+0.066
 gen+0.066
 severe+0.066
Neg logit contributions
ashes-0.060
ips-0.058
olls-0.058
 recess-0.056
olphins-0.055
Token her
Token ID607
Feature activation+4.26e-02

Pos logit contributions
ache+0.001
 badly+0.001
 spe+0.001
 gen+0.001
 severe+0.001
Neg logit contributions
ashes-0.001
olls-0.001
ips-0.001
 recess-0.001
les-0.001
Token daughter
Token ID4957
Feature activation+7.78e-02

Pos logit contributions
ache+0.088
Mill+0.080
 spe+0.080
 badly+0.078
Jean+0.076
Neg logit contributions
les-0.056
ashes-0.055
olls-0.055
ips-0.051
olphins-0.050
Token and
Token ID290
Feature activation-4.39e-03

Pos logit contributions
ache+0.164
 spe+0.149
Mill+0.148
 badly+0.147
 gen+0.146
Neg logit contributions
ashes-0.103
olls-0.098
les-0.098
ips-0.097
 scores-0.095
Token said
Token ID531
Feature activation+4.03e-02

Pos logit contributions
les+0.004
 recess+0.004
ashed+0.004
ashes+0.004
ips+0.004
Neg logit contributions
ache-0.011
 badly-0.010
 spe-0.009
Sad-0.009
Am-0.009
Token,
Token ID11
Feature activation+5.17e-02

Pos logit contributions
ache+0.091
 severe+0.083
 spe+0.083
Mill+0.082
Sad+0.082
Neg logit contributions
olls-0.043
ips-0.039
les-0.039
ashes-0.038
 morning-0.038
Token "
Token ID366
Feature activation+2.55e-02

Pos logit contributions
ache+0.098
 badly+0.092
 mercy+0.087
 severe+0.086
 spe+0.086
Neg logit contributions
olls-0.075
ashes-0.075
ips-0.073
olphins-0.070
asher-0.069
TokenYou
Token ID1639
Feature activation-1.72e-02

Pos logit contributions
ache+0.048
 badly+0.045
Mill+0.043
Am+0.042
Sad+0.042
Neg logit contributions
ashes-0.042
olls-0.040
ips-0.040
 recess-0.039
 scores-0.038
Token sad
Token ID6507
Feature activation-1.62e-02

Pos logit contributions
ache+0.028
 spe+0.025
 badly+0.025
 gen+0.024
Am+0.024
Neg logit contributions
ashes-0.017
olls-0.017
les-0.017
 recess-0.017
ips-0.017
Token.
Token ID13
Feature activation+4.61e-03

Pos logit contributions
ashes+0.025
olls+0.024
ips+0.024
les+0.023
 recess+0.023
Neg logit contributions
ache-0.031
 badly-0.028
 spe-0.028
 severe-0.027
 gen-0.027
Token She
Token ID1375
Feature activation+1.53e-02

Pos logit contributions
ache+0.009
 badly+0.009
 spe+0.008
 severe+0.008
 gen+0.008
Neg logit contributions
ashes-0.007
olls-0.007
ips-0.007
 recess-0.006
les-0.006
Token hugged
Token ID41130
Feature activation+1.43e-04

Pos logit contributions
ache+0.031
 spe+0.029
 badly+0.029
comb+0.028
Mill+0.028
Neg logit contributions
les-0.019
olls-0.018
 scores-0.018
ashes-0.018
 rains-0.017
Token her
Token ID607
Feature activation+3.10e-02

Pos logit contributions
ache+0.000
 badly+0.000
 spe+0.000
 severe+0.000
 gen+0.000
Neg logit contributions
olls-0.000
ashes-0.000
ips-0.000
les-0.000
 recess-0.000
Token daughter
Token ID4957
Feature activation+7.78e-02

Pos logit contributions
ache+0.057
Mill+0.051
 spe+0.051
 badly+0.050
Jess+0.049
Neg logit contributions
les-0.048
olls-0.048
ashes-0.047
 day-0.046
 morning-0.045
Token and
Token ID290
Feature activation-1.59e-03

Pos logit contributions
ache+0.161
 spe+0.149
Mill+0.144
 gen+0.144
 badly+0.140
Neg logit contributions
ashes-0.106
olls-0.100
les-0.100
 scores-0.097
ips-0.097
Token hoped
Token ID10719
Feature activation+1.73e-02

Pos logit contributions
 day+0.001
 morning+0.001
 recess+0.001
les+0.001
 Ben+0.001
Neg logit contributions
ache-0.004
 spe-0.004
 badly-0.004
Sad-0.004
Am-0.004
Token that
Token ID326
Feature activation+2.05e-02

Pos logit contributions
ache+0.036
 spe+0.031
 badly+0.031
 gen+0.031
 severe+0.031
Neg logit contributions
 recess-0.023
 morning-0.023
 day-0.023
olls-0.022
ips-0.022
Token she
Token ID673
Feature activation+1.76e-04

Pos logit contributions
ache+0.042
 badly+0.036
 spe+0.035
 severe+0.034
 gen+0.034
Neg logit contributions
 day-0.029
 recess-0.029
 morning-0.028
olls-0.027
ips-0.027
Token had
Token ID550
Feature activation-5.26e-03

Pos logit contributions
ache+0.000
Mill+0.000
 badly+0.000
 gen+0.000
 spe+0.000
Neg logit contributions
olls-0.000
les-0.000
ashes-0.000
ips-0.000
ops-0.000
Token been
Token ID587
Feature activation+9.21e-03

Pos logit contributions
ashes+0.036
olls+0.035
ips+0.035
les+0.034
olphins+0.034
Neg logit contributions
ache-0.041
 badly-0.039
 severe-0.035
 mercy-0.035
 spe-0.035
Token bad
Token ID2089
Feature activation-2.00e-02

Pos logit contributions
ache+0.015
 badly+0.014
 spe+0.013
 gen+0.013
 severe+0.013
Neg logit contributions
ashes-0.017
ips-0.017
olls-0.016
 recess-0.016
 scores-0.016
Token and
Token ID290
Feature activation+1.22e-02

Pos logit contributions
ashes+0.036
ips+0.036
olls+0.035
asher+0.035
olphins+0.034
Neg logit contributions
ache-0.033
 badly-0.031
 mercy-0.028
 able-0.026
 gen-0.026
Token made
Token ID925
Feature activation+9.25e-03

Pos logit contributions
ache+0.022
 badly+0.020
Mill+0.019
Am+0.019
 spe+0.019
Neg logit contributions
ashes-0.020
olls-0.019
ips-0.019
 recess-0.019
 scores-0.019
Token their
Token ID511
Feature activation+2.04e-02

Pos logit contributions
ache+0.017
 spe+0.015
 badly+0.014
 gen+0.014
Mill+0.014
Neg logit contributions
ashes-0.016
ips-0.015
olls-0.015
les-0.015
 recess-0.015
Token mom
Token ID1995
Feature activation+7.78e-02

Pos logit contributions
ache+0.035
 badly+0.032
 spe+0.030
Mill+0.029
 gen+0.029
Neg logit contributions
ashes-0.037
ips-0.036
olls-0.036
 recess-0.035
 scores-0.034
Token angry
Token ID7954
Feature activation+6.18e-03

Pos logit contributions
ache+0.137
 spe+0.134
Mill+0.134
comb+0.130
Jess+0.129
Neg logit contributions
ashes-0.126
les-0.116
 scores-0.113
ips-0.110
 day-0.108
Token.
Token ID13
Feature activation+3.00e-03

Pos logit contributions
ache+0.011
 badly+0.010
 gen+0.009
 mercy+0.009
 severe+0.009
Neg logit contributions
ashes-0.011
ips-0.010
olls-0.010
 recess-0.010
olphins-0.010
Token They
Token ID1119
Feature activation-1.38e-02

Pos logit contributions
ache+0.008
 badly+0.008
 spe+0.007
 severe+0.007
 gen+0.007
Neg logit contributions
ashes-0.002
olls-0.002
ips-0.002
 recess-0.002
olphins-0.002
Token quickly
Token ID2952
Feature activation-7.43e-03

Pos logit contributions
olls+0.017
les+0.017
ashes+0.016
ashed+0.016
 scored+0.015
Neg logit contributions
ache-0.028
 spe-0.027
 badly-0.026
comb-0.026
Mill-0.025
Token apologized
Token ID22893
Feature activation-8.90e-03

Pos logit contributions
ashes+0.010
les+0.010
olls+0.009
ashed+0.009
 scores+0.009
Neg logit contributions
ache-0.015
 badly-0.015
Mill-0.014
 spe-0.014
 gen-0.014
Token!"
Token ID2474
Feature activation+2.60e-03

Pos logit contributions
ashes+0.006
olls+0.006
ips+0.006
 recess+0.006
les+0.005
Neg logit contributions
ache-0.010
 badly-0.009
 severe-0.009
 gen-0.009
 spe-0.009
Token and
Token ID290
Feature activation-9.25e-03

Pos logit contributions
ache+0.006
 badly+0.005
 spe+0.005
 severe+0.005
 gen+0.005
Neg logit contributions
ashes-0.004
olls-0.003
ips-0.003
les-0.003
 recess-0.003
Token quickly
Token ID2952
Feature activation-1.20e-02

Pos logit contributions
ashes+0.012
olls+0.012
ips+0.012
 recess+0.011
les+0.011
Neg logit contributions
ache-0.020
 badly-0.018
 severe-0.017
 mercy-0.017
 gen-0.017
Token made
Token ID925
Feature activation+9.21e-03

Pos logit contributions
ashes+0.017
olls+0.016
les+0.016
ips+0.016
 recess+0.016
Neg logit contributions
ache-0.024
 badly-0.023
 severe-0.021
 gen-0.021
Sad-0.021
Token her
Token ID607
Feature activation+2.85e-02

Pos logit contributions
ache+0.017
 badly+0.016
 spe+0.015
 severe+0.014
 gen+0.014
Neg logit contributions
ashes-0.016
les-0.015
ips-0.015
olls-0.015
 recess-0.014
Token daughter
Token ID4957
Feature activation+7.77e-02

Pos logit contributions
ache+0.069
 badly+0.062
Mill+0.061
 severe+0.057
 mercy+0.057
Neg logit contributions
 day-0.036
ashes-0.036
 morning-0.035
 recess-0.033
 scores-0.032
Token her
Token ID607
Feature activation+2.99e-02

Pos logit contributions
ache+0.163
 spe+0.143
 badly+0.142
Mill+0.142
Am+0.140
Neg logit contributions
ashes-0.114
 scores-0.099
ips-0.098
 day-0.097
 morning-0.095
Token favourite
Token ID12507
Feature activation-2.62e-02

Pos logit contributions
ache+0.071
Mill+0.065
 badly+0.064
Sad+0.061
Am+0.060
Neg logit contributions
ashes-0.038
 day-0.037
 morning-0.035
 scores-0.034
 recess-0.033
Token dish
Token ID9433
Feature activation+1.71e-02

Pos logit contributions
ashes+0.036
 day+0.034
les+0.033
olls+0.033
ips+0.033
Neg logit contributions
ache-0.057
 badly-0.049
 severe-0.048
Mill-0.047
Sad-0.047
Token -
Token ID532
Feature activation+4.09e-02

Pos logit contributions
ache+0.035
 badly+0.032
 spe+0.031
 severe+0.031
Mill+0.030
Neg logit contributions
ashes-0.025
olls-0.024
ips-0.024
les-0.023
ops-0.023
Token a
Token ID257
Feature activation+2.24e-02

Pos logit contributions
ache+0.077
 badly+0.070
 severe+0.066
Sad+0.063
 mercy+0.063
Neg logit contributions
olls-0.064
ashes-0.063
ips-0.062
olphins-0.059
 scores-0.059
Token longer
Token ID2392
Feature activation-1.77e-02

Pos logit contributions
ache+0.015
 badly+0.013
 severe+0.013
 spe+0.013
Mill+0.013
Neg logit contributions
ashes-0.012
olls-0.011
ips-0.011
les-0.011
 recess-0.011
Token and
Token ID290
Feature activation+1.98e-03

Pos logit contributions
ashes+0.026
ips+0.025
olls+0.025
 recess+0.024
les+0.024
Neg logit contributions
ache-0.035
 badly-0.032
 gen-0.031
Mill-0.031
 spe-0.031
Token she
Token ID673
Feature activation-1.31e-02

Pos logit contributions
ache+0.004
 badly+0.003
Am+0.003
 spe+0.003
Mill+0.003
Neg logit contributions
 recess-0.003
 day-0.003
ashes-0.003
 scores-0.003
 morning-0.003
Token made
Token ID925
Feature activation+1.08e-02

Pos logit contributions
les+0.018
ashes+0.018
ops+0.018
ips+0.018
 scores+0.018
Neg logit contributions
ache-0.026
 badly-0.024
Mill-0.023
 mercy-0.023
 spe-0.023
Token her
Token ID607
Feature activation+2.94e-02

Pos logit contributions
ache+0.019
 badly+0.016
 spe+0.016
 severe+0.015
 gen+0.015
Neg logit contributions
ashes-0.019
les-0.019
ips-0.018
olls-0.018
 recess-0.018
Token mom
Token ID1995
Feature activation+7.74e-02

Pos logit contributions
ache+0.066
Mill+0.059
Am+0.058
Jess+0.056
 badly+0.056
Neg logit contributions
 day-0.039
ashes-0.037
 morning-0.036
 scores-0.035
 recess-0.035
Token proud
Token ID6613
Feature activation-9.56e-03

Pos logit contributions
ache+0.159
 badly+0.144
 mercy+0.144
 spe+0.144
Am+0.142
Neg logit contributions
ashes-0.106
les-0.097
ips-0.096
 scores-0.093
 day-0.093
Token by
Token ID416
Feature activation+3.40e-02

Pos logit contributions
ashes+0.015
ips+0.015
olls+0.015
 recess+0.014
les+0.014
Neg logit contributions
ache-0.018
 badly-0.017
 spe-0.016
 severe-0.016
 gen-0.016
Token being
Token ID852
Feature activation+1.77e-03

Pos logit contributions
ache+0.068
 badly+0.056
 severe+0.056
 spe+0.055
 gen+0.053
Neg logit contributions
ips-0.054
 recess-0.052
 scores-0.048
olls-0.048
ashes-0.047
Token calm
Token ID9480
Feature activation-3.58e-02

Pos logit contributions
ache+0.003
comb+0.003
 spe+0.002
 gen+0.002
 mercy+0.002
Neg logit contributions
ips-0.003
ashes-0.003
 recess-0.003
 scores-0.003
asher-0.003
Token and
Token ID290
Feature activation+2.90e-02

Pos logit contributions
ashes+0.061
olls+0.060
ips+0.059
 recess+0.058
olphins+0.057
Neg logit contributions
ache-0.063
 badly-0.060
 severe-0.054
 spe-0.053
 gen-0.052
Token so
Token ID523
Feature activation+2.76e-02

Pos logit contributions
ache+0.077
 mercy+0.068
 severe+0.066
comb+0.064
Sad+0.062
Neg logit contributions
ips-0.060
 Win-0.058
 day-0.058
 players-0.057
 scores-0.057
Token happy
Token ID3772
Feature activation-1.96e-02

Pos logit contributions
ache+0.050
 mercy+0.045
 badly+0.044
 severe+0.043
Sad+0.042
Neg logit contributions
ashes-0.046
ips-0.044
olls-0.043
 scores-0.042
acking-0.042
Token and
Token ID290
Feature activation+9.48e-03

Pos logit contributions
ashes+0.038
ips+0.037
olls+0.037
 recess+0.036
asher+0.035
Neg logit contributions
ache-0.031
 badly-0.029
 spe-0.026
 gen-0.025
Mill-0.025
Token gave
Token ID2921
Feature activation-1.53e-02

Pos logit contributions
ache+0.017
 badly+0.015
 spe+0.014
 severe+0.014
 gen+0.014
Neg logit contributions
ashes-0.016
olls-0.016
ips-0.016
 recess-0.015
les-0.015
Token her
Token ID607
Feature activation+2.93e-02

Pos logit contributions
ashes+0.025
olls+0.024
ips+0.023
olphins+0.022
asher+0.022
Neg logit contributions
ache-0.028
 badly-0.027
Mill-0.026
 spe-0.025
 gen-0.025
Token son
Token ID3367
Feature activation+7.72e-02

Pos logit contributions
ache+0.058
 badly+0.053
 spe+0.049
 severe+0.049
Mill+0.049
Neg logit contributions
ashes-0.043
 recess-0.042
ips-0.042
olls-0.042
 scores-0.041
Token a
Token ID257
Feature activation+2.53e-02

Pos logit contributions
ache+0.109
 badly+0.100
 spe+0.090
 severe+0.089
 gen+0.088
Neg logit contributions
ashes-0.159
ips-0.155
olls-0.155
 recess-0.150
les-0.149
Token big
Token ID1263
Feature activation+1.42e-02

Pos logit contributions
ache+0.045
 badly+0.042
 spe+0.039
Mill+0.038
 severe+0.038
Neg logit contributions
ashes-0.042
olls-0.040
ips-0.040
 recess-0.040
les-0.039
Token hug
Token ID16225
Feature activation-7.42e-04

Pos logit contributions
ache+0.025
 badly+0.023
 spe+0.023
 gen+0.023
 mercy+0.021
Neg logit contributions
ips-0.025
ashes-0.024
olls-0.024
olphins-0.023
ops-0.022
Token.
Token ID13
Feature activation-4.86e-03

Pos logit contributions
ashes+0.001
olls+0.001
ips+0.001
 recess+0.001
les+0.001
Neg logit contributions
ache-0.001
 badly-0.001
 spe-0.001
 severe-0.001
 gen-0.001
Token
Token ID198
Feature activation+1.52e-02

Pos logit contributions
ashes+0.009
les+0.009
olls+0.009
ips+0.008
 recess+0.008
Neg logit contributions
Mill-0.007
ache-0.007
 badly-0.007
Am-0.007
Sad-0.006
Token woman
Token ID2415
Feature activation+7.33e-02

Pos logit contributions
ache+0.073
 badly+0.070
 spe+0.068
Sad+0.067
comb+0.067
Neg logit contributions
 day-0.054
 morning-0.052
les-0.051
ashes-0.050
 recess-0.049
Token.
Token ID13
Feature activation-3.46e-03

Pos logit contributions
ache+0.158
 spe+0.145
 badly+0.143
Mill+0.142
Sad+0.141
Neg logit contributions
ashes-0.094
les-0.087
 scores-0.085
ips-0.084
olls-0.084
Token She
Token ID1375
Feature activation+2.46e-03

Pos logit contributions
ashes+0.005
ips+0.005
olls+0.005
 recess+0.005
les+0.005
Neg logit contributions
ache-0.007
 badly-0.006
 spe-0.006
 severe-0.006
 gen-0.006
Token asked
Token ID1965
Feature activation+2.55e-02

Pos logit contributions
ache+0.005
 badly+0.005
 severe+0.005
 spe+0.005
 mercy+0.005
Neg logit contributions
les-0.003
olls-0.003
ashes-0.003
ashed-0.003
ips-0.003
Token the
Token ID262
Feature activation+3.76e-02

Pos logit contributions
ache+0.054
 badly+0.048
 spe+0.048
 severe+0.048
 gen+0.046
Neg logit contributions
olls-0.036
les-0.033
 recess-0.033
ips-0.033
ashes-0.032
Token woman
Token ID2415
Feature activation+7.71e-02

Pos logit contributions
ache+0.063
 badly+0.063
 able+0.060
Sad+0.058
 spe+0.057
Neg logit contributions
 day-0.061
 morning-0.060
olls-0.059
les-0.057
 recess-0.057
Token if
Token ID611
Feature activation+1.97e-02

Pos logit contributions
ache+0.133
 spe+0.121
 badly+0.118
 severe+0.116
 gen+0.113
Neg logit contributions
olls-0.132
ashes-0.128
les-0.127
ips-0.125
olphins-0.125
Token she
Token ID673
Feature activation-2.67e-02

Pos logit contributions
ache+0.039
 badly+0.035
 severe+0.033
 spe+0.033
Sad+0.032
Neg logit contributions
olls-0.029
 recess-0.028
olphins-0.028
ips-0.027
ashes-0.027
Token wanted
Token ID2227
Feature activation-9.10e-03

Pos logit contributions
olls+0.033
ashes+0.032
les+0.032
ops+0.031
ips+0.030
Neg logit contributions
ache-0.056
 badly-0.053
 severe-0.051
Mill-0.051
Sad-0.051
Token help
Token ID1037
Feature activation+1.32e-02

Pos logit contributions
ashes+0.013
olls+0.012
 recess+0.012
ips+0.012
les+0.012
Neg logit contributions
ache-0.018
 badly-0.017
 spe-0.016
 severe-0.016
Sad-0.016
Token and
Token ID290
Feature activation+6.05e-03

Pos logit contributions
ache+0.028
 spe+0.025
 badly+0.025
 gen+0.025
 severe+0.025
Neg logit contributions
ashes-0.017
olls-0.016
ips-0.016
les-0.016
 recess-0.015
Token wanted
Token ID2227
Feature activation-2.51e-03

Pos logit contributions
ache+0.015
 badly+0.014
 severe+0.013
 spe+0.013
 mercy+0.013
Neg logit contributions
ashes-0.010
olls-0.010
les-0.010
ips-0.010
 scores-0.009
Token to
Token ID284
Feature activation+2.89e-02

Pos logit contributions
 recess+0.004
ashes+0.003
olls+0.003
ips+0.003
 scores+0.003
Neg logit contributions
ache-0.005
 badly-0.005
 spe-0.004
 severe-0.004
Mill-0.004
Token make
Token ID787
Feature activation+3.41e-03

Pos logit contributions
ache+0.066
 badly+0.061
 spe+0.058
 severe+0.058
Mill+0.056
Neg logit contributions
ashes-0.034
 recess-0.033
olls-0.031
 scores-0.031
 Win-0.030
Token her
Token ID607
Feature activation+3.43e-02

Pos logit contributions
ache+0.006
 badly+0.005
 spe+0.005
 severe+0.005
 gen+0.005
Neg logit contributions
ashes-0.006
ips-0.006
olls-0.006
les-0.006
 recess-0.006
Token little
Token ID1310
Feature activation+1.74e-02

Pos logit contributions
ache+0.068
Mill+0.059
 badly+0.059
 spe+0.059
Am+0.058
Neg logit contributions
ashes-0.054
 day-0.050
 recess-0.050
 scores-0.049
 morning-0.048
Token girl
Token ID2576
Feature activation+7.70e-02

Pos logit contributions
ache+0.034
 badly+0.032
Mill+0.030
 severe+0.030
 spe+0.030
Neg logit contributions
ashes-0.026
olls-0.025
ips-0.024
 recess-0.024
 scores-0.024
Token happy
Token ID3772
Feature activation-1.40e-02

Pos logit contributions
ache+0.135
 spe+0.118
 badly+0.118
Mill+0.116
Am+0.114
Neg logit contributions
ashes-0.133
 scores-0.123
ips-0.123
olls-0.122
les-0.121
Token again
Token ID757
Feature activation+4.25e-03

Pos logit contributions
ashes+0.021
ips+0.020
olls+0.020
 recess+0.019
les+0.019
Neg logit contributions
ache-0.028
 badly-0.026
 spe-0.025
 severe-0.025
Mill-0.024
Token.
Token ID13
Feature activation-3.96e-03

Pos logit contributions
ache+0.009
 badly+0.008
 gen+0.008
 spe+0.008
 severe+0.008
Neg logit contributions
ashes-0.005
ips-0.005
 recess-0.005
olls-0.005
 day-0.005
Token Mom
Token ID11254
Feature activation+2.83e-02

Pos logit contributions
ashes+0.006
olls+0.006
ips+0.006
 recess+0.005
les+0.005
Neg logit contributions
ache-0.008
 badly-0.008
 spe-0.007
 severe-0.007
 gen-0.007
Token decided
Token ID3066
Feature activation+9.79e-03

Pos logit contributions
ache+0.055
 badly+0.052
 spe+0.048
 severe+0.048
 gen+0.047
Neg logit contributions
ashes-0.043
olls-0.042
ips-0.042
les-0.040
 recess-0.040
Token very
Token ID845
Feature activation+3.40e-02

Pos logit contributions
ache+0.086
 mercy+0.077
comb+0.076
 severe+0.074
vern+0.069
Neg logit contributions
 day-0.057
 Win-0.057
 morning-0.054
 sun-0.051
ips-0.051
Token curious
Token ID11040
Feature activation-8.09e-03

Pos logit contributions
ache+0.059
 mercy+0.054
comb+0.052
Sad+0.051
 badly+0.050
Neg logit contributions
ashes-0.055
asher-0.051
 day-0.051
olls-0.051
 Win-0.051
Token and
Token ID290
Feature activation+6.18e-03

Pos logit contributions
ashes+0.011
les+0.011
olls+0.011
ips+0.010
 scores+0.010
Neg logit contributions
ache-0.017
 badly-0.015
 severe-0.015
 spe-0.015
Mill-0.015
Token asked
Token ID1965
Feature activation+2.36e-02

Pos logit contributions
ache+0.013
 badly+0.012
 severe+0.012
 gen+0.012
 spe+0.012
Neg logit contributions
ashes-0.008
olls-0.008
les-0.007
olphins-0.007
 recess-0.007
Token the
Token ID262
Feature activation+3.13e-02

Pos logit contributions
ache+0.055
 spe+0.050
 severe+0.050
 badly+0.049
 swollen+0.048
Neg logit contributions
olls-0.026
 day-0.024
 morning-0.024
 Win-0.023
les-0.023
Token woman
Token ID2415
Feature activation+7.68e-02

Pos logit contributions
 badly+0.060
ache+0.059
comb+0.055
 able+0.055
 spe+0.053
Neg logit contributions
 day-0.049
 morning-0.047
les-0.044
 sun-0.044
 air-0.043
Token,
Token ID11
Feature activation+5.50e-02

Pos logit contributions
ache+0.124
 spe+0.113
 severe+0.108
 badly+0.108
 gen+0.102
Neg logit contributions
olls-0.143
ashes-0.138
olphins-0.136
les-0.135
 scores-0.133
Token "
Token ID366
Feature activation+2.69e-02

Pos logit contributions
ache+0.128
 badly+0.116
 severe+0.116
 spe+0.112
 mercy+0.111
Neg logit contributions
 Win-0.057
olls-0.056
ips-0.055
ashes-0.053
 You-0.052
TokenWhat
Token ID2061
Feature activation-1.03e-02

Pos logit contributions
ache+0.054
 badly+0.053
 spe+0.049
 severe+0.049
 mercy+0.048
Neg logit contributions
olls-0.037
ips-0.036
ashes-0.036
les-0.035
 recess-0.034
Token is
Token ID318
Feature activation+1.80e-02

Pos logit contributions
ashes+0.010
olls+0.010
ips+0.010
 recess+0.009
 scores+0.009
Neg logit contributions
ache-0.026
 badly-0.024
 spe-0.023
 severe-0.023
Mill-0.023
Token that
Token ID326
Feature activation-1.01e-02

Pos logit contributions
ache+0.035
 badly+0.032
 severe+0.031
 mercy+0.030
Sad+0.030
Neg logit contributions
olls-0.026
 recess-0.026
ips-0.025
ashes-0.025
 morning-0.025
Token she
Token ID673
Feature activation-4.08e-04

Pos logit contributions
ache+0.076
 badly+0.068
 gen+0.068
 mercy+0.066
 spe+0.066
Neg logit contributions
olls-0.056
ashes-0.053
ips-0.053
 recess-0.052
 day-0.052
Token decided
Token ID3066
Feature activation+9.92e-03

Pos logit contributions
ashes+0.001
olls+0.001
ips+0.001
les+0.001
 recess+0.001
Neg logit contributions
ache-0.001
 badly-0.001
 spe-0.001
 severe-0.001
 gen-0.001
Token to
Token ID284
Feature activation+2.96e-02

Pos logit contributions
ache+0.020
 spe+0.019
 badly+0.019
 gen+0.018
 severe+0.018
Neg logit contributions
olls-0.013
ashes-0.013
 recess-0.013
les-0.012
 scores-0.012
Token give
Token ID1577
Feature activation-1.92e-02

Pos logit contributions
ache+0.059
 badly+0.055
 spe+0.052
 severe+0.051
 gen+0.051
Neg logit contributions
ashes-0.044
ips-0.043
olls-0.043
 recess-0.041
les-0.041
Token her
Token ID607
Feature activation+2.64e-02

Pos logit contributions
ashes+0.036
ips+0.035
olls+0.035
 recess+0.034
les+0.034
Neg logit contributions
ache-0.031
 badly-0.028
 spe-0.026
 severe-0.026
 gen-0.025
Token daughter
Token ID4957
Feature activation+7.66e-02

Pos logit contributions
ache+0.045
 badly+0.041
 spe+0.039
Mill+0.039
 gen+0.038
Neg logit contributions
ashes-0.045
olls-0.044
 recess-0.044
ips-0.043
les-0.043
Token a
Token ID257
Feature activation+2.00e-02

Pos logit contributions
ache+0.120
 badly+0.110
 spe+0.104
 gen+0.102
Mill+0.100
Neg logit contributions
ashes-0.145
olls-0.140
ips-0.140
 recess-0.137
les-0.135
Token teaspoon
Token ID22326
Feature activation+3.67e-02

Pos logit contributions
ache+0.039
 badly+0.038
Mill+0.035
 spe+0.035
Sad+0.034
Neg logit contributions
ashes-0.028
olls-0.027
 recess-0.027
 morning-0.026
 day-0.026
Token.
Token ID13
Feature activation+7.05e-05

Pos logit contributions
ache+0.076
 badly+0.070
 spe+0.069
 gen+0.068
Mill+0.067
Neg logit contributions
ashes-0.051
olls-0.049
ips-0.048
les-0.046
 recess-0.045
Token The
Token ID383
Feature activation+2.12e-02

Pos logit contributions
ache+0.000
 badly+0.000
 spe+0.000
Mill+0.000
 severe+0.000
Neg logit contributions
ashes-0.000
ips-0.000
olls-0.000
 recess-0.000
les-0.000
Token little
Token ID1310
Feature activation+1.11e-02

Pos logit contributions
ache+0.038
 badly+0.036
 spe+0.035
Mill+0.034
 able+0.033
Neg logit contributions
olls-0.034
 day-0.033
ashes-0.033
 morning-0.033
 recess-0.033
Token ball
Token ID2613
Feature activation+5.93e-03

Pos logit contributions
ashes+0.048
ips+0.046
olls+0.045
olphins+0.044
 recess+0.042
Neg logit contributions
 badly-0.086
ache-0.080
 spe-0.077
 gen-0.076
bul-0.071
Token that
Token ID326
Feature activation-2.25e-02

Pos logit contributions
ache+0.010
 badly+0.010
 spe+0.009
 gen+0.009
 severe+0.009
Neg logit contributions
ashes-0.010
olls-0.010
ips-0.010
 recess-0.010
olphins-0.010
Token was
Token ID373
Feature activation+3.78e-02

Pos logit contributions
ashes+0.033
olls+0.032
ips+0.032
 recess+0.031
les+0.031
Neg logit contributions
ache-0.045
 badly-0.042
 severe-0.039
 spe-0.039
 gen-0.038
Token just
Token ID655
Feature activation-1.89e-02

Pos logit contributions
ache+0.068
Am+0.061
Jess+0.061
Mill+0.060
Jean+0.059
Neg logit contributions
ips-0.058
ashes-0.056
 scores-0.055
 day-0.055
 recess-0.055
Token as
Token ID355
Feature activation+8.81e-03

Pos logit contributions
ashes+0.032
ips+0.031
olls+0.031
 recess+0.030
les+0.030
Neg logit contributions
ache-0.034
 badly-0.031
 severe-0.029
 spe-0.029
 gen-0.028
Token boun
Token ID31283
Feature activation-1.05e-01

Pos logit contributions
ache+0.016
 badly+0.014
Am+0.013
Mill+0.013
 gen+0.013
Neg logit contributions
ashes-0.015
olls-0.014
ips-0.014
 recess-0.014
 scores-0.014
Tokency
Token ID948
Feature activation-2.21e-02

Pos logit contributions
olls+0.102
ashes+0.101
 players+0.099
olphins+0.098
ops+0.098
Neg logit contributions
 badly-0.262
ful-0.214
ache-0.212
 spe-0.208
 sadly-0.208
Token as
Token ID355
Feature activation+1.23e-02

Pos logit contributions
olphins+0.039
olls+0.038
ips+0.037
asher+0.037
 Win+0.036
Neg logit contributions
 badly-0.036
ache-0.036
 spe-0.034
 able-0.032
 mercy-0.028
Token the
Token ID262
Feature activation+1.54e-02

Pos logit contributions
ache+0.024
 badly+0.022
 severe+0.020
 gen+0.020
 spe+0.020
Neg logit contributions
ashes-0.019
ips-0.019
olls-0.019
 recess-0.018
les-0.018
Token red
Token ID2266
Feature activation-1.78e-02

Pos logit contributions
 badly+0.028
ache+0.027
 spe+0.025
 severe+0.025
 swollen+0.025
Neg logit contributions
olls-0.025
les-0.025
ips-0.024
acks-0.024
ashes-0.024
Token one
Token ID530
Feature activation-1.22e-02

Pos logit contributions
olphins+0.024
ashes+0.023
olls+0.023
ips+0.023
acks+0.023
Neg logit contributions
 badly-0.038
ache-0.033
 spe-0.031
 mercy-0.029
 slightly-0.029
Token sign
Token ID1051
Feature activation-2.18e-02

Pos logit contributions
ache+0.014
 badly+0.013
 severe+0.012
 spe+0.012
Mill+0.012
Neg logit contributions
ashes-0.009
olls-0.009
ips-0.009
 recess-0.009
les-0.009
Token '
Token ID705
Feature activation-3.19e-02

Pos logit contributions
ashes+0.034
ips+0.033
olls+0.033
 recess+0.032
les+0.031
Neg logit contributions
ache-0.041
 badly-0.039
 spe-0.036
 severe-0.036
 gen-0.036
Tokenhappy
Token ID34191
Feature activation-4.35e-02

Pos logit contributions
ashes+0.053
olls+0.051
ips+0.049
 recess+0.049
olphins+0.049
Neg logit contributions
ache-0.059
 badly-0.054
 spe-0.051
Mill-0.051
Am-0.051
Token',
Token ID3256
Feature activation-2.30e-04

Pos logit contributions
ashes+0.068
ips+0.067
olls+0.065
 recess+0.065
les+0.062
Neg logit contributions
ache-0.084
 badly-0.078
 spe-0.071
 severe-0.071
 gen-0.071
Token '
Token ID705
Feature activation-5.31e-03

Pos logit contributions
ashes+0.000
ips+0.000
olls+0.000
 recess+0.000
les+0.000
Neg logit contributions
ache-0.000
 badly-0.000
 spe-0.000
 gen-0.000
 severe-0.000
Tokenbirth
Token ID24280
Feature activation-1.04e-01

Pos logit contributions
ashes+0.009
olls+0.008
ips+0.008
les+0.008
 recess+0.008
Neg logit contributions
ache-0.010
 badly-0.009
 spe-0.009
Am-0.009
Mill-0.009
Tokenday
Token ID820
Feature activation-6.43e-03

Pos logit contributions
ashes+0.146
olls+0.141
asher+0.128
 scores+0.127
olphins+0.127
Neg logit contributions
ache-0.200
 gen-0.197
Am-0.197
 severe-0.189
 badly-0.188
Token',
Token ID3256
Feature activation+2.56e-04

Pos logit contributions
ashes+0.012
ips+0.012
olls+0.011
 recess+0.011
les+0.011
Neg logit contributions
ache-0.011
 badly-0.010
 gen-0.009
 severe-0.009
 spe-0.009
Token and
Token ID290
Feature activation-1.13e-02

Pos logit contributions
ache+0.000
 badly+0.000
 gen+0.000
 spe+0.000
 severe+0.000
Neg logit contributions
ashes-0.000
ips-0.000
 recess-0.000
olls-0.000
 scores-0.000
Token '
Token ID705
Feature activation-6.51e-03

Pos logit contributions
ashes+0.022
ips+0.021
olls+0.021
 recess+0.021
les+0.020
Neg logit contributions
ache-0.017
 badly-0.016
 spe-0.015
 severe-0.014
 gen-0.014
Tokenyou
Token ID5832
Feature activation-3.96e-02

Pos logit contributions
ashes+0.010
olls+0.010
ips+0.010
les+0.010
 recess+0.010
Neg logit contributions
ache-0.012
 badly-0.011
 spe-0.011
Am-0.011
Mill-0.011
Token.
Token ID13
Feature activation-1.05e-02

Pos logit contributions
ache+0.011
 badly+0.010
 spe+0.009
 severe+0.009
 gen+0.009
Neg logit contributions
ashes-0.009
olls-0.009
ips-0.009
 recess-0.009
les-0.009
Token The
Token ID383
Feature activation-1.49e-03

Pos logit contributions
ips+0.017
les+0.017
olphins+0.017
ashes+0.017
 recess+0.017
Neg logit contributions
 badly-0.017
ache-0.017
 spe-0.016
 severe-0.015
Mill-0.015
Token basketball
Token ID9669
Feature activation-1.59e-02

Pos logit contributions
olphins+0.002
ips+0.002
ops+0.002
les+0.002
ites+0.002
Neg logit contributions
 badly-0.003
 severe-0.002
 worse-0.002
 swollen-0.002
 compassionate-0.002
Token was
Token ID373
Feature activation+3.92e-02

Pos logit contributions
ips+0.030
ashes+0.030
olls+0.029
olphins+0.029
 recess+0.029
Neg logit contributions
 badly-0.026
ache-0.025
 severe-0.021
 spe-0.020
 able-0.020
Token not
Token ID407
Feature activation-2.58e-04

Pos logit contributions
ache+0.062
Mill+0.053
 gen+0.053
Am+0.052
 badly+0.052
Neg logit contributions
ashes-0.074
ips-0.072
olls-0.071
 recess-0.070
 scores-0.069
Token boun
Token ID31283
Feature activation-1.04e-01

Pos logit contributions
ashes+0.000
olls+0.000
ips+0.000
 recess+0.000
les+0.000
Neg logit contributions
ache-0.000
 badly-0.000
 spe-0.000
 severe-0.000
 gen-0.000
Tokency
Token ID948
Feature activation-1.57e-02

Pos logit contributions
olphins+0.097
olls+0.095
ashes+0.092
ops+0.090
 recess+0.089
Neg logit contributions
 badly-0.259
ache-0.224
ful-0.213
 spe-0.207
 able-0.206
Token anymore
Token ID7471
Feature activation-1.92e-02

Pos logit contributions
ashes+0.026
ips+0.026
olls+0.026
 recess+0.025
olphins+0.025
Neg logit contributions
ache-0.028
 badly-0.026
 spe-0.024
 severe-0.024
 gen-0.023
Token.
Token ID13
Feature activation-1.26e-02

Pos logit contributions
ashes+0.031
ips+0.030
olls+0.030
 recess+0.029
les+0.029
Neg logit contributions
ache-0.036
 badly-0.034
 spe-0.031
 severe-0.031
 gen-0.031
Token It
Token ID632
Feature activation-3.18e-02

Pos logit contributions
ips+0.020
olphins+0.020
ashes+0.020
 recess+0.020
les+0.020
Neg logit contributions
 badly-0.022
ache-0.021
 spe-0.019
Sad-0.019
 severe-0.019
Token was
Token ID373
Feature activation+2.95e-02

Pos logit contributions
ashes+0.048
olls+0.046
ips+0.046
les+0.044
 recess+0.044
Neg logit contributions
ache-0.063
 badly-0.058
 severe-0.054
 spe-0.054
Mill-0.054
Token found
Token ID1043
Feature activation+4.95e-04

Pos logit contributions
ips+0.096
 recess+0.089
olls+0.088
olphins+0.086
ops+0.086
Neg logit contributions
ache-0.086
 spe-0.085
 badly-0.082
 able-0.082
 rather-0.081
Token.
Token ID13
Feature activation-1.51e-02

Pos logit contributions
 badly+0.001
ache+0.001
 spe+0.001
 able+0.001
 gen+0.001
Neg logit contributions
ashes-0.001
olls-0.001
ips-0.001
 recess-0.001
asher-0.001
Token It
Token ID632
Feature activation-2.81e-02

Pos logit contributions
ashes+0.019
ips+0.019
olls+0.018
 recess+0.018
les+0.018
Neg logit contributions
ache-0.033
 badly-0.031
 spe-0.030
 gen-0.029
Mill-0.029
Token's
Token ID338
Feature activation+1.76e-02

Pos logit contributions
 recess+0.041
ips+0.040
ashes+0.040
olls+0.040
olphins+0.038
Neg logit contributions
ache-0.056
 badly-0.052
 spe-0.051
 gen-0.049
 severe-0.048
Token really
Token ID1107
Feature activation+1.39e-04

Pos logit contributions
ache+0.027
 badly+0.024
 spe+0.022
 gen+0.022
 severe+0.022
Neg logit contributions
ashes-0.035
ips-0.034
olls-0.034
 recess-0.033
 scores-0.032
Token boun
Token ID31283
Feature activation-9.88e-02

Pos logit contributions
 badly+0.000
ache+0.000
 spe+0.000
 severe+0.000
 able+0.000
Neg logit contributions
ips-0.000
ops-0.000
olls-0.000
 recess-0.000
les-0.000
Tokency
Token ID948
Feature activation-1.03e-02

Pos logit contributions
ops+0.106
olls+0.101
ashes+0.100
olphins+0.099
 sidelines+0.096
Neg logit contributions
 badly-0.224
ful-0.185
 spe-0.184
ache-0.184
bul-0.181
Token!"
Token ID2474
Feature activation-9.10e-03

Pos logit contributions
ips+0.017
olls+0.017
 recess+0.017
olphins+0.016
ashes+0.016
Neg logit contributions
ache-0.018
 badly-0.018
 spe-0.016
 able-0.015
Am-0.015
Token
Token ID198
Feature activation+8.76e-03

Pos logit contributions
ips+0.018
ashes+0.017
olls+0.017
asher+0.017
olphins+0.017
Neg logit contributions
ache-0.012
Mill-0.012
 badly-0.012
Sad-0.011
 gen-0.011
Token
Token ID198
Feature activation+2.16e-02

Pos logit contributions
ache+0.018
 badly+0.017
 spe+0.015
 severe+0.015
 gen+0.015
Neg logit contributions
ashes-0.013
ips-0.012
olls-0.012
 recess-0.012
les-0.012
TokenL
Token ID43
Feature activation+4.02e-03

Pos logit contributions
ache+0.041
 badly+0.039
 spe+0.036
 severe+0.036
 gen+0.036
Neg logit contributions
ashes-0.034
ips-0.033
olls-0.033
 recess-0.032
les-0.031
Token.
Token ID13
Feature activation-1.63e-02

Pos logit contributions
ache+0.020
Mill+0.019
Am+0.018
 badly+0.018
 severe+0.018
Neg logit contributions
ashes-0.013
ips-0.012
olls-0.012
 scores-0.012
les-0.012
Token It
Token ID632
Feature activation-3.02e-02

Pos logit contributions
les+0.021
ips+0.020
olls+0.020
ashes+0.020
ops+0.019
Neg logit contributions
ache-0.034
 badly-0.034
 spe-0.032
Mill-0.031
Sad-0.031
Token was
Token ID373
Feature activation+2.62e-02

Pos logit contributions
ashes+0.039
les+0.037
olls+0.036
ips+0.036
ops+0.035
Neg logit contributions
ache-0.065
 badly-0.061
 severe-0.059
Mill-0.058
 mercy-0.057
Token shiny
Token ID22441
Feature activation-4.01e-02

Pos logit contributions
ache+0.051
 badly+0.044
 severe+0.043
 gen+0.043
Mill+0.043
Neg logit contributions
ashes-0.040
ips-0.039
 recess-0.038
olls-0.037
 day-0.037
Token and
Token ID290
Feature activation+1.07e-03

Pos logit contributions
ashes+0.052
les+0.051
olls+0.050
ips+0.049
 scores+0.046
Neg logit contributions
ache-0.087
Mill-0.081
 badly-0.080
 severe-0.080
Am-0.079
Token boun
Token ID31283
Feature activation-9.85e-02

Pos logit contributions
ache+0.002
 badly+0.002
 spe+0.002
 severe+0.002
 gen+0.002
Neg logit contributions
ashes-0.002
ips-0.002
olls-0.002
les-0.002
 recess-0.002
Tokency
Token ID948
Feature activation-4.74e-03

Pos logit contributions
olls+0.100
ashes+0.096
 scores+0.095
olphins+0.094
ops+0.094
Neg logit contributions
 badly-0.233
ache-0.201
ful-0.196
 spe-0.196
bul-0.189
Token and
Token ID290
Feature activation-5.20e-03

Pos logit contributions
ashes+0.008
olls+0.007
ips+0.007
 recess+0.007
les+0.007
Neg logit contributions
ache-0.009
 badly-0.008
 spe-0.008
 severe-0.008
 gen-0.008
Token fun
Token ID1257
Feature activation-3.37e-02

Pos logit contributions
ashes+0.008
ips+0.008
olls+0.008
olphins+0.007
les+0.007
Neg logit contributions
ache-0.010
 badly-0.010
 spe-0.009
 gen-0.009
 severe-0.009
Token.
Token ID13
Feature activation-1.24e-02

Pos logit contributions
ashes+0.065
ips+0.065
olls+0.065
olphins+0.065
asher+0.063
Neg logit contributions
 badly-0.050
ache-0.048
 spe-0.042
 gen-0.040
 able-0.039
Token But
Token ID887
Feature activation+2.22e-02

Pos logit contributions
les+0.016
ashes+0.016
ips+0.016
olls+0.016
ops+0.015
Neg logit contributions
ache-0.025
 badly-0.025
 spe-0.023
Mill-0.023
Am-0.023
Token It
Token ID632
Feature activation-2.61e-02

Pos logit contributions
ashes+0.019
ips+0.018
olls+0.018
les+0.017
 recess+0.017
Neg logit contributions
ache-0.040
 badly-0.038
 spe-0.036
 gen-0.036
 severe-0.036
Token is
Token ID318
Feature activation+2.23e-02

Pos logit contributions
ashes+0.030
ips+0.029
olls+0.029
 recess+0.028
olphins+0.027
Neg logit contributions
ache-0.061
 badly-0.058
 spe-0.055
 gen-0.054
 severe-0.054
Token very
Token ID845
Feature activation+2.22e-02

Pos logit contributions
ache+0.040
 badly+0.036
 severe+0.035
Mill+0.034
 gen+0.034
Neg logit contributions
ashes-0.037
ips-0.036
olls-0.035
 scores-0.034
 recess-0.034
Token pretty
Token ID2495
Feature activation-3.25e-02

Pos logit contributions
 badly+0.029
ache+0.029
 spe+0.026
 severe+0.024
 gen+0.024
Neg logit contributions
ips-0.048
ashes-0.047
olls-0.047
 recess-0.046
ops-0.045
Token and
Token ID290
Feature activation+2.18e-03

Pos logit contributions
ashes+0.045
olls+0.044
ips+0.043
les+0.042
 recess+0.040
Neg logit contributions
ache-0.067
 badly-0.062
 severe-0.061
 spe-0.060
Mill-0.060
Token boun
Token ID31283
Feature activation-9.78e-02

Pos logit contributions
ache+0.003
 badly+0.003
 spe+0.003
 gen+0.003
 severe+0.003
Neg logit contributions
ashes-0.004
ips-0.004
olls-0.004
 recess-0.004
olphins-0.004
Tokency
Token ID948
Feature activation-3.84e-03

Pos logit contributions
ops+0.098
olls+0.097
ashes+0.097
olphins+0.096
 Win+0.094
Neg logit contributions
 badly-0.225
ache-0.199
 spe-0.192
ful-0.190
bul-0.186
Token."
Token ID526
Feature activation+1.32e-03

Pos logit contributions
ashes+0.006
ips+0.006
olls+0.006
 recess+0.006
olphins+0.006
Neg logit contributions
ache-0.007
 badly-0.007
 spe-0.006
 gen-0.006
Am-0.006
Token The
Token ID383
Feature activation+2.57e-02

Pos logit contributions
ache+0.003
 badly+0.003
 spe+0.002
 gen+0.002
 severe+0.002
Neg logit contributions
ashes-0.002
ips-0.002
olls-0.002
les-0.002
 recess-0.002
Token girl
Token ID2576
Feature activation+4.17e-02

Pos logit contributions
ache+0.050
 badly+0.046
 gen+0.044
 spe+0.044
 severe+0.042
Neg logit contributions
ashes-0.040
ips-0.040
olls-0.039
ops-0.036
les-0.036
Token said
Token ID531
Feature activation+3.03e-02

Pos logit contributions
ache+0.098
 badly+0.095
 severe+0.094
Mill+0.090
 mercy+0.090
Neg logit contributions
les-0.043
ashes-0.043
olls-0.039
ips-0.039
 scores-0.039
Token cave
Token ID11527
Feature activation+2.52e-02

Pos logit contributions
ache+0.008
 badly+0.007
 gen+0.007
 spe+0.007
 mercy+0.007
Neg logit contributions
ashes-0.011
ips-0.011
olls-0.010
ops-0.010
asher-0.010
Token.
Token ID13
Feature activation-6.69e-03

Pos logit contributions
ache+0.051
 badly+0.047
Mill+0.047
 spe+0.046
 severe+0.045
Neg logit contributions
ashes-0.036
olls-0.034
ips-0.034
les-0.033
 recess-0.032
Token You
Token ID921
Feature activation-4.03e-02

Pos logit contributions
ashes+0.007
olls+0.007
ips+0.007
 recess+0.007
les+0.006
Neg logit contributions
ache-0.016
 badly-0.015
 spe-0.014
 severe-0.014
 gen-0.014
Token are
Token ID389
Feature activation+1.49e-02

Pos logit contributions
ashes+0.048
olls+0.047
ips+0.046
 recess+0.044
les+0.044
Neg logit contributions
ache-0.091
 badly-0.087
 spe-0.082
 severe-0.081
 gen-0.081
Token not
Token ID407
Feature activation+2.09e-03

Pos logit contributions
ache+0.026
 badly+0.023
 spe+0.022
 severe+0.022
Mill+0.022
Neg logit contributions
ips-0.025
ashes-0.025
 recess-0.025
 scores-0.025
olls-0.024
Token en
Token ID551
Feature activation-9.60e-02

Pos logit contributions
ache+0.004
 spe+0.003
 gen+0.003
 badly+0.003
comb+0.003
Neg logit contributions
ashes-0.003
 scores-0.003
ips-0.003
 recess-0.003
olls-0.003
Tokenvious
Token ID1442
Feature activation-3.52e-02

Pos logit contributions
olphins+0.150
ops+0.148
 recess+0.144
 jerseys+0.142
 rods+0.139
Neg logit contributions
ache-0.170
 badly-0.162
 worse-0.147
 able-0.135
 mercy-0.131
Token.
Token ID13
Feature activation-7.86e-03

Pos logit contributions
ashes+0.060
olls+0.058
ips+0.058
 recess+0.057
olphins+0.056
Neg logit contributions
ache-0.063
 badly-0.060
 spe-0.053
 severe-0.053
 gen-0.052
Token You
Token ID921
Feature activation-3.92e-02

Pos logit contributions
ashes+0.008
ips+0.008
les+0.008
olls+0.008
 recess+0.008
Neg logit contributions
ache-0.019
 badly-0.018
 spe-0.017
 gen-0.017
Mill-0.017
Token are
Token ID389
Feature activation+1.26e-02

Pos logit contributions
ashes+0.048
ips+0.047
olls+0.046
 recess+0.045
olphins+0.043
Neg logit contributions
ache-0.089
 badly-0.084
 spe-0.079
 severe-0.078
 gen-0.078
Token adventurous
Token ID39770
Feature activation-2.20e-02

Pos logit contributions
ache+0.022
 badly+0.019
 spe+0.018
 severe+0.018
Mill+0.018
Neg logit contributions
ashes-0.021
ips-0.021
olls-0.021
 recess-0.021
 scores-0.021
Token is
Token ID318
Feature activation+2.28e-02

Pos logit contributions
 recess+0.039
ashes+0.037
ips+0.037
olls+0.036
olphins+0.035
Neg logit contributions
ache-0.062
 badly-0.058
 spe-0.056
 gen-0.055
Am-0.053
Token big
Token ID1263
Feature activation-6.00e-03

Pos logit contributions
ache+0.040
 badly+0.036
 severe+0.034
 gen+0.033
 spe+0.033
Neg logit contributions
ashes-0.040
ips-0.039
olls-0.039
 recess-0.037
 scores-0.037
Token and
Token ID290
Feature activation+9.88e-03

Pos logit contributions
ashes+0.009
olls+0.009
ips+0.009
 recess+0.008
les+0.008
Neg logit contributions
ache-0.012
 badly-0.011
 spe-0.010
 severe-0.010
 gen-0.010
Token round
Token ID2835
Feature activation-4.00e-02

Pos logit contributions
ache+0.016
 badly+0.016
 spe+0.015
 severe+0.014
 gen+0.014
Neg logit contributions
ashes-0.018
ips-0.018
olls-0.017
olphins-0.017
 recess-0.017
Token and
Token ID290
Feature activation+9.51e-03

Pos logit contributions
 recess+0.072
ashes+0.072
ips+0.071
olphins+0.071
olls+0.070
Neg logit contributions
 badly-0.062
ache-0.062
 spe-0.054
 gen-0.051
 mercy-0.049
Token boun
Token ID31283
Feature activation-9.58e-02

Pos logit contributions
ache+0.016
 spe+0.016
 badly+0.016
 gen+0.015
 swollen+0.014
Neg logit contributions
ashes-0.016
ips-0.016
olls-0.015
olphins-0.015
 recess-0.015
Tokency
Token ID948
Feature activation-1.53e-03

Pos logit contributions
ops+0.111
 sidelines+0.110
olls+0.105
olphins+0.105
 Win+0.104
Neg logit contributions
 badly-0.201
ful-0.169
 spe-0.168
bul-0.160
ache-0.159
Token.
Token ID13
Feature activation-8.68e-03

Pos logit contributions
 recess+0.003
olls+0.003
ips+0.003
olphins+0.003
ashes+0.003
Neg logit contributions
 badly-0.002
ache-0.002
 spe-0.002
Am-0.002
 gen-0.002
Token Can
Token ID1680
Feature activation+3.66e-03

Pos logit contributions
ashes+0.011
ips+0.010
olls+0.010
les+0.010
 recess+0.010
Neg logit contributions
ache-0.019
 badly-0.018
 spe-0.017
 gen-0.017
Mill-0.017
Token I
Token ID314
Feature activation-3.08e-02

Pos logit contributions
 badly+0.007
ache+0.007
 spe+0.007
 gen+0.007
 mercy+0.006
Neg logit contributions
ashes-0.006
les-0.005
ips-0.005
olls-0.005
olphins-0.005
Token hold
Token ID1745
Feature activation-3.56e-02

Pos logit contributions
ips+0.041
olls+0.039
olphins+0.039
les+0.038
ashes+0.038
Neg logit contributions
 badly-0.064
ache-0.063
 spe-0.057
 able-0.054
 gen-0.054
Token is
Token ID318
Feature activation+2.42e-02

Pos logit contributions
 recess+0.031
ashes+0.031
ips+0.031
olls+0.030
olphins+0.028
Neg logit contributions
ache-0.056
 badly-0.053
 spe-0.050
 gen-0.049
 severe-0.048
Token shiny
Token ID22441
Feature activation-3.78e-02

Pos logit contributions
ache+0.050
 badly+0.047
 spe+0.044
 severe+0.044
 gen+0.043
Neg logit contributions
ashes-0.034
olls-0.033
ips-0.033
 recess-0.032
les-0.031
Token and
Token ID290
Feature activation+4.83e-03

Pos logit contributions
ashes+0.061
ips+0.059
olls+0.059
 recess+0.058
olphins+0.056
Neg logit contributions
ache-0.071
 badly-0.067
 spe-0.062
 severe-0.060
 gen-0.060
Token round
Token ID2835
Feature activation-3.94e-02

Pos logit contributions
 badly+0.007
ache+0.007
 spe+0.007
 gen+0.006
 severe+0.006
Neg logit contributions
ashes-0.009
ips-0.009
olls-0.009
les-0.009
 recess-0.009
Token and
Token ID290
Feature activation+4.05e-03

Pos logit contributions
 recess+0.072
ashes+0.072
ips+0.071
olphins+0.071
olls+0.070
Neg logit contributions
 badly-0.063
ache-0.062
 spe-0.053
 gen-0.049
 able-0.049
Token boun
Token ID31283
Feature activation-9.56e-02

Pos logit contributions
ache+0.008
 badly+0.007
 spe+0.007
 gen+0.007
 severe+0.007
Neg logit contributions
ashes-0.006
ips-0.006
olls-0.006
olphins-0.006
 recess-0.006
Tokency
Token ID948
Feature activation+6.66e-04

Pos logit contributions
ops+0.105
 sidelines+0.103
olls+0.102
olphins+0.100
ashes+0.097
Neg logit contributions
 badly-0.221
ful-0.180
ache-0.178
 spe-0.176
bul-0.168
Token.
Token ID13
Feature activation-8.22e-03

Pos logit contributions
 badly+0.001
ache+0.001
 spe+0.001
 able+0.001
 gen+0.001
Neg logit contributions
olls-0.001
ips-0.001
 recess-0.001
olphins-0.001
ashes-0.001
Token I
Token ID314
Feature activation-3.20e-02

Pos logit contributions
ashes+0.009
ips+0.009
les+0.009
 recess+0.009
olls+0.009
Neg logit contributions
ache-0.019
 badly-0.018
 spe-0.017
 gen-0.017
Am-0.017
Token like
Token ID588
Feature activation-1.68e-02

Pos logit contributions
ips+0.047
 recess+0.046
olls+0.046
ashes+0.045
olphins+0.043
Neg logit contributions
ache-0.065
 badly-0.063
 spe-0.058
 severe-0.056
 gen-0.055
Token it
Token ID340
Feature activation-1.23e-02

Pos logit contributions
ashes+0.027
olls+0.027
ips+0.027
olphins+0.026
ops+0.026
Neg logit contributions
 badly-0.031
ache-0.030
 spe-0.028
 able-0.026
 mercy-0.026
Token It
Token ID632
Feature activation-2.11e-02

Pos logit contributions
ashes+0.013
olls+0.012
ips+0.012
 recess+0.012
les+0.012
Neg logit contributions
ache-0.031
 badly-0.029
 spe-0.028
 severe-0.027
 gen-0.027
Token was
Token ID373
Feature activation+2.50e-02

Pos logit contributions
ashes+0.027
les+0.026
 scores+0.025
olls+0.025
ips+0.025
Neg logit contributions
ache-0.045
 badly-0.042
Mill-0.041
 severe-0.040
Am-0.039
Token still
Token ID991
Feature activation-5.79e-03

Pos logit contributions
ache+0.044
Mill+0.038
Am+0.038
 badly+0.037
Sad+0.037
Neg logit contributions
ashes-0.041
ips-0.040
 recess-0.039
 scores-0.039
olls-0.039
Token round
Token ID2835
Feature activation-4.46e-02

Pos logit contributions
ashes+0.010
olls+0.010
ips+0.010
 recess+0.010
les+0.010
Neg logit contributions
ache-0.010
 badly-0.009
 spe-0.008
 severe-0.008
 gen-0.008
Token and
Token ID290
Feature activation+4.54e-03

Pos logit contributions
ashes+0.071
olls+0.069
ips+0.069
 recess+0.066
olphins+0.065
Neg logit contributions
ache-0.084
 badly-0.079
 spe-0.073
 severe-0.072
 gen-0.072
Token boun
Token ID31283
Feature activation-9.52e-02

Pos logit contributions
ache+0.007
 badly+0.007
 spe+0.007
 severe+0.006
 gen+0.006
Neg logit contributions
ashes-0.008
ips-0.008
olls-0.008
les-0.008
olphins-0.008
Tokency
Token ID948
Feature activation-1.43e-03

Pos logit contributions
olls+0.095
olphins+0.094
ops+0.091
 sidelines+0.090
ashes+0.089
Neg logit contributions
 badly-0.230
ache-0.192
ful-0.190
 spe-0.185
bul-0.179
Token and
Token ID290
Feature activation+6.24e-04

Pos logit contributions
olls+0.002
ashes+0.002
ips+0.002
 recess+0.002
olphins+0.002
Neg logit contributions
ache-0.002
 badly-0.002
 spe-0.002
 gen-0.002
 severe-0.002
Token colorful
Token ID20239
Feature activation-1.68e-02

Pos logit contributions
ache+0.001
 badly+0.001
 spe+0.001
 swollen+0.001
 severe+0.001
Neg logit contributions
ashes-0.001
ips-0.001
olls-0.001
olphins-0.001
les-0.001
Token.
Token ID13
Feature activation-8.49e-03

Pos logit contributions
ashes+0.028
ips+0.028
olls+0.028
olphins+0.027
 recess+0.027
Neg logit contributions
ache-0.029
 badly-0.028
 spe-0.026
 gen-0.025
 severe-0.024
Token They
Token ID1119
Feature activation-2.07e-02

Pos logit contributions
ashes+0.009
olls+0.009
ips+0.009
les+0.008
 recess+0.008
Neg logit contributions
ache-0.020
 badly-0.019
 spe-0.018
 severe-0.018
 gen-0.018
Token round
Token ID2835
Feature activation-3.72e-02

Pos logit contributions
ache+0.012
 badly+0.012
 spe+0.011
 severe+0.011
 swollen+0.010
Neg logit contributions
ashes-0.016
ips-0.015
olls-0.015
olphins-0.015
 recess-0.015
Token,
Token ID11
Feature activation+2.63e-02

Pos logit contributions
ashes+0.059
ips+0.058
olls+0.058
 recess+0.055
les+0.055
Neg logit contributions
ache-0.070
 badly-0.066
 spe-0.061
 severe-0.061
 gen-0.060
Token and
Token ID290
Feature activation+7.75e-03

Pos logit contributions
 badly+0.043
ache+0.042
 spe+0.040
 gen+0.037
Mill+0.037
Neg logit contributions
ashes-0.048
ips-0.047
olls-0.047
 recess-0.046
olphins-0.045
Token ever
Token ID1683
Feature activation-1.45e-02

Pos logit contributions
ache+0.015
 badly+0.014
 spe+0.014
 severe+0.013
 gen+0.013
Neg logit contributions
ashes-0.012
ips-0.012
olls-0.012
 recess-0.011
olphins-0.011
Token so
Token ID523
Feature activation+6.52e-03

Pos logit contributions
ashes+0.025
ips+0.025
olls+0.025
olphins+0.024
 recess+0.024
Neg logit contributions
ache-0.025
 badly-0.024
 spe-0.022
 gen-0.021
 severe-0.021
Token boun
Token ID31283
Feature activation-9.51e-02

Pos logit contributions
ache+0.012
 badly+0.011
 severe+0.010
 gen+0.010
 spe+0.010
Neg logit contributions
ashes-0.011
olls-0.011
ips-0.011
 recess-0.010
les-0.010
Tokency
Token ID948
Feature activation-9.55e-03

Pos logit contributions
ashes+0.090
olls+0.089
ips+0.085
ops+0.085
 scores+0.082
Neg logit contributions
 badly-0.242
ache-0.214
 spe-0.203
Mill-0.201
ful-0.197
Token.
Token ID13
Feature activation-9.04e-03

Pos logit contributions
olls+0.017
ashes+0.017
ips+0.017
olphins+0.017
 recess+0.017
Neg logit contributions
 badly-0.016
ache-0.015
 spe-0.014
 able-0.014
Mill-0.012
Token Every
Token ID3887
Feature activation-2.77e-02

Pos logit contributions
ashes+0.017
ips+0.017
les+0.017
olls+0.016
olphins+0.016
Neg logit contributions
Mill-0.013
 badly-0.013
 spe-0.013
Am-0.012
Sad-0.012
Token day
Token ID1110
Feature activation+3.27e-03

Pos logit contributions
olls+0.018
ashes+0.018
ips+0.018
olphins+0.016
 recess+0.014
Neg logit contributions
 badly-0.077
ache-0.077
 spe-0.072
 severe-0.071
 gen-0.071
Token,
Token ID11
Feature activation+2.22e-02

Pos logit contributions
 badly+0.004
 spe+0.004
ache+0.004
 gen+0.004
Am+0.004
Neg logit contributions
ashes-0.007
ips-0.007
olls-0.007
olphins-0.007
asher-0.006
Token.
Token ID13
Feature activation-1.76e-02

Pos logit contributions
ache+0.013
 badly+0.013
 spe+0.011
 gen+0.011
 severe+0.011
Neg logit contributions
ashes-0.013
olls-0.013
ips-0.013
 recess-0.013
olphins-0.013
Token It
Token ID632
Feature activation-2.62e-02

Pos logit contributions
les+0.025
ops+0.024
olls+0.024
ips+0.024
ashes+0.023
Neg logit contributions
 badly-0.033
 spe-0.033
ache-0.032
Mill-0.030
Sad-0.030
Token is
Token ID318
Feature activation+2.55e-02

Pos logit contributions
 recess+0.032
olls+0.031
ips+0.030
ashes+0.030
olphins+0.029
Neg logit contributions
 spe-0.055
ache-0.055
 badly-0.054
 gen-0.051
 severe-0.049
Token big
Token ID1263
Feature activation+6.11e-04

Pos logit contributions
ache+0.049
 badly+0.043
 gen+0.041
Mill+0.041
 severe+0.041
Neg logit contributions
ashes-0.041
ips-0.040
olls-0.039
 recess-0.038
 scores-0.037
Token and
Token ID290
Feature activation+8.69e-03

Pos logit contributions
ache+0.001
 badly+0.001
 severe+0.001
 spe+0.001
Mill+0.001
Neg logit contributions
ashes-0.001
ips-0.001
olls-0.001
les-0.001
 recess-0.001
Token boun
Token ID31283
Feature activation-9.51e-02

Pos logit contributions
ache+0.015
 badly+0.014
 spe+0.013
 severe+0.013
 gen+0.013
Neg logit contributions
ashes-0.015
ips-0.015
olls-0.015
les-0.015
 recess-0.014
Tokency
Token ID948
Feature activation-1.20e-03

Pos logit contributions
ops+0.102
asher+0.095
olls+0.094
ashes+0.094
olphins+0.092
Neg logit contributions
 badly-0.216
ful-0.186
 spe-0.181
ache-0.180
bul-0.170
Token.
Token ID13
Feature activation-1.51e-02

Pos logit contributions
olls+0.002
ashes+0.002
ips+0.002
 recess+0.002
olphins+0.002
Neg logit contributions
ache-0.002
 badly-0.002
 spe-0.002
 gen-0.002
 severe-0.002
Token They
Token ID1119
Feature activation-2.50e-02

Pos logit contributions
ashes+0.019
olls+0.019
ips+0.019
les+0.019
ops+0.018
Neg logit contributions
ache-0.031
 badly-0.031
 spe-0.029
Mill-0.028
 gen-0.028
Token grab
Token ID5552
Feature activation-2.34e-02

Pos logit contributions
ips+0.039
olls+0.037
 recess+0.037
acked+0.037
ashes+0.036
Neg logit contributions
ache-0.046
 spe-0.044
 badly-0.044
 gen-0.039
 mercy-0.039
Token it
Token ID340
Feature activation+6.33e-03

Pos logit contributions
olls+0.043
olphins+0.043
asher+0.043
ashes+0.042
ops+0.042
Neg logit contributions
 badly-0.035
 spe-0.032
ache-0.031
 severe-0.028
 mercy-0.028
Token is
Token ID318
Feature activation+3.29e-02

Pos logit contributions
ache+0.001
 gen+0.001
 badly+0.001
 spe+0.001
 mercy+0.001
Neg logit contributions
 recess-0.001
asher-0.001
olls-0.001
oom-0.001
ashes-0.001
Token fun
Token ID1257
Feature activation-2.04e-02

Pos logit contributions
ache+0.056
 badly+0.048
 gen+0.048
Mill+0.047
Am+0.046
Neg logit contributions
ashes-0.059
ips-0.057
olls-0.055
 recess-0.054
 scores-0.054
Token.
Token ID13
Feature activation-1.25e-02

Pos logit contributions
olls+0.037
ashes+0.037
ips+0.037
olphins+0.036
les+0.036
Neg logit contributions
 badly-0.032
ache-0.032
 spe-0.028
 able-0.027
 gen-0.026
Token It
Token ID632
Feature activation-2.44e-02

Pos logit contributions
les+0.018
ips+0.017
 recess+0.017
ops+0.017
olls+0.017
Neg logit contributions
 badly-0.024
ache-0.023
 spe-0.022
 slightly-0.021
Am-0.020
Token is
Token ID318
Feature activation+3.02e-02

Pos logit contributions
 recess+0.032
ips+0.032
olls+0.031
ashes+0.030
oom+0.030
Neg logit contributions
ache-0.049
 spe-0.049
 badly-0.046
 gen-0.046
Am-0.043
Token boun
Token ID31283
Feature activation-9.44e-02

Pos logit contributions
ache+0.054
 badly+0.048
 gen+0.046
 severe+0.045
Mill+0.045
Neg logit contributions
ashes-0.053
ips-0.051
olls-0.049
 recess-0.049
 scores-0.048
Tokency
Token ID948
Feature activation-3.34e-03

Pos logit contributions
ops+0.096
ashes+0.090
olls+0.088
 scores+0.088
olphins+0.087
Neg logit contributions
 badly-0.224
ful-0.192
ache-0.187
 spe-0.184
Mill-0.182
Token and
Token ID290
Feature activation+2.85e-03

Pos logit contributions
ashes+0.006
olls+0.006
ips+0.006
 recess+0.005
olphins+0.005
Neg logit contributions
ache-0.006
 badly-0.006
 spe-0.005
 gen-0.005
 severe-0.005
Token w
Token ID266
Feature activation-4.32e-02

Pos logit contributions
 spe+0.004
 badly+0.004
 swollen+0.004
ache+0.003
 cob+0.003
Neg logit contributions
les-0.006
oom-0.005
ips-0.005
olphins-0.005
olls-0.005
Tokenobb
Token ID21963
Feature activation-4.23e-02

Pos logit contributions
 morning+0.048
 Win+0.047
olphins+0.047
asher+0.047
 day+0.047
Neg logit contributions
 badly-0.093
ache-0.092
 mercy-0.083
vern-0.081
 able-0.079
Tokenly
Token ID306
Feature activation-1.24e-02

Pos logit contributions
 recess+0.071
ips+0.069
 league+0.068
olphins+0.067
olls+0.066
Neg logit contributions
ache-0.077
 badly-0.071
 spe-0.061
 severe-0.059
 able-0.057
Token is
Token ID318
Feature activation+2.50e-02

Pos logit contributions
 recess+0.056
ashes+0.053
ips+0.052
olls+0.051
olphins+0.050
Neg logit contributions
 spe-0.063
 badly-0.059
 gen-0.056
ache-0.056
 cob-0.052
Token red
Token ID2266
Feature activation-4.94e-02

Pos logit contributions
ache+0.051
 badly+0.043
 gen+0.042
 severe+0.042
Mill+0.042
Neg logit contributions
ashes-0.038
ips-0.036
olls-0.036
 recess-0.035
 scores-0.035
Token and
Token ID290
Feature activation+6.15e-03

Pos logit contributions
ashes+0.077
ips+0.074
olls+0.074
 recess+0.071
les+0.070
Neg logit contributions
ache-0.095
 badly-0.089
 spe-0.083
 severe-0.082
 gen-0.082
Token shiny
Token ID22441
Feature activation-3.97e-02

Pos logit contributions
 spe+0.010
 badly+0.010
ache+0.010
 swollen+0.009
 severe+0.009
Neg logit contributions
ashes-0.011
ips-0.011
olls-0.011
les-0.011
olphins-0.011
Token and
Token ID290
Feature activation+1.42e-04

Pos logit contributions
ashes+0.060
olls+0.058
ips+0.058
les+0.056
 recess+0.055
Neg logit contributions
ache-0.078
 badly-0.072
 severe-0.069
Mill-0.068
 spe-0.068
Token boun
Token ID31283
Feature activation-9.31e-02

Pos logit contributions
ache+0.000
 badly+0.000
 spe+0.000
 gen+0.000
 severe+0.000
Neg logit contributions
ashes-0.000
ips-0.000
olls-0.000
 recess-0.000
olphins-0.000
Tokency
Token ID948
Feature activation-2.20e-03

Pos logit contributions
 sidelines+0.109
ops+0.108
olls+0.103
 players+0.102
ashes+0.099
Neg logit contributions
 badly-0.207
 spe-0.167
ful-0.166
ache-0.160
bul-0.157
Token.
Token ID13
Feature activation-8.10e-03

Pos logit contributions
olls+0.004
ashes+0.004
ips+0.004
 recess+0.004
olphins+0.004
Neg logit contributions
 badly-0.004
ache-0.004
 spe-0.003
 gen-0.003
 able-0.003
Token
Token ID198
Feature activation-7.90e-04

Pos logit contributions
les+0.015
robat+0.015
 recess+0.015
ips+0.015
olls+0.015
Neg logit contributions
 badly-0.011
Mill-0.010
ache-0.009
Am-0.009
 Kitty-0.009
Token
Token ID198
Feature activation+2.07e-02

Pos logit contributions
ashes+0.001
ips+0.001
olls+0.001
 recess+0.001
les+0.001
Neg logit contributions
ache-0.001
 badly-0.001
Mill-0.001
 severe-0.001
 spe-0.001
Token"
Token ID1
Feature activation+1.99e-02

Pos logit contributions
 badly+0.034
ache+0.031
 severe+0.030
Mill+0.029
Am+0.028
Neg logit contributions
ips-0.040
ashes-0.038
 recess-0.037
 scores-0.037
olphins-0.036
Token is
Token ID318
Feature activation+2.45e-02

Pos logit contributions
 recess+0.057
ashes+0.052
ips+0.051
olls+0.050
oom+0.050
Neg logit contributions
 spe-0.064
 badly-0.058
 gen-0.056
ache-0.056
 swollen-0.053
Token red
Token ID2266
Feature activation-4.91e-02

Pos logit contributions
ache+0.050
 badly+0.043
 gen+0.042
Mill+0.042
Am+0.041
Neg logit contributions
ashes-0.036
ips-0.036
olls-0.035
 recess-0.034
 scores-0.033
Token and
Token ID290
Feature activation+5.74e-03

Pos logit contributions
ashes+0.078
ips+0.076
olls+0.076
 recess+0.074
olphins+0.072
Neg logit contributions
ache-0.092
 badly-0.087
 spe-0.080
 severe-0.079
 gen-0.079
Token shiny
Token ID22441
Feature activation-4.00e-02

Pos logit contributions
 spe+0.010
 badly+0.010
ache+0.009
 swollen+0.009
 severe+0.009
Neg logit contributions
ashes-0.010
ips-0.010
olls-0.010
les-0.010
olphins-0.009
Token and
Token ID290
Feature activation-6.38e-04

Pos logit contributions
ashes+0.061
olls+0.059
ips+0.059
les+0.057
 recess+0.056
Neg logit contributions
ache-0.079
 badly-0.073
 severe-0.069
 spe-0.069
Mill-0.068
Token boun
Token ID31283
Feature activation-9.31e-02

Pos logit contributions
ashes+0.001
ips+0.001
olls+0.001
 recess+0.001
olphins+0.001
Neg logit contributions
ache-0.001
 badly-0.001
 spe-0.001
 gen-0.001
 severe-0.001
Tokency
Token ID948
Feature activation-2.72e-03

Pos logit contributions
ops+0.108
 sidelines+0.107
olls+0.099
 players+0.098
olphins+0.098
Neg logit contributions
 badly-0.206
ful-0.168
 spe-0.165
ache-0.159
bul-0.158
Token.
Token ID13
Feature activation-1.25e-03

Pos logit contributions
olls+0.005
 recess+0.005
ashes+0.005
ips+0.005
olphins+0.005
Neg logit contributions
 badly-0.004
ache-0.004
 spe-0.004
 able-0.004
 gen-0.004
Token They
Token ID1119
Feature activation-2.20e-02

Pos logit contributions
ashes+0.002
ips+0.002
olls+0.002
les+0.002
 recess+0.002
Neg logit contributions
ache-0.002
 badly-0.002
 spe-0.002
Mill-0.002
 severe-0.002
Token want
Token ID765
Feature activation-2.23e-02

Pos logit contributions
ips+0.038
 recess+0.035
ashes+0.034
ops+0.034
les+0.034
Neg logit contributions
 badly-0.037
ache-0.037
 spe-0.035
 mercy-0.033
 able-0.032
Token to
Token ID284
Feature activation+2.02e-02

Pos logit contributions
ashes+0.041
olls+0.041
ips+0.041
olphins+0.039
 recess+0.039
Neg logit contributions
ache-0.036
 badly-0.034
 spe-0.031
 severe-0.031
 gen-0.030
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
ashes+0.018
olls+0.017
ips+0.017
 recess+0.017
 scores+0.017
Neg logit contributions
ache-0.027
 severe-0.024
 badly-0.024
 gen-0.024
Mill-0.023
Token It
Token ID632
Feature activation-3.09e-02

Pos logit contributions
ashes+0.024
ips+0.023
olls+0.023
 recess+0.023
les+0.023
Neg logit contributions
ache-0.023
 badly-0.023
Sad-0.022
Mill-0.022
Jean-0.021
Token was
Token ID373
Feature activation+2.75e-02

Pos logit contributions
ashes+0.039
olls+0.037
les+0.037
ips+0.036
ops+0.036
Neg logit contributions
ache-0.067
 badly-0.063
 severe-0.060
 mercy-0.059
Mill-0.059
Token big
Token ID1263
Feature activation-1.56e-03

Pos logit contributions
ache+0.056
 badly+0.048
 mercy+0.047
 severe+0.047
 gen+0.046
Neg logit contributions
 day-0.041
 morning-0.040
 recess-0.039
ashes-0.039
 Win-0.039
Token and
Token ID290
Feature activation+2.42e-03

Pos logit contributions
ashes+0.002
olls+0.002
ips+0.002
les+0.002
 recess+0.002
Neg logit contributions
ache-0.003
 badly-0.003
 severe-0.003
Mill-0.003
 gen-0.003
Token boun
Token ID31283
Feature activation-9.28e-02

Pos logit contributions
ache+0.004
 badly+0.004
 spe+0.004
 severe+0.004
 gen+0.004
Neg logit contributions
ashes-0.004
ips-0.004
olls-0.004
 recess-0.004
les-0.004
Tokency
Token ID948
Feature activation+3.11e-03

Pos logit contributions
olls+0.099
olphins+0.095
ops+0.093
ashes+0.093
 scores+0.091
Neg logit contributions
 badly-0.220
ache-0.186
 spe-0.182
ful-0.178
bul-0.176
Token and
Token ID290
Feature activation-2.99e-03

Pos logit contributions
ache+0.005
 badly+0.005
 spe+0.005
 gen+0.005
 severe+0.005
Neg logit contributions
ashes-0.005
olls-0.005
ips-0.005
 recess-0.005
olphins-0.005
Token shiny
Token ID22441
Feature activation-3.55e-02

Pos logit contributions
ashes+0.005
ips+0.004
olls+0.004
olphins+0.004
les+0.004
Neg logit contributions
ache-0.006
 badly-0.006
 spe-0.005
 severe-0.005
 gen-0.005
Token.
Token ID13
Feature activation-1.24e-02

Pos logit contributions
ashes+0.057
ips+0.055
olls+0.055
 recess+0.053
les+0.052
Neg logit contributions
ache-0.067
 badly-0.063
 spe-0.059
 severe-0.058
 gen-0.058
Token
Token ID198
Feature activation-2.53e-03

Pos logit contributions
ashes+0.020
ips+0.020
 recess+0.020
olls+0.020
les+0.019
Neg logit contributions
ache-0.022
 badly-0.021
Mill-0.020
Sad-0.019
Jean-0.019
Token doll
Token ID3654
Feature activation+2.34e-02

Pos logit contributions
ashes+0.002
ips+0.002
olls+0.002
olphins+0.002
acks+0.002
Neg logit contributions
ache-0.003
 badly-0.003
 gen-0.003
 spe-0.002
 severe-0.002
Token.
Token ID13
Feature activation-2.11e-02

Pos logit contributions
ache+0.046
 badly+0.044
Mill+0.042
 severe+0.041
 spe+0.041
Neg logit contributions
ashes-0.035
ips-0.033
olls-0.033
les-0.032
 recess-0.032
Token They
Token ID1119
Feature activation-2.90e-02

Pos logit contributions
olls+0.025
ashes+0.025
ips+0.025
les+0.024
ops+0.024
Neg logit contributions
ache-0.046
 badly-0.044
 severe-0.042
 spe-0.042
Mill-0.041
Token were
Token ID547
Feature activation+2.38e-02

Pos logit contributions
ashes+0.038
ips+0.037
olls+0.037
 recess+0.037
les+0.036
Neg logit contributions
ache-0.061
 badly-0.058
 severe-0.054
Mill-0.054
 spe-0.053
Token not
Token ID407
Feature activation+4.52e-03

Pos logit contributions
ache+0.043
Mill+0.037
 badly+0.036
 spe+0.036
 gen+0.035
Neg logit contributions
ips-0.040
ashes-0.039
 players-0.038
 recess-0.038
 scores-0.038
Token en
Token ID551
Feature activation-9.28e-02

Pos logit contributions
ache+0.007
Am+0.007
Mill+0.007
 gen+0.007
 spe+0.007
Neg logit contributions
ashes-0.008
ips-0.008
 recess-0.007
 scores-0.007
les-0.007
Tokenvious
Token ID1442
Feature activation-2.97e-02

Pos logit contributions
olphins+0.137
ops+0.131
olls+0.130
 recess+0.126
 jerseys+0.122
Neg logit contributions
ache-0.181
 badly-0.167
 worse-0.156
 able-0.151
 severe-0.140
Token anymore
Token ID7471
Feature activation-4.98e-03

Pos logit contributions
ashes+0.049
ips+0.047
olls+0.047
 recess+0.046
les+0.046
Neg logit contributions
ache-0.054
 badly-0.051
 spe-0.048
 severe-0.048
Mill-0.047
Token.
Token ID13
Feature activation-1.41e-02

Pos logit contributions
ashes+0.006
ips+0.006
olls+0.006
ops+0.006
 recess+0.006
Neg logit contributions
ache-0.011
Mill-0.010
 spe-0.010
 severe-0.010
 gen-0.010
Token They
Token ID1119
Feature activation-2.00e-02

Pos logit contributions
ashes+0.018
olls+0.018
ips+0.018
les+0.017
 recess+0.017
Neg logit contributions
ache-0.030
 badly-0.029
 spe-0.027
 severe-0.027
 gen-0.027
Token were
Token ID547
Feature activation+2.27e-02

Pos logit contributions
ashes+0.025
olls+0.024
ips+0.023
les+0.023
 recess+0.023
Neg logit contributions
ache-0.044
 badly-0.041
 severe-0.039
Mill-0.039
 spe-0.038
Token ball
Token ID2613
Feature activation+3.49e-03

Pos logit contributions
ashes+0.006
ips+0.006
olphins+0.006
ites+0.006
ops+0.006
Neg logit contributions
 badly-0.006
 swollen-0.006
 ow-0.005
 no-0.005
 comforting-0.005
Token was
Token ID373
Feature activation+4.00e-02

Pos logit contributions
ache+0.006
 badly+0.006
 spe+0.006
 gen+0.006
 severe+0.005
Neg logit contributions
ashes-0.006
ips-0.006
olls-0.006
 recess-0.005
olphins-0.005
Token purple
Token ID14032
Feature activation-3.38e-02

Pos logit contributions
ache+0.088
 mercy+0.080
comb+0.076
 gen+0.075
Jess+0.074
Neg logit contributions
 day-0.051
ips-0.049
 morning-0.047
 recess-0.046
ashes-0.046
Token and
Token ID290
Feature activation-4.50e-04

Pos logit contributions
ashes+0.044
olls+0.042
ips+0.042
les+0.040
ops+0.040
Neg logit contributions
ache-0.074
 severe-0.069
Mill-0.067
 gen-0.066
Am-0.066
Token very
Token ID845
Feature activation+1.08e-02

Pos logit contributions
olls+0.001
ashes+0.001
ips+0.001
 recess+0.001
les+0.001
Neg logit contributions
ache-0.001
 badly-0.001
 severe-0.001
 mercy-0.001
 gen-0.001
Token boun
Token ID31283
Feature activation-9.27e-02

Pos logit contributions
ache+0.016
 badly+0.015
 spe+0.013
 severe+0.013
 gen+0.013
Neg logit contributions
ashes-0.022
ips-0.021
olls-0.021
 recess-0.021
les-0.020
Tokency
Token ID948
Feature activation-1.59e-03

Pos logit contributions
ashes+0.088
olphins+0.086
olls+0.086
ops+0.083
ips+0.083
Neg logit contributions
 badly-0.230
ache-0.202
 spe-0.191
Mill-0.190
ful-0.187
Token.
Token ID13
Feature activation-1.46e-02

Pos logit contributions
ashes+0.003
olls+0.003
ips+0.003
 recess+0.003
olphins+0.003
Neg logit contributions
ache-0.003
 badly-0.003
 spe-0.002
 gen-0.002
 severe-0.002
Token One
Token ID1881
Feature activation-3.17e-02

Pos logit contributions
ashes+0.026
olphins+0.026
ips+0.026
 recess+0.025
olls+0.025
Neg logit contributions
 badly-0.021
ache-0.021
Sad-0.020
Mill-0.019
 spe-0.019
Token day
Token ID1110
Feature activation-2.40e-03

Pos logit contributions
ips+0.026
olls+0.025
ashes+0.024
olphins+0.022
 recess+0.021
Neg logit contributions
 badly-0.085
ache-0.084
 severe-0.079
 spe-0.077
 gen-0.076
Token,
Token ID11
Feature activation+1.72e-02

Pos logit contributions
ashes+0.005
ips+0.005
olphins+0.005
asher+0.005
olls+0.004
Neg logit contributions
 badly-0.004
ache-0.003
 spe-0.003
 severe-0.003
 able-0.003
Token't
Token ID470
Feature activation-8.11e-03

Pos logit contributions
ache+0.007
 badly+0.007
 severe+0.006
 spe+0.006
 gen+0.006
Neg logit contributions
ashes-0.006
ips-0.006
olls-0.006
 recess-0.005
olphins-0.005
Token have
Token ID423
Feature activation-3.45e-02

Pos logit contributions
ips+0.014
olls+0.013
ashes+0.013
olphins+0.013
acked+0.012
Neg logit contributions
 badly-0.016
ache-0.015
 severe-0.013
 mercy-0.013
ful-0.012
Token dinner
Token ID8073
Feature activation-2.12e-02

Pos logit contributions
ashes+0.060
olls+0.059
ips+0.058
olphins+0.056
les+0.056
Neg logit contributions
ache-0.060
 badly-0.058
 spe-0.052
 severe-0.052
 gen-0.051
Token until
Token ID1566
Feature activation+1.48e-02

Pos logit contributions
ashes+0.037
olls+0.036
ips+0.036
olphins+0.035
les+0.035
Neg logit contributions
ache-0.037
 badly-0.035
 spe-0.030
 severe-0.030
 able-0.030
Token you
Token ID345
Feature activation-6.71e-02

Pos logit contributions
 badly+0.030
ache+0.029
 spe+0.027
 severe+0.026
 able+0.026
Neg logit contributions
ashes-0.022
olls-0.021
ips-0.021
olphins-0.020
les-0.020
Token bat
Token ID7365
Feature activation-9.25e-02

Pos logit contributions
ips+0.098
olls+0.095
 recess+0.094
ashes+0.090
olphins+0.090
Neg logit contributions
ache-0.136
 badly-0.130
 severe-0.116
 able-0.114
 mercy-0.113
Tokenhe
Token ID258
Feature activation-1.69e-02

Pos logit contributions
olphins+0.145
 scores+0.139
 recess+0.136
 Win+0.135
ashes+0.134
Neg logit contributions
 badly-0.166
ache-0.160
 able-0.138
ful-0.137
 severe-0.137
Token."
Token ID526
Feature activation-9.26e-03

Pos logit contributions
ashes+0.029
olls+0.028
ips+0.028
olphins+0.028
 recess+0.027
Neg logit contributions
 badly-0.029
ache-0.029
 able-0.025
 severe-0.025
 gen-0.024
Token
Token ID198
Feature activation+4.52e-03

Pos logit contributions
ips+0.016
 recess+0.016
ashes+0.016
olphins+0.015
olls+0.015
Neg logit contributions
 badly-0.016
ache-0.015
Mill-0.015
Sad-0.014
 severe-0.013
Token
Token ID198
Feature activation+1.84e-02

Pos logit contributions
ache+0.009
 badly+0.009
 spe+0.008
 severe+0.008
 gen+0.008
Neg logit contributions
ashes-0.006
ips-0.006
olls-0.006
 recess-0.006
les-0.006
TokenSo
Token ID2396
Feature activation-9.87e-03

Pos logit contributions
ache+0.035
 badly+0.033
 severe+0.030
Mill+0.030
 spe+0.030
Neg logit contributions
ashes-0.030
ips-0.029
olls-0.029
 recess-0.028
les-0.027
Token understand
Token ID1833
Feature activation+1.50e-02

Pos logit contributions
ips+0.005
ashes+0.005
 recess+0.005
olls+0.005
asher+0.005
Neg logit contributions
ache-0.005
 badly-0.005
 mercy-0.005
 gen-0.005
 severe-0.005
Token.
Token ID13
Feature activation-7.93e-03

Pos logit contributions
ache+0.033
 spe+0.031
Mill+0.030
 badly+0.030
 severe+0.029
Neg logit contributions
ashes-0.018
olls-0.018
ips-0.018
les-0.017
 recess-0.017
Token They
Token ID1119
Feature activation-2.57e-02

Pos logit contributions
ips+0.008
olls+0.008
ashes+0.008
les+0.008
 recess+0.008
Neg logit contributions
ache-0.018
 badly-0.018
 spe-0.017
Am-0.017
 severe-0.017
Token are
Token ID389
Feature activation+2.13e-02

Pos logit contributions
ips+0.041
ashes+0.040
olls+0.039
 recess+0.039
les+0.037
Neg logit contributions
ache-0.049
 badly-0.045
 mercy-0.042
 severe-0.042
 spe-0.041
Token not
Token ID407
Feature activation+2.19e-03

Pos logit contributions
ache+0.036
Mill+0.031
 spe+0.030
 badly+0.030
 gen+0.030
Neg logit contributions
ashes-0.039
ips-0.039
olls-0.036
 recess-0.035
 players-0.035
Token en
Token ID551
Feature activation-9.23e-02

Pos logit contributions
ache+0.003
 badly+0.003
 spe+0.003
 gen+0.003
Mill+0.003
Neg logit contributions
ashes-0.004
ips-0.004
olls-0.004
les-0.004
 recess-0.004
Tokenvious
Token ID1442
Feature activation-3.08e-02

Pos logit contributions
ops+0.136
olphins+0.135
 recess+0.130
robat+0.126
gers+0.126
Neg logit contributions
ache-0.177
 badly-0.161
 worse-0.153
 able-0.140
 mercy-0.136
Token anymore
Token ID7471
Feature activation+1.17e-04

Pos logit contributions
ashes+0.052
olls+0.051
ips+0.051
 recess+0.050
olphins+0.049
Neg logit contributions
ache-0.055
 badly-0.051
 spe-0.046
 severe-0.046
 gen-0.045
Token.
Token ID13
Feature activation-9.80e-03

Pos logit contributions
ache+0.000
 badly+0.000
 spe+0.000
 severe+0.000
 gen+0.000
Neg logit contributions
ashes-0.000
ips-0.000
olls-0.000
 recess-0.000
les-0.000
Token They
Token ID1119
Feature activation-2.46e-02

Pos logit contributions
olls+0.011
ips+0.011
les+0.011
ashes+0.011
 recess+0.010
Neg logit contributions
ache-0.022
 badly-0.022
 spe-0.021
Am-0.020
Mill-0.020
Token hug
Token ID16225
Feature activation-1.72e-02

Pos logit contributions
ips+0.041
 recess+0.038
ashes+0.038
olls+0.038
olphins+0.036
Neg logit contributions
ache-0.046
 badly-0.043
 spe-0.039
 mercy-0.039
 gen-0.039
Token.
Token ID13
Feature activation-1.18e-02

Pos logit contributions
ache+0.047
 gen+0.042
Sad+0.040
 spe+0.040
Mill+0.040
Neg logit contributions
ashes-0.021
 recess-0.019
 scores-0.018
 day-0.018
ips-0.018
Token
Token ID198
Feature activation+1.10e-02

Pos logit contributions
ashes+0.017
olls+0.017
ips+0.017
les+0.016
 recess+0.016
Neg logit contributions
ache-0.023
 badly-0.023
 spe-0.021
Mill-0.021
 severe-0.021
Token
Token ID198
Feature activation+2.54e-02

Pos logit contributions
ache+0.026
 badly+0.024
 spe+0.023
 gen+0.023
 mercy+0.022
Neg logit contributions
ashes-0.013
ips-0.012
olls-0.012
 recess-0.012
les-0.011
TokenThe
Token ID464
Feature activation+2.57e-02

Pos logit contributions
ache+0.041
 badly+0.037
 spe+0.036
 gen+0.035
 severe+0.034
Neg logit contributions
ashes-0.047
olls-0.046
ips-0.046
 recess-0.045
les-0.044
Token girl
Token ID2576
Feature activation+3.36e-02

Pos logit contributions
ache+0.054
 badly+0.051
 spe+0.048
 severe+0.047
 gen+0.047
Neg logit contributions
ashes-0.036
olls-0.035
ips-0.035
 recess-0.033
les-0.033
Token was
Token ID373
Feature activation+4.08e-02

Pos logit contributions
ache+0.072
 badly+0.069
Mill+0.066
 severe+0.066
 mercy+0.066
Neg logit contributions
les-0.041
ashes-0.038
 scores-0.037
ops-0.036
ips-0.036
Token very
Token ID845
Feature activation+3.62e-02

Pos logit contributions
ache+0.077
 extingu+0.072
comb+0.072
Mill+0.069
 spe+0.068
Neg logit contributions
ips-0.058
 day-0.057
 morning-0.055
ashes-0.054
 scores-0.052
Token happy
Token ID3772
Feature activation-1.93e-02

Pos logit contributions
ache+0.062
comb+0.056
 gen+0.055
 spe+0.055
Am+0.054
Neg logit contributions
ashes-0.064
 scores-0.056
 day-0.056
 recess-0.055
ips-0.055
Token.
Token ID13
Feature activation-9.99e-03

Pos logit contributions
ashes+0.031
ips+0.030
olls+0.030
 recess+0.029
les+0.028
Neg logit contributions
ache-0.037
 badly-0.034
 spe-0.032
 severe-0.032
 gen-0.031
Token She
Token ID1375
Feature activation-2.30e-03

Pos logit contributions
ashes+0.018
ips+0.017
olls+0.017
 recess+0.017
les+0.017
Neg logit contributions
ache-0.017
 badly-0.016
 spe-0.015
Mill-0.014
 severe-0.014
Token shouted
Token ID17293
Feature activation-4.92e-03

Pos logit contributions
ashes+0.003
les+0.003
olls+0.003
 scores+0.003
ips+0.003
Neg logit contributions
ache-0.005
 badly-0.004
 severe-0.004
 mercy-0.004
 gen-0.004
Token was
Token ID373
Feature activation+3.79e-02

Pos logit contributions
olls+0.025
ashes+0.024
 recess+0.024
ips+0.024
olphins+0.022
Neg logit contributions
 gen-0.012
ache-0.012
 spe-0.012
bul-0.010
 badly-0.010
Token warm
Token ID5814
Feature activation-2.88e-02

Pos logit contributions
ache+0.062
 badly+0.056
 severe+0.052
 spe+0.052
 gen+0.051
Neg logit contributions
ashes-0.070
ips-0.069
olls-0.068
 recess-0.066
les-0.066
Token and
Token ID290
Feature activation+8.23e-03

Pos logit contributions
olls+0.055
ashes+0.055
ips+0.054
 recess+0.054
 scores+0.053
Neg logit contributions
ache-0.044
 badly-0.042
 spe-0.039
 gen-0.037
Mill-0.036
Token the
Token ID262
Feature activation-4.33e-03

Pos logit contributions
ache+0.012
 spe+0.012
 badly+0.012
 severe+0.011
Mill+0.011
Neg logit contributions
ashes-0.016
olls-0.016
ips-0.016
 recess-0.015
les-0.015
Token water
Token ID1660
Feature activation-7.23e-03

Pos logit contributions
olls+0.009
ips+0.008
ops+0.008
ashes+0.007
ash+0.007
Neg logit contributions
 spe-0.007
 ow-0.006
 gen-0.006
 re-0.006
 faint-0.006
Token was
Token ID373
Feature activation+4.65e-02

Pos logit contributions
olls+0.016
 recess+0.016
ips+0.016
ashes+0.015
olphins+0.014
Neg logit contributions
ache-0.009
 spe-0.008
 gen-0.008
 badly-0.008
 wil-0.007
Token cool
Token ID3608
Feature activation-2.97e-02

Pos logit contributions
ache+0.082
 badly+0.073
 mercy+0.069
 gen+0.069
 severe+0.069
Neg logit contributions
ashes-0.079
ips-0.077
 recess-0.074
olls-0.074
les-0.074
Token,
Token ID11
Feature activation+2.22e-02

Pos logit contributions
olls+0.056
ips+0.055
 recess+0.055
ashes+0.054
olphins+0.053
Neg logit contributions
ache-0.047
 badly-0.046
 spe-0.041
 able-0.039
 severe-0.038
Token making
Token ID1642
Feature activation+8.19e-03

Pos logit contributions
ache+0.037
 badly+0.035
 spe+0.032
 severe+0.031
 gen+0.031
Neg logit contributions
ashes-0.040
olls-0.040
ips-0.039
 recess-0.038
les-0.037
Token it
Token ID340
Feature activation+1.09e-02

Pos logit contributions
ache+0.015
 badly+0.015
 spe+0.013
 gen+0.013
 severe+0.013
Neg logit contributions
olls-0.013
ips-0.013
ashes-0.013
 recess-0.012
olphins-0.012
Token the
Token ID262
Feature activation-5.35e-03

Pos logit contributions
ache+0.019
 badly+0.018
 spe+0.017
 severe+0.017
 gen+0.017
Neg logit contributions
ashes-0.018
olls-0.018
ips-0.018
 recess-0.017
olphins-0.017
Token
Token ID198
Feature activation+1.05e-02

Pos logit contributions
ashes+0.005
ips+0.004
olls+0.004
 recess+0.004
les+0.004
Neg logit contributions
ache-0.008
 badly-0.007
 spe-0.007
 severe-0.007
Mill-0.007
Token
Token ID198
Feature activation+1.63e-02

Pos logit contributions
ache+0.024
 badly+0.023
 spe+0.022
 severe+0.021
 mercy+0.021
Neg logit contributions
ashes-0.012
ips-0.012
olls-0.012
les-0.011
 recess-0.011
TokenS
Token ID50
Feature activation-3.49e-02

Pos logit contributions
ache+0.028
 badly+0.026
 spe+0.024
 severe+0.024
 gen+0.024
Neg logit contributions
ashes-0.029
ips-0.028
olls-0.028
 recess-0.027
les-0.027
Tokenara
Token ID3301
Feature activation+1.34e-03

Pos logit contributions
ashes+0.043
olls+0.039
 recess+0.039
asher+0.039
ips+0.038
Neg logit contributions
ache-0.080
 badly-0.072
 gen-0.069
Am-0.068
 spe-0.067
Token said
Token ID531
Feature activation+2.03e-02

Pos logit contributions
ache+0.003
 badly+0.003
 severe+0.002
 spe+0.002
Mill+0.002
Neg logit contributions
ashes-0.002
les-0.002
ips-0.002
olls-0.002
ops-0.002
Token,
Token ID11
Feature activation+4.52e-02

Pos logit contributions
ache+0.047
 severe+0.045
Mill+0.044
Sad+0.043
 badly+0.043
Neg logit contributions
olls-0.022
ips-0.022
ashes-0.021
les-0.020
 scores-0.020
Token "
Token ID366
Feature activation+9.51e-03

Pos logit contributions
ache+0.093
 badly+0.090
 severe+0.086
Mill+0.084
 mercy+0.084
Neg logit contributions
ips-0.057
ashes-0.057
olls-0.056
les-0.053
 recess-0.052
TokenThis
Token ID1212
Feature activation-2.81e-02

Pos logit contributions
ache+0.019
 badly+0.018
 spe+0.017
 severe+0.016
 gen+0.016
Neg logit contributions
ashes-0.015
ips-0.014
olls-0.014
 recess-0.013
les-0.013
Token is
Token ID318
Feature activation+2.42e-02

Pos logit contributions
ashes+0.040
ips+0.036
asher+0.034
olls+0.034
 recess+0.034
Neg logit contributions
ache-0.062
 gen-0.057
 badly-0.057
 spe-0.054
Am-0.054
Token a
Token ID257
Feature activation+1.59e-02

Pos logit contributions
ache+0.045
 badly+0.042
Mill+0.041
 severe+0.040
Sad+0.040
Neg logit contributions
 scores-0.036
olls-0.035
 Win-0.035
 morning-0.035
 recess-0.034
Token book
Token ID1492
Feature activation+1.13e-02

Pos logit contributions
ache+0.029
 badly+0.028
 severe+0.026
Mill+0.026
Sad+0.025
Neg logit contributions
 scores-0.024
 recess-0.024
olls-0.024
ashes-0.023
 day-0.023
Token Tom
Token ID4186
Feature activation-2.79e-03

Pos logit contributions
ashes+0.018
olls+0.017
ips+0.017
 recess+0.016
les+0.016
Neg logit contributions
ache-0.038
 badly-0.036
 spe-0.034
 severe-0.034
 gen-0.034
Token and
Token ID290
Feature activation-1.83e-02

Pos logit contributions
ashes+0.004
ips+0.004
olls+0.004
les+0.004
 recess+0.004
Neg logit contributions
ache-0.005
 badly-0.005
 spe-0.005
 severe-0.005
 gen-0.005
Token Lily
Token ID20037
Feature activation-7.34e-03

Pos logit contributions
ashes+0.027
ips+0.027
olls+0.026
les+0.025
olphins+0.025
Neg logit contributions
ache-0.036
 badly-0.034
 spe-0.033
 severe-0.032
 gen-0.032
Token asked
Token ID1965
Feature activation+1.90e-02

Pos logit contributions
ashes+0.010
olls+0.009
les+0.009
ips+0.009
 scores+0.009
Neg logit contributions
ache-0.015
 badly-0.015
Mill-0.014
 severe-0.014
 gen-0.014
Token their
Token ID511
Feature activation+2.23e-02

Pos logit contributions
ache+0.045
 badly+0.039
 severe+0.039
 spe+0.039
Sad+0.039
Neg logit contributions
olls-0.023
ashes-0.021
 recess-0.021
ips-0.021
olphins-0.021
Token mom
Token ID1995
Feature activation+6.10e-02

Pos logit contributions
ache+0.040
 badly+0.037
Mill+0.035
 spe+0.035
 severe+0.034
Neg logit contributions
ashes-0.038
 recess-0.036
olls-0.036
ips-0.035
 scores-0.035
Token if
Token ID611
Feature activation+1.90e-02

Pos logit contributions
ache+0.112
 badly+0.106
 spe+0.104
Mill+0.101
 severe+0.099
Neg logit contributions
olls-0.097
ashes-0.097
ips-0.093
les-0.092
olphins-0.092
Token they
Token ID484
Feature activation-3.97e-02

Pos logit contributions
ache+0.043
 badly+0.040
 spe+0.038
 severe+0.038
Sad+0.037
Neg logit contributions
ashes-0.022
olls-0.022
 recess-0.021
ips-0.021
olphins-0.021
Token could
Token ID714
Feature activation+2.40e-03

Pos logit contributions
ashes+0.057
olls+0.055
ips+0.053
les+0.052
 recess+0.052
Neg logit contributions
ache-0.080
 badly-0.076
Mill-0.071
 severe-0.071
 spe-0.071
Token go
Token ID467
Feature activation-5.73e-03

Pos logit contributions
ache+0.006
 badly+0.005
 severe+0.005
 spe+0.005
 gen+0.005
Neg logit contributions
ashes-0.003
ips-0.003
olls-0.003
 recess-0.002
olphins-0.002
Token outside
Token ID2354
Feature activation-5.36e-03

Pos logit contributions
ashes+0.009
ips+0.009
olls+0.009
 recess+0.008
les+0.008
Neg logit contributions
ache-0.011
 badly-0.010
 spe-0.010
 severe-0.010
 gen-0.010
Token thought
Token ID1807
Feature activation-9.63e-03

Pos logit contributions
ache+0.021
 badly+0.020
 spe+0.019
 severe+0.018
 gen+0.018
Neg logit contributions
ashes-0.017
olls-0.016
ips-0.016
les-0.016
 recess-0.015
Token about
Token ID546
Feature activation+7.37e-03

Pos logit contributions
ashes+0.016
ips+0.016
olls+0.016
les+0.015
 recess+0.015
Neg logit contributions
ache-0.017
 badly-0.016
 spe-0.015
 severe-0.015
Mill-0.015
Token it
Token ID340
Feature activation-1.41e-02

Pos logit contributions
ache+0.017
 badly+0.015
 spe+0.014
 severe+0.014
Mill+0.014
Neg logit contributions
ips-0.009
ashes-0.009
olls-0.009
 recess-0.009
 scores-0.008
Token and
Token ID290
Feature activation-1.21e-02

Pos logit contributions
ashes+0.021
olls+0.020
ips+0.020
 recess+0.019
les+0.019
Neg logit contributions
ache-0.028
 badly-0.026
 spe-0.025
 severe-0.024
 gen-0.024
Token said
Token ID531
Feature activation+3.85e-02

Pos logit contributions
ashes+0.019
olls+0.018
ips+0.018
les+0.018
 recess+0.017
Neg logit contributions
ache-0.023
 badly-0.022
 spe-0.020
 severe-0.020
 gen-0.020
Token,
Token ID11
Feature activation+4.51e-02

Pos logit contributions
ache+0.079
 severe+0.071
Mill+0.070
 badly+0.070
 spe+0.069
Neg logit contributions
olls-0.053
ashes-0.052
ips-0.051
 scores-0.049
les-0.048
Token "
Token ID366
Feature activation+8.33e-03

Pos logit contributions
ache+0.080
 badly+0.075
 spe+0.069
 severe+0.068
 gen+0.068
Neg logit contributions
ashes-0.077
ips-0.075
olls-0.075
 recess-0.072
les-0.071
TokenYou
Token ID1639
Feature activation-2.41e-02

Pos logit contributions
ache+0.016
 badly+0.015
Mill+0.014
 spe+0.014
Sad+0.014
Neg logit contributions
ashes-0.013
ips-0.013
olls-0.013
 recess-0.013
les-0.012
Token're
Token ID821
Feature activation+1.20e-02

Pos logit contributions
ashes+0.029
ips+0.028
olls+0.028
 recess+0.027
les+0.026
Neg logit contributions
ache-0.056
 badly-0.053
 spe-0.050
 severe-0.049
 gen-0.049
Token right
Token ID826
Feature activation-1.49e-02

Pos logit contributions
ache+0.025
 badly+0.023
 spe+0.022
 severe+0.021
 gen+0.021
Neg logit contributions
ashes-0.017
ips-0.017
olls-0.016
 recess-0.016
 scores-0.015
Token,
Token ID11
Feature activation+3.38e-02

Pos logit contributions
olls+0.019
ips+0.019
ashes+0.019
 recess+0.018
olphins+0.018
Neg logit contributions
ache-0.031
 badly-0.028
 spe-0.028
 severe-0.028
Mill-0.028
Token I
Token ID314
Feature activation-3.48e-02

Pos logit contributions
ashes+0.003
ips+0.003
olls+0.003
 recess+0.003
les+0.003
Neg logit contributions
ache-0.006
 badly-0.005
 spe-0.005
 gen-0.005
 severe-0.005
Token want
Token ID765
Feature activation-2.41e-02

Pos logit contributions
ips+0.057
ashes+0.055
olls+0.054
 recess+0.053
olphins+0.052
Neg logit contributions
ache-0.064
 badly-0.061
 spe-0.058
 gen-0.056
 severe-0.054
Token to
Token ID284
Feature activation+1.61e-02

Pos logit contributions
ashes+0.043
ips+0.042
olls+0.042
 recess+0.040
olphins+0.039
Neg logit contributions
ache-0.041
 badly-0.039
 spe-0.036
 gen-0.035
Mill-0.035
Token own
Token ID898
Feature activation-1.73e-02

Pos logit contributions
ache+0.035
 badly+0.032
 severe+0.031
 spe+0.030
 gen+0.030
Neg logit contributions
ashes-0.021
olls-0.021
ips-0.020
 recess-0.020
les-0.019
Token it
Token ID340
Feature activation-1.03e-02

Pos logit contributions
ashes+0.023
ips+0.023
olls+0.022
 recess+0.021
les+0.021
Neg logit contributions
ache-0.037
 badly-0.035
 spe-0.033
 gen-0.033
 severe-0.032
Token."
Token ID526
Feature activation+1.02e-03

Pos logit contributions
ashes+0.015
ips+0.014
olls+0.014
 recess+0.014
les+0.014
Neg logit contributions
ache-0.021
 badly-0.020
 spe-0.018
 gen-0.018
 severe-0.018
Token
Token ID198
Feature activation+9.03e-03

Pos logit contributions
 badly+0.001
Mill+0.001
ache+0.001
Her+0.001
 Jean+0.001
Neg logit contributions
les-0.002
ashes-0.002
asher-0.002
olls-0.002
olphins-0.002
Token
Token ID198
Feature activation+2.31e-02

Pos logit contributions
ache+0.016
 badly+0.015
Mill+0.014
Am+0.014
Sad+0.014
Neg logit contributions
ashes-0.015
olls-0.015
ips-0.014
 recess-0.014
asher-0.014
Token"
Token ID1
Feature activation+2.08e-02

Pos logit contributions
 badly+0.039
ache+0.039
Mill+0.035
Am+0.035
Sad+0.034
Neg logit contributions
ashes-0.039
ips-0.039
les-0.038
 recess-0.037
asher-0.037
TokenNo
Token ID2949
Feature activation-1.98e-02

Pos logit contributions
ache+0.041
 badly+0.039
 spe+0.037
Mill+0.036
 gen+0.036
Neg logit contributions
ashes-0.031
ips-0.030
olls-0.030
les-0.029
 recess-0.029
Token,
Token ID11
Feature activation+3.27e-02

Pos logit contributions
ashes+0.034
ips+0.033
olls+0.033
 recess+0.031
les+0.031
Neg logit contributions
ache-0.035
 badly-0.034
 spe-0.030
 gen-0.030
 mercy-0.030
Token to
Token ID284
Feature activation+6.32e-03

Pos logit contributions
ashes+0.023
olls+0.022
ips+0.022
les+0.022
 scores+0.021
Neg logit contributions
ache-0.023
 badly-0.022
 spe-0.021
 gen-0.020
Mill-0.020
Token take
Token ID1011
Feature activation-2.94e-02

Pos logit contributions
ache+0.013
 badly+0.012
 spe+0.011
 severe+0.011
 gen+0.011
Neg logit contributions
ashes-0.009
olls-0.009
ips-0.009
 recess-0.009
 scores-0.008
Token something
Token ID1223
Feature activation+3.25e-02

Pos logit contributions
ashes+0.044
ips+0.044
olls+0.043
 recess+0.041
olphins+0.041
Neg logit contributions
ache-0.057
 badly-0.055
 severe-0.050
 spe-0.050
 mercy-0.049
Token that
Token ID326
Feature activation-2.68e-02

Pos logit contributions
ache+0.054
 spe+0.048
 badly+0.048
Sad+0.048
 gen+0.048
Neg logit contributions
ashes-0.058
olls-0.055
les-0.054
 scores-0.053
ips-0.053
Token doesn
Token ID1595
Feature activation-3.34e-02

Pos logit contributions
ips+0.041
 recess+0.039
ashes+0.039
olls+0.038
acking+0.036
Neg logit contributions
ache-0.053
 badly-0.050
 spe-0.047
 severe-0.046
 gen-0.046
Token't
Token ID470
Feature activation+5.12e-03

Pos logit contributions
ashes+0.054
olls+0.052
ips+0.051
 recess+0.051
olphins+0.049
Neg logit contributions
ache-0.064
 badly-0.062
 severe-0.056
 spe-0.053
 gen-0.053
Token belong
Token ID5594
Feature activation-1.93e-02

Pos logit contributions
ache+0.010
 badly+0.009
 severe+0.009
 spe+0.009
 gen+0.008
Neg logit contributions
ips-0.008
ashes-0.008
olls-0.008
 recess-0.008
les-0.007
Token to
Token ID284
Feature activation+1.63e-02

Pos logit contributions
ashes+0.035
ips+0.034
olls+0.034
 recess+0.033
les+0.033
Neg logit contributions
ache-0.032
 badly-0.030
 spe-0.027
 severe-0.027
 gen-0.026
Token you
Token ID345
Feature activation-2.65e-03

Pos logit contributions
ache+0.038
 badly+0.037
 severe+0.034
 spe+0.034
 mercy+0.034
Neg logit contributions
ashes-0.019
ips-0.018
olls-0.017
 recess-0.016
les-0.016
Token.
Token ID13
Feature activation-1.29e-02

Pos logit contributions
ashes+0.004
ips+0.004
olls+0.004
 recess+0.004
les+0.004
Neg logit contributions
ache-0.005
 badly-0.005
 spe-0.004
 severe-0.004
 gen-0.004
Token<|endoftext|>
Token ID50256
Feature activation-6.08e-02

Pos logit contributions
ashes+0.018
olls+0.017
ips+0.017
 recess+0.017
les+0.016
Neg logit contributions
ache-0.027
 badly-0.026
 spe-0.024
 gen-0.024
Mill-0.024
Token just
Token ID655
Feature activation-1.28e-02

Pos logit contributions
ache+0.056
 badly+0.050
 severe+0.048
 mercy+0.048
 spe+0.048
Neg logit contributions
ips-0.043
 recess-0.042
ashes-0.041
les-0.041
 morning-0.040
Token the
Token ID262
Feature activation-1.11e-03

Pos logit contributions
ashes+0.022
ips+0.021
olls+0.021
 recess+0.021
les+0.020
Neg logit contributions
ache-0.023
 badly-0.021
 severe-0.019
 spe-0.019
 gen-0.019
Token way
Token ID835
Feature activation-1.66e-03

Pos logit contributions
ashes+0.002
olls+0.002
ips+0.002
 recess+0.002
les+0.002
Neg logit contributions
ache-0.002
 badly-0.002
 spe-0.002
 severe-0.002
 gen-0.002
Token she
Token ID673
Feature activation-1.30e-02

Pos logit contributions
ashes+0.003
ips+0.003
olls+0.003
 recess+0.003
olphins+0.003
Neg logit contributions
ache-0.003
 badly-0.003
 spe-0.002
 severe-0.002
Mill-0.002
Token wanted
Token ID2227
Feature activation-6.40e-03

Pos logit contributions
ashes+0.019
ips+0.019
olls+0.019
les+0.018
 recess+0.018
Neg logit contributions
ache-0.026
 badly-0.024
 severe-0.022
 spe-0.022
 gen-0.022
Token it
Token ID340
Feature activation-1.30e-03

Pos logit contributions
ashes+0.010
ips+0.010
olls+0.010
 recess+0.009
les+0.009
Neg logit contributions
ache-0.012
 badly-0.011
 spe-0.011
 severe-0.011
 gen-0.010
Token.
Token ID13
Feature activation-1.07e-02

Pos logit contributions
ashes+0.002
ips+0.002
olls+0.002
 recess+0.002
les+0.002
Neg logit contributions
ache-0.002
 badly-0.002
 spe-0.002
 gen-0.002
 severe-0.002
Token
Token ID198
Feature activation+1.28e-02

Pos logit contributions
ashes+0.017
ips+0.016
olls+0.016
les+0.015
 recess+0.015
Neg logit contributions
ache-0.020
 badly-0.019
Mill-0.018
 spe-0.018
 gen-0.018
Token
Token ID198
Feature activation+2.13e-02

Pos logit contributions
ache+0.027
 badly+0.025
 spe+0.024
 severe+0.023
 gen+0.023
Neg logit contributions
ashes-0.018
ips-0.017
olls-0.017
 recess-0.016
les-0.016
TokenThe
Token ID464
Feature activation+2.07e-02

Pos logit contributions
ache+0.033
 badly+0.030
 spe+0.028
 severe+0.027
 gen+0.027
Neg logit contributions
ashes-0.042
olls-0.041
ips-0.041
 recess-0.040
les-0.039
Token little
Token ID1310
Feature activation+7.14e-03

Pos logit contributions
ache+0.039
 badly+0.036
 spe+0.034
 severe+0.034
 gen+0.033
Neg logit contributions
ashes-0.033
ips-0.032
olls-0.032
 recess-0.031
les-0.031
Token Lily
Token ID20037
Feature activation+8.28e-03

Pos logit contributions
ache+0.076
 badly+0.069
 severe+0.066
 spe+0.065
 gen+0.065
Neg logit contributions
ashes-0.053
olls-0.053
ips-0.051
 scores-0.049
 recess-0.049
Token.
Token ID13
Feature activation-6.15e-03

Pos logit contributions
ache+0.016
 badly+0.015
 spe+0.014
 severe+0.014
 gen+0.014
Neg logit contributions
ashes-0.013
olls-0.012
ips-0.012
les-0.012
 recess-0.012
Token Sometimes
Token ID8975
Feature activation-1.22e-02

Pos logit contributions
ashes+0.008
les+0.007
 recess+0.007
ips+0.007
olls+0.007
Neg logit contributions
ache-0.013
 badly-0.013
 spe-0.012
Sad-0.012
 gen-0.012
Token,
Token ID11
Feature activation+2.56e-02

Pos logit contributions
ashes+0.016
ips+0.016
olls+0.016
 recess+0.015
les+0.015
Neg logit contributions
ache-0.026
 badly-0.025
 spe-0.023
 gen-0.023
 severe-0.023
Token a
Token ID257
Feature activation+2.36e-02

Pos logit contributions
ache+0.056
 badly+0.053
 spe+0.050
 gen+0.050
 severe+0.049
Neg logit contributions
ashes-0.033
ips-0.032
olls-0.031
 recess-0.030
les-0.030
Token little
Token ID1310
Feature activation+5.74e-03

Pos logit contributions
ache+0.042
 badly+0.040
Mill+0.038
 severe+0.038
 mercy+0.036
Neg logit contributions
ashes-0.036
 scores-0.036
 recess-0.035
olls-0.035
 day-0.035
Token gift
Token ID6979
Feature activation+2.75e-03

Pos logit contributions
ache+0.013
 badly+0.012
 severe+0.011
Mill+0.011
Am+0.011
Neg logit contributions
ashes-0.007
olls-0.007
 scores-0.007
ips-0.007
 recess-0.006
Token can
Token ID460
Feature activation+7.05e-03

Pos logit contributions
ache+0.006
 badly+0.006
 gen+0.005
 spe+0.005
 severe+0.005
Neg logit contributions
ashes-0.004
ips-0.003
olls-0.003
 recess-0.003
les-0.003
Token make
Token ID787
Feature activation+4.23e-04

Pos logit contributions
ache+0.014
 badly+0.013
 spe+0.012
 severe+0.012
Mill+0.012
Neg logit contributions
ashes-0.010
olls-0.010
ips-0.010
les-0.010
 recess-0.010
Token someone
Token ID2130
Feature activation+4.35e-02

Pos logit contributions
ache+0.001
 badly+0.001
 spe+0.001
 severe+0.001
 gen+0.001
Neg logit contributions
ashes-0.000
ips-0.000
olls-0.000
 recess-0.000
les-0.000
Token feel
Token ID1254
Feature activation+2.18e-02

Pos logit contributions
ache+0.066
 badly+0.062
Mill+0.060
Am+0.060
 severe+0.059
Neg logit contributions
ashes-0.081
les-0.077
 scores-0.077
olls-0.075
ips-0.074
Token give
Token ID1577
Feature activation-3.41e-02

Feature not active on prev token;
no predictions were affected.
Token my
Token ID616
Feature activation+1.51e-02

Pos logit contributions
ashes+0.039
olls+0.038
ips+0.038
les+0.036
 recess+0.036
Neg logit contributions
ache-0.079
 badly-0.074
 spe-0.071
 severe-0.070
 gen-0.070
Token re
Token ID302
Feature activation+1.11e-02

Pos logit contributions
ache+0.024
 badly+0.022
Mill+0.021
 severe+0.021
Sad+0.021
Neg logit contributions
ashes-0.027
olls-0.027
les-0.027
ips-0.026
olphins-0.026
Tokenind
Token ID521
Feature activation+6.05e-04

Pos logit contributions
ache+0.017
 badly+0.016
 severe+0.015
 spe+0.015
Mill+0.015
Neg logit contributions
ips-0.020
ashes-0.020
les-0.020
olls-0.020
oom-0.019
Tokeneer
Token ID28153
Feature activation+2.81e-02

Pos logit contributions
ache+0.001
 badly+0.001
 spe+0.001
 severe+0.001
 gen+0.001
Neg logit contributions
ashes-0.001
ips-0.001
olls-0.001
 recess-0.001
les-0.001
Token some
Token ID617
Feature activation-5.56e-03

Pos logit contributions
ache+0.046
 badly+0.043
 spe+0.040
 severe+0.039
 gen+0.039
Neg logit contributions
ashes-0.051
ips-0.050
olls-0.049
 recess-0.048
les-0.047
Token carrots
Token ID34397
Feature activation-1.60e-02

Pos logit contributions
ashes+0.008
olls+0.008
ips+0.008
les+0.008
 recess+0.008
Neg logit contributions
ache-0.011
 badly-0.010
Mill-0.010
 spe-0.010
 severe-0.010
Token and
Token ID290
Feature activation-8.17e-03

Pos logit contributions
ashes+0.028
ips+0.027
olls+0.027
 recess+0.027
les+0.026
Neg logit contributions
ache-0.028
 badly-0.026
 severe-0.024
 spe-0.023
 gen-0.023
Token water
Token ID1660
Feature activation-2.12e-02

Pos logit contributions
ashes+0.012
olls+0.011
les+0.011
ips+0.011
 scores+0.011
Neg logit contributions
ache-0.016
 badly-0.016
Mill-0.015
 severe-0.014
Sad-0.014
Token.
Token ID13
Feature activation-1.52e-02

Pos logit contributions
ashes+0.036
 recess+0.036
ips+0.036
olls+0.035
 scores+0.033
Neg logit contributions
ache-0.037
 badly-0.034
 spe-0.031
 gen-0.030
 severe-0.030
Token They
Token ID1119
Feature activation-2.94e-02

Pos logit contributions
ashes+0.018
ips+0.017
olls+0.017
 recess+0.016
les+0.016
Neg logit contributions
ache-0.035
 badly-0.033
 spe-0.032
 severe-0.031
 gen-0.031
Token,
Token ID11
Feature activation-2.00e-04

Pos logit contributions
ashes+0.036
olls+0.035
ips+0.035
 recess+0.033
les+0.033
Neg logit contributions
ache-0.046
 badly-0.043
 spe-0.040
 severe-0.040
 gen-0.040
Token two
Token ID734
Feature activation-4.07e-03

Pos logit contributions
ashes+0.000
olls+0.000
ips+0.000
 recess+0.000
les+0.000
Neg logit contributions
ache-0.000
 severe-0.000
 badly-0.000
 mercy-0.000
 spe-0.000
Token friends
Token ID2460
Feature activation+4.89e-03

Pos logit contributions
ashes+0.005
ips+0.005
olls+0.005
les+0.005
 recess+0.005
Neg logit contributions
ache-0.009
 badly-0.008
 spe-0.008
 severe-0.008
 gen-0.008
Token named
Token ID3706
Feature activation-8.19e-03

Pos logit contributions
ache+0.009
 badly+0.008
 spe+0.008
Mill+0.007
 severe+0.007
Neg logit contributions
ashes-0.008
ips-0.008
olls-0.008
olphins-0.008
les-0.008
Token John
Token ID1757
Feature activation-5.23e-03

Pos logit contributions
ips+0.013
ashes+0.013
les+0.013
olls+0.013
olphins+0.012
Neg logit contributions
ache-0.014
 badly-0.014
Am-0.013
Mill-0.013
 spe-0.013
Token and
Token ID290
Feature activation-2.01e-02

Pos logit contributions
ashes+0.009
olls+0.009
ips+0.009
 recess+0.009
olphins+0.009
Neg logit contributions
ache-0.009
 badly-0.008
 spe-0.008
 severe-0.008
Mill-0.008
Token Sarah
Token ID10490
Feature activation+9.69e-03

Pos logit contributions
olls+0.028
ashes+0.028
 recess+0.028
ips+0.027
olphins+0.026
Neg logit contributions
ache-0.041
 badly-0.038
 spe-0.036
 severe-0.036
 gen-0.035
Token were
Token ID547
Feature activation+3.22e-02

Pos logit contributions
ache+0.018
 badly+0.017
 spe+0.016
 severe+0.016
 gen+0.015
Neg logit contributions
ashes-0.015
ips-0.015
olls-0.015
 recess-0.014
olphins-0.014
Token playing
Token ID2712
Feature activation-2.86e-02

Pos logit contributions
ache+0.065
 badly+0.063
 spe+0.058
 severe+0.057
Mill+0.057
Neg logit contributions
ashes-0.047
olls-0.045
ips-0.044
les-0.043
olphins-0.043
Token in
Token ID287
Feature activation+1.78e-03

Pos logit contributions
olls+0.051
ips+0.050
ashes+0.050
olphins+0.050
les+0.050
Neg logit contributions
 badly-0.044
ache-0.040
 who-0.038
 whose-0.038
 able-0.038
Token the
Token ID262
Feature activation-1.38e-02

Pos logit contributions
 badly+0.003
ache+0.003
 spe+0.003
Mill+0.003
Am+0.003
Neg logit contributions
ashes-0.003
olls-0.003
ips-0.003
les-0.003
olphins-0.003
Token Tom
Token ID4186
Feature activation-2.72e-04

Pos logit contributions
ashes+0.042
asher+0.041
les+0.040
olls+0.039
acked+0.039
Neg logit contributions
ache-0.051
 badly-0.048
 mercy-0.047
 severe-0.043
Am-0.042
Token look
Token ID804
Feature activation-1.92e-02

Pos logit contributions
ips+0.000
ashes+0.000
olls+0.000
 recess+0.000
asher+0.000
Neg logit contributions
ache-0.001
 badly-0.000
 mercy-0.000
 gen-0.000
 severe-0.000
Token at
Token ID379
Feature activation-2.15e-03

Pos logit contributions
ashes+0.025
ips+0.025
olls+0.024
 recess+0.024
olphins+0.023
Neg logit contributions
ache-0.041
 badly-0.039
 severe-0.036
 spe-0.036
 gen-0.035
Token Ben
Token ID3932
Feature activation+2.34e-02

Pos logit contributions
ashes+0.003
ips+0.003
olls+0.003
 recess+0.003
les+0.003
Neg logit contributions
ache-0.004
 badly-0.004
 spe-0.004
 severe-0.004
 gen-0.004
Token.
Token ID13
Feature activation-1.39e-02

Pos logit contributions
ache+0.043
 badly+0.041
 severe+0.037
 spe+0.036
 gen+0.036
Neg logit contributions
ashes-0.039
olls-0.038
ips-0.038
 recess-0.037
olphins-0.036
Token They
Token ID1119
Feature activation-2.55e-02

Pos logit contributions
les+0.018
ips+0.018
olls+0.017
ops+0.017
olphins+0.016
Neg logit contributions
ache-0.028
 badly-0.027
 spe-0.026
 gen-0.025
 mercy-0.024
Token are
Token ID389
Feature activation+2.08e-02

Pos logit contributions
ashes+0.040
ips+0.039
olls+0.039
 recess+0.038
les+0.036
Neg logit contributions
ache-0.049
 badly-0.046
 spe-0.042
 gen-0.042
 severe-0.042
Token still
Token ID991
Feature activation-3.00e-03

Pos logit contributions
ache+0.039
 spe+0.035
comb+0.034
Mill+0.034
Am+0.033
Neg logit contributions
ips-0.034
ashes-0.032
 players-0.030
 scores-0.030
 recess-0.029
Token sad
Token ID6507
Feature activation-2.23e-02

Pos logit contributions
ashes+0.006
ips+0.006
olls+0.006
 recess+0.005
les+0.005
Neg logit contributions
ache-0.005
 badly-0.004
 spe-0.004
 severe-0.004
 gen-0.004
Token.
Token ID13
Feature activation-1.08e-02

Pos logit contributions
ashes+0.037
ips+0.037
olls+0.037
 recess+0.035
olphins+0.035
Neg logit contributions
ache-0.040
 badly-0.038
 spe-0.034
 severe-0.034
 gen-0.034
Token They
Token ID1119
Feature activation-2.27e-02

Pos logit contributions
ips+0.013
les+0.013
olls+0.013
ashes+0.012
ops+0.012
Neg logit contributions
ache-0.023
 badly-0.023
 spe-0.021
Mill-0.021
Am-0.021
TokenHer
Token ID9360
Feature activation+1.13e-02

Pos logit contributions
ache+0.026
 badly+0.023
 severe+0.020
Mill+0.020
Am+0.019
Neg logit contributions
ashes-0.067
ips-0.066
olls-0.065
les-0.064
 recess-0.063
Token mom
Token ID1995
Feature activation+3.72e-02

Pos logit contributions
ache+0.022
 badly+0.021
 spe+0.019
Mill+0.019
 severe+0.019
Neg logit contributions
ashes-0.017
ips-0.017
olls-0.017
 recess-0.017
les-0.016
Token asked
Token ID1965
Feature activation+2.13e-02

Pos logit contributions
ache+0.085
 badly+0.084
 spe+0.082
 reality+0.079
 severe+0.078
Neg logit contributions
les-0.041
acking-0.034
olls-0.033
ops-0.033
ips-0.033
Token her
Token ID607
Feature activation+3.55e-02

Pos logit contributions
ache+0.040
 badly+0.035
 spe+0.035
 gen+0.034
 severe+0.034
Neg logit contributions
olls-0.035
ashes-0.034
ips-0.034
 recess-0.034
les-0.033
Token why
Token ID1521
Feature activation+1.62e-02

Pos logit contributions
 spe+0.060
ache+0.060
 badly+0.055
Mill+0.053
Sad+0.053
Neg logit contributions
olls-0.061
ashes-0.057
olphins-0.057
les-0.055
 scores-0.054
Token she
Token ID673
Feature activation-1.87e-02

Pos logit contributions
ache+0.028
 badly+0.026
 severe+0.024
 spe+0.024
 gen+0.023
Neg logit contributions
ashes-0.029
olls-0.028
ips-0.028
 recess-0.027
les-0.027
Token was
Token ID373
Feature activation+3.48e-02

Pos logit contributions
ashes+0.027
olls+0.026
les+0.026
ips+0.026
 scores+0.025
Neg logit contributions
ache-0.037
 badly-0.035
 spe-0.033
 severe-0.033
Mill-0.033
Token scared
Token ID12008
Feature activation-1.29e-02

Pos logit contributions
ache+0.057
 spe+0.055
 gen+0.051
 mercy+0.050
comb+0.050
Neg logit contributions
ashes-0.056
ips-0.056
 Win-0.055
 recess-0.053
 players-0.053
Token.
Token ID13
Feature activation-3.39e-03

Pos logit contributions
ashes+0.017
ips+0.017
olls+0.017
les+0.017
 recess+0.016
Neg logit contributions
ache-0.027
 spe-0.025
 gen-0.024
 badly-0.024
 severe-0.024
Token Lily
Token ID20037
Feature activation+7.70e-04

Pos logit contributions
ashes+0.004
olls+0.004
ips+0.004
 recess+0.004
 scores+0.004
Neg logit contributions
ache-0.008
 badly-0.007
 spe-0.007
 severe-0.007
 gen-0.007
Token said
Token ID531
Feature activation+3.35e-02

Pos logit contributions
ache+0.002
 spe+0.002
 badly+0.001
 gen+0.001
Mill+0.001
Neg logit contributions
les-0.001
olls-0.001
ops-0.001
ashes-0.001
ips-0.001
Token the
Token ID262
Feature activation+2.50e-02

Pos logit contributions
 scores+0.005
 players+0.005
les+0.005
 scored+0.005
 recess+0.005
Neg logit contributions
ache-0.011
 badly-0.010
 spe-0.010
Sad-0.010
comb-0.010
Token lady
Token ID10846
Feature activation+4.70e-02

Pos logit contributions
ache+0.059
 badly+0.056
 spe+0.053
Mill+0.053
 gen+0.052
Neg logit contributions
ashes-0.029
olls-0.027
ips-0.027
 recess-0.026
olphins-0.025
Token said
Token ID531
Feature activation+3.53e-02

Pos logit contributions
ache+0.088
Mill+0.087
 prope+0.087
 spe+0.086
Sad+0.084
Neg logit contributions
les-0.066
ashes-0.058
 scores-0.058
 day-0.057
olls-0.055
Token she
Token ID673
Feature activation-1.65e-02

Pos logit contributions
ache+0.068
Am+0.064
Mill+0.064
Sad+0.063
 spe+0.062
Neg logit contributions
olls-0.046
ips-0.043
 scores-0.043
 recess-0.043
ops-0.043
Token would
Token ID561
Feature activation+4.53e-03

Pos logit contributions
ashes+0.024
olls+0.024
ips+0.023
les+0.023
ops+0.022
Neg logit contributions
ache-0.032
 badly-0.030
 spe-0.029
 gen-0.029
 severe-0.028
Token take
Token ID1011
Feature activation-1.93e-02

Pos logit contributions
ache+0.009
 badly+0.008
 spe+0.008
 severe+0.008
 gen+0.007
Neg logit contributions
ashes-0.007
olls-0.007
ips-0.007
 recess-0.006
les-0.006
Token care
Token ID1337
Feature activation+6.89e-03

Pos logit contributions
ashes+0.033
olls+0.032
ips+0.032
 recess+0.031
olphins+0.031
Neg logit contributions
ache-0.034
 badly-0.032
 spe-0.030
 severe-0.029
 gen-0.029
Token of
Token ID286
Feature activation+1.37e-02

Pos logit contributions
ache+0.015
 spe+0.014
 badly+0.013
 gen+0.013
Mill+0.013
Neg logit contributions
ashes-0.009
olls-0.009
ips-0.009
les-0.009
 recess-0.008
Token it
Token ID340
Feature activation+4.37e-03

Pos logit contributions
ache+0.028
 badly+0.025
 gen+0.024
 spe+0.024
 severe+0.024
Neg logit contributions
ashes-0.019
ips-0.019
olls-0.019
 recess-0.018
les-0.018
Token.
Token ID13
Feature activation-6.29e-03

Pos logit contributions
ache+0.010
 spe+0.009
 gen+0.009
Mill+0.009
 badly+0.008
Neg logit contributions
ashes-0.006
olls-0.005
ips-0.005
les-0.005
ops-0.005
Token She
Token ID1375
Feature activation-7.26e-03

Pos logit contributions
ashes+0.010
ips+0.010
olls+0.010
 recess+0.009
olphins+0.009
Neg logit contributions
ache-0.012
 badly-0.011
 spe-0.010
 severe-0.010
Mill-0.010
Token surprise
Token ID5975
Feature activation-1.53e-02

Pos logit contributions
 recess+0.022
 morning+0.021
 day+0.020
 scores+0.020
ips+0.020
Neg logit contributions
ache-0.032
 badly-0.029
Mill-0.028
 spe-0.027
 severe-0.027
Token,
Token ID11
Feature activation+1.72e-02

Pos logit contributions
ashes+0.023
olls+0.023
ips+0.023
 recess+0.022
les+0.022
Neg logit contributions
ache-0.030
 badly-0.028
 spe-0.026
 severe-0.026
 gen-0.026
Token it
Token ID340
Feature activation-3.59e-02

Pos logit contributions
ache+0.033
 badly+0.029
 spe+0.028
 severe+0.028
 gen+0.028
Neg logit contributions
olls-0.028
 recess-0.027
ashes-0.027
ips-0.026
 scores-0.025
Token was
Token ID373
Feature activation+3.26e-02

Pos logit contributions
ashes+0.050
les+0.050
olls+0.049
ips+0.049
 recess+0.048
Neg logit contributions
ache-0.073
 badly-0.068
 spe-0.063
 mercy-0.063
 severe-0.063
Token raining
Token ID43079
Feature activation-2.73e-02

Pos logit contributions
ache+0.072
 mercy+0.062
keys+0.059
Jean+0.057
 severe+0.057
Neg logit contributions
 morning-0.047
 day-0.047
 afternoon-0.043
 recess-0.043
 sun-0.041
Token!
Token ID0
Feature activation-1.56e-02

Pos logit contributions
ashes+0.039
ips+0.038
olls+0.038
les+0.036
 recess+0.036
Neg logit contributions
ache-0.056
 badly-0.051
 spe-0.049
 gen-0.049
 severe-0.049
Token
Token ID198
Feature activation+1.18e-03

Pos logit contributions
ashes+0.028
ips+0.027
asher+0.026
olphins+0.026
les+0.025
Neg logit contributions
ache-0.025
 badly-0.024
Sad-0.023
Am-0.022
Mill-0.022
Token
Token ID198
Feature activation+1.97e-02

Pos logit contributions
ache+0.003
 badly+0.002
 spe+0.002
 severe+0.002
 gen+0.002
Neg logit contributions
ashes-0.002
olls-0.001
ips-0.001
 recess-0.001
les-0.001
TokenRose
Token ID31087
Feature activation+1.08e-02

Pos logit contributions
ache+0.034
 badly+0.032
 severe+0.029
Am+0.029
Mill+0.029
Neg logit contributions
ashes-0.035
ips-0.033
olls-0.032
asher-0.032
olphins-0.032
Token grabbed
Token ID13176
Feature activation-5.83e-03

Pos logit contributions
ache+0.022
 badly+0.021
 spe+0.020
 gen+0.019
 mercy+0.019
Neg logit contributions
ashes-0.015
olls-0.015
les-0.015
ips-0.014
 recess-0.014
Token her
Token ID607
Feature activation-3.10e-03

Pos logit contributions
ashes+0.010
olls+0.010
ips+0.010
 recess+0.010
les+0.010
Neg logit contributions
ache-0.010
 badly-0.009
 gen-0.008
 spe-0.008
 severe-0.008
Token be
Token ID307
Feature activation+8.22e-03

Pos logit contributions
ache+0.036
 badly+0.033
 spe+0.031
 severe+0.031
 gen+0.031
Neg logit contributions
ashes-0.025
olls-0.023
ips-0.023
 recess-0.023
 scores-0.022
Token mindful
Token ID33798
Feature activation-1.45e-02

Pos logit contributions
ache+0.013
 spe+0.011
 gen+0.011
 badly+0.011
Am+0.011
Neg logit contributions
ashes-0.015
ips-0.015
 recess-0.014
olls-0.014
les-0.014
Token of
Token ID286
Feature activation+2.68e-02

Pos logit contributions
ashes+0.024
ips+0.024
olls+0.023
 recess+0.023
olphins+0.022
Neg logit contributions
ache-0.026
 badly-0.025
 severe-0.022
 spe-0.022
 gen-0.022
Token others
Token ID1854
Feature activation+1.63e-03

Pos logit contributions
ache+0.056
 badly+0.050
 spe+0.049
 gen+0.048
 severe+0.048
Neg logit contributions
ashes-0.037
ips-0.037
olls-0.036
 recess-0.036
 scores-0.035
Token.
Token ID13
Feature activation-1.73e-02

Pos logit contributions
ache+0.003
 badly+0.003
 spe+0.003
 severe+0.003
 gen+0.003
Neg logit contributions
ashes-0.003
olls-0.003
ips-0.003
 recess-0.002
les-0.002
Token<|endoftext|>
Token ID50256
Feature activation-5.96e-02

Pos logit contributions
ashes+0.025
olls+0.024
ips+0.024
les+0.023
 recess+0.023
Neg logit contributions
ache-0.034
 badly-0.033
Mill-0.031
 spe-0.031
Am-0.030
TokenOnce
Token ID7454
Feature activation-4.25e-02

Pos logit contributions
ashes+0.113
olls+0.105
asher+0.105
olphins+0.098
ashed+0.097
Neg logit contributions
 badly-0.087
Am-0.086
ache-0.084
Mill-0.083
 gen-0.082
Token upon
Token ID2402
Feature activation-1.09e-02

Pos logit contributions
ashes+0.050
olls+0.045
ips+0.044
 recess+0.041
asher+0.041
Neg logit contributions
 badly-0.099
ache-0.097
Mill-0.088
 severe-0.088
 spe-0.087
Token a
Token ID257
Feature activation-1.91e-02

Pos logit contributions
ashes+0.015
 recess+0.015
 players+0.015
 day+0.015
 morning+0.015
Neg logit contributions
ache-0.022
 spe-0.019
 gen-0.018
 severe-0.018
bul-0.018
Token time
Token ID640
Feature activation-2.92e-02

Pos logit contributions
ashes+0.012
ips+0.011
olls+0.010
les+0.010
 recess+0.010
Neg logit contributions
ache-0.054
 badly-0.051
 gen-0.050
 severe-0.049
 spe-0.049
Token,
Token ID11
Feature activation+1.43e-03

Pos logit contributions
ashes+0.042
ips+0.042
olls+0.042
 recess+0.040
olphins+0.039
Neg logit contributions
ache-0.059
 badly-0.054
 severe-0.052
 spe-0.052
 gen-0.051
Token feel
Token ID1254
Feature activation+9.86e-03

Pos logit contributions
ache+0.037
 badly+0.034
 spe+0.032
 gen+0.032
Mill+0.032
Neg logit contributions
ashes-0.044
olls-0.042
ips-0.042
les-0.041
 scores-0.040
Token comfortable
Token ID6792
Feature activation-2.48e-02

Pos logit contributions
ache+0.015
 badly+0.013
 spe+0.013
Am+0.013
 gen+0.013
Neg logit contributions
ashes-0.019
les-0.018
olls-0.018
ips-0.018
 recess-0.018
Token and
Token ID290
Feature activation+1.22e-02

Pos logit contributions
ashes+0.037
ips+0.036
olls+0.036
les+0.034
 recess+0.034
Neg logit contributions
ache-0.049
 badly-0.045
 spe-0.043
 severe-0.042
 gen-0.042
Token happy
Token ID3772
Feature activation-1.92e-02

Pos logit contributions
ache+0.017
 badly+0.016
 spe+0.015
 severe+0.014
 gen+0.014
Neg logit contributions
ashes-0.025
ips-0.024
olls-0.024
 recess-0.024
les-0.023
Token.
Token ID13
Feature activation-1.50e-02

Pos logit contributions
ashes+0.031
olls+0.030
ips+0.030
 recess+0.029
les+0.028
Neg logit contributions
ache-0.036
 badly-0.034
 spe-0.031
 severe-0.031
 gen-0.031
Token<|endoftext|>
Token ID50256
Feature activation-6.61e-02

Pos logit contributions
ashes+0.024
ips+0.024
olls+0.023
 recess+0.023
les+0.022
Neg logit contributions
ache-0.028
 badly-0.027
 severe-0.024
 spe-0.024
 gen-0.024
TokenOnce
Token ID7454
Feature activation-5.19e-02

Pos logit contributions
ashes+0.110
olls+0.107
ips+0.104
olphins+0.101
asher+0.100
Neg logit contributions
ache-0.117
 badly-0.113
 gen-0.104
 severe-0.103
 spe-0.103
Token upon
Token ID2402
Feature activation-2.22e-02

Pos logit contributions
ashes+0.061
olls+0.055
ips+0.054
asher+0.051
 scores+0.051
Neg logit contributions
 badly-0.119
ache-0.118
 severe-0.107
Mill-0.106
 gen-0.106
Token a
Token ID257
Feature activation-3.23e-02

Pos logit contributions
ashes+0.036
 recess+0.035
olls+0.035
ips+0.035
 day+0.034
Neg logit contributions
ache-0.040
 spe-0.035
 badly-0.034
 gen-0.033
 severe-0.033
Token time
Token ID640
Feature activation-3.49e-02

Pos logit contributions
ashes+0.025
ips+0.023
olls+0.023
 recess+0.021
les+0.021
Neg logit contributions
ache-0.088
 badly-0.083
 gen-0.080
 spe-0.080
 severe-0.079
Token,
Token ID11
Feature activation-5.99e-03

Pos logit contributions
ashes+0.055
olls+0.054
ips+0.054
 recess+0.051
les+0.051
Neg logit contributions
ache-0.066
 badly-0.062
 spe-0.058
 severe-0.057
 gen-0.057
Token enjoy
Token ID2883
Feature activation-6.37e-03

Pos logit contributions
ashes+0.019
olls+0.019
 recess+0.018
ips+0.018
 scores+0.018
Neg logit contributions
ache-0.028
 badly-0.025
Am-0.024
Mill-0.024
 severe-0.024
Token her
Token ID607
Feature activation-1.24e-02

Pos logit contributions
ips+0.010
 recess+0.010
ashes+0.009
olls+0.009
les+0.009
Neg logit contributions
ache-0.013
 badly-0.011
 severe-0.011
 gen-0.011
 mercy-0.010
Token shiny
Token ID22441
Feature activation-3.50e-02

Pos logit contributions
ashes+0.024
ips+0.023
olls+0.023
 recess+0.023
les+0.022
Neg logit contributions
ache-0.019
 badly-0.018
 spe-0.016
 severe-0.016
 gen-0.016
Token home
Token ID1363
Feature activation+1.69e-02

Pos logit contributions
ashes+0.060
ips+0.058
olls+0.058
 recess+0.056
les+0.055
Neg logit contributions
ache-0.062
 badly-0.058
 spe-0.053
 severe-0.053
 gen-0.053
Token.
Token ID13
Feature activation-2.06e-02

Pos logit contributions
ache+0.039
 spe+0.035
 mercy+0.035
Mill+0.035
Jean+0.034
Neg logit contributions
 day-0.018
ips-0.018
ashes-0.018
olls-0.018
 recess-0.018
Token<|endoftext|>
Token ID50256
Feature activation-6.76e-02

Pos logit contributions
ashes+0.033
ips+0.032
olls+0.031
 recess+0.030
les+0.030
Neg logit contributions
ache-0.039
 badly-0.036
 spe-0.034
Mill-0.034
 gen-0.034
TokenOnce
Token ID7454
Feature activation-5.70e-02

Pos logit contributions
ashes+0.117
olls+0.115
ips+0.109
asher+0.108
olphins+0.108
Neg logit contributions
ache-0.113
 badly-0.109
 gen-0.101
 spe-0.101
Am-0.101
Token upon
Token ID2402
Feature activation-2.55e-02

Pos logit contributions
ashes+0.067
olls+0.061
ips+0.059
asher+0.056
les+0.056
Neg logit contributions
 badly-0.129
ache-0.129
 spe-0.117
 severe-0.116
 gen-0.116
Token a
Token ID257
Feature activation-3.37e-02

Pos logit contributions
ashes+0.042
 recess+0.040
ips+0.040
olls+0.039
 day+0.039
Neg logit contributions
ache-0.046
 spe-0.040
 badly-0.040
 severe-0.038
 gen-0.038
Token time
Token ID640
Feature activation-3.36e-02

Pos logit contributions
ashes+0.026
ips+0.024
olls+0.024
 recess+0.022
les+0.022
Neg logit contributions
ache-0.091
 badly-0.086
 gen-0.083
 spe-0.083
 severe-0.083
Token,
Token ID11
Feature activation-8.44e-03

Pos logit contributions
ashes+0.051
ips+0.050
olls+0.049
 recess+0.047
les+0.046
Neg logit contributions
ache-0.066
 badly-0.061
 severe-0.058
 spe-0.058
 gen-0.057
Token hand
Token ID1021
Feature activation+2.26e-02

Pos logit contributions
ache+0.052
 spe+0.049
 badly+0.049
Mill+0.049
 gen+0.048
Neg logit contributions
ashes-0.043
 scores-0.041
olls-0.041
les-0.040
olphins-0.039
Token or
Token ID393
Feature activation+1.34e-02

Pos logit contributions
ache+0.041
 badly+0.038
 spe+0.035
 severe+0.035
 gen+0.035
Neg logit contributions
ashes-0.038
ips-0.037
olls-0.037
 recess-0.035
les-0.035
Token a
Token ID257
Feature activation+2.72e-02

Pos logit contributions
ache+0.025
 badly+0.023
 spe+0.022
Mill+0.022
Am+0.022
Neg logit contributions
ashes-0.021
olls-0.020
 recess-0.020
 scores-0.020
 Win-0.019
Token cane
Token ID33009
Feature activation+2.09e-02

Pos logit contributions
ache+0.048
Mill+0.046
 badly+0.045
 spe+0.045
Sad+0.045
Neg logit contributions
ashes-0.039
 scores-0.038
olls-0.037
 day-0.037
 morning-0.036
Token when
Token ID618
Feature activation+1.58e-02

Pos logit contributions
ache+0.039
 badly+0.037
 spe+0.034
 severe+0.034
 gen+0.034
Neg logit contributions
ashes-0.033
olls-0.032
ips-0.032
 recess-0.031
les-0.030
Token you
Token ID345
Feature activation-6.55e-02

Pos logit contributions
 badly+0.030
ache+0.030
 spe+0.027
 severe+0.027
 mercy+0.026
Neg logit contributions
ashes-0.026
ips-0.024
olls-0.024
les-0.023
acked-0.023
Token can
Token ID460
Feature activation-1.70e-03

Pos logit contributions
ips+0.104
ashes+0.101
olls+0.100
 recess+0.100
olphins+0.094
Neg logit contributions
ache-0.126
 badly-0.118
 severe-0.106
 mercy-0.105
 able-0.104
Token.
Token ID13
Feature activation-2.23e-02

Pos logit contributions
ashes+0.002
olls+0.002
ips+0.002
 recess+0.002
les+0.002
Neg logit contributions
ache-0.003
 badly-0.003
 severe-0.003
 spe-0.003
 gen-0.003
Token<|endoftext|>
Token ID50256
Feature activation-6.88e-02

Pos logit contributions
ashes+0.037
ips+0.035
olls+0.035
 recess+0.035
les+0.034
Neg logit contributions
ache-0.040
 badly-0.039
 gen-0.036
 spe-0.036
Mill-0.036
TokenOnce
Token ID7454
Feature activation-5.88e-02

Pos logit contributions
ashes+0.129
olls+0.125
asher+0.119
olphins+0.118
ips+0.118
Neg logit contributions
ache-0.104
 badly-0.104
Am-0.096
 gen-0.094
Mill-0.094
Token upon
Token ID2402
Feature activation-2.51e-02

Pos logit contributions
ashes+0.071
olls+0.064
ips+0.062
asher+0.059
les+0.058
Neg logit contributions
 badly-0.134
ache-0.132
 severe-0.119
 spe-0.119
 gen-0.119
Token have
Token ID423
Feature activation-1.20e-02

Pos logit contributions
ashes+0.002
ips+0.002
olls+0.002
les+0.002
 recess+0.002
Neg logit contributions
ache-0.004
 badly-0.004
 spe-0.003
 severe-0.003
 gen-0.003
Token some
Token ID617
Feature activation-6.25e-03

Pos logit contributions
ashes+0.018
 recess+0.017
ips+0.017
olls+0.017
 scores+0.017
Neg logit contributions
ache-0.024
 badly-0.022
 gen-0.021
 spe-0.020
 severe-0.020
Token ice
Token ID4771
Feature activation-1.33e-02

Pos logit contributions
ashes+0.009
ips+0.009
olls+0.009
les+0.008
olphins+0.008
Neg logit contributions
ache-0.012
 badly-0.012
 spe-0.011
 gen-0.011
 severe-0.011
Token cream
Token ID8566
Feature activation-1.11e-02

Pos logit contributions
 Win+0.020
olls+0.020
ips+0.020
 recess+0.020
 scores+0.020
Neg logit contributions
ache-0.025
 badly-0.024
 spe-0.021
 gen-0.021
 severe-0.021
Token."
Token ID526
Feature activation-6.48e-03

Pos logit contributions
ashes+0.018
ips+0.018
olls+0.018
 recess+0.017
les+0.017
Neg logit contributions
ache-0.020
 badly-0.019
 spe-0.017
 gen-0.017
 severe-0.017
Token<|endoftext|>
Token ID50256
Feature activation-6.33e-02

Pos logit contributions
ashes+0.010
olls+0.009
ips+0.009
les+0.009
 recess+0.009
Neg logit contributions
ache-0.013
 badly-0.012
 spe-0.011
 severe-0.011
Mill-0.011
TokenTom
Token ID13787
Feature activation-1.77e-02

Pos logit contributions
ashes+0.099
asher+0.096
ashed+0.092
olls+0.092
angles+0.088
Neg logit contributions
Am-0.103
 gen-0.102
 badly-0.099
 spe-0.099
ache-0.097
Token was
Token ID373
Feature activation+1.14e-02

Pos logit contributions
 recess+0.037
ashes+0.037
olls+0.035
ips+0.035
 sidelines+0.035
Neg logit contributions
ache-0.022
 badly-0.018
 who-0.018
 able-0.017
 severe-0.016
Token a
Token ID257
Feature activation+1.22e-02

Pos logit contributions
ache+0.022
 badly+0.020
 spe+0.019
 severe+0.019
 gen+0.019
Neg logit contributions
ashes-0.018
ips-0.017
olls-0.017
 recess-0.017
les-0.016
Token boy
Token ID2933
Feature activation+2.75e-02

Pos logit contributions
ache+0.021
 badly+0.019
 severe+0.018
 mercy+0.018
 spe+0.018
Neg logit contributions
ashes-0.021
olls-0.020
ips-0.020
 recess-0.020
les-0.020
Token who
Token ID508
Feature activation-3.45e-02

Pos logit contributions
ache+0.050
 badly+0.046
 severe+0.045
Mill+0.043
 mercy+0.043
Neg logit contributions
ashes-0.044
ips-0.043
olls-0.042
les-0.042
 recess-0.041