TOP ACTIVATIONS
MAX = 8.197

the sky before they walked fore shadow ed the down pour
yard . He had been fore shadow ed about this bad
, but it was all fore shadow ed by the kind
The girl had been fore shadow ed . Even though
the heavy bag had been fore shadow ed , and that
eyes . She had been fore shadow ed about the power
know , her mum was fore shadow ing ... the next
That was the setup that fore shadow ed the bad ending
The wave had fore shadow ed L ola 's
The bad ending was fore shadow ed by Maggie 's
, but when he turned back around , he noticed his
L ily had fore shadow ed the danger with
little girl remembered the earlier fore shadow ing , and it
again . But unb ek nown to him , the king
. When they reached the end of their adventure , they
With the key , the young boy was
With the key , the young boy was
earlier and promised to call back . She was afraid that
Grand ma 's words fore shadow ed a happy future
it was time to come back , the glad bird flew

MIN ACTIVATIONS
MIN = -7.499

: houses , towers , bridges , cars . One day
about numbers , shapes , patterns , and more . Do
build houses , towers , bridges and cars . They had
build houses , towers , bridges , and cars . Sometimes
trucks of different colors and sizes . They make noises like
make houses , towers , bridges and cars with the blocks
make houses , castles , bridges and more .
cars of different colors and sizes . He liked to make
had many dolls of different sizes and colors . They also
build towers , houses , bridges and anything they wanted with
. They make pictures and patterns with them on the floor
trucks of different colors and sizes . He liked to make
cars of different colors and sizes , but their favorite ones
trucks of different colors and sizes . Ben likes to make
cars of different colors and sizes . They make sounds like
cars of different colors and sizes . He makes them go
skirts of different colors and patterns . She liked to spin
We have different likes and disl ikes . We can be
They can make towers , bridges , houses and more with
cars of different colors and sizes . They make roads and

INTERVAL 4.273 - 8.197
CONTAINS 0.184%

time for Lily to go back inside , she said goodbye
followed her . When they got to the stable , it
. Tom screamed and pulled back his hand . It was
when the princess got the magnet it was fake ! She
not know how to go back . Suddenly ,

INTERVAL 0.349 - 4.273
CONTAINS 40.304%

laugh or scream . He looks bored and mean .
" What is it ?" Ben asked .
angry . He wanted to scare them again . He ran
big boots . One day , Tim wanted to be just
again . <|endoftext|> Once upon a time , there was a

INTERVAL -3.575 - 0.349
CONTAINS 58.960%

named Tim my . Tim my was very poor and he
her to spread some peanut butter on a piece of bread
. He feels sorry . He says , " I am
big and red !" " It is funny ,
. The end . <|endoftext|> Once upon a time , there

INTERVAL -7.499 - -3.575
CONTAINS 0.552%

their beds . They c uddle with their blankets and pill
big desk , a phone , a computer and some papers
nightmare couldn 't hurt her , so she lay in bed
You are a good girl , Lily . You can help
tr amp oline and a sandbox . He was having so
Token the
Token ID262
Feature activation-4.28e-01

Pos logit contributions
 aback+0.021
 closer+0.018
fired+0.018
 away+0.017
 home+0.017
Neg logit contributions
kin-0.032
pron-0.031
uren-0.029
omo-0.026
lf-0.025
Token sky
Token ID6766
Feature activation-2.23e+00

Pos logit contributions
kin+0.009
pron+0.008
uren+0.008
omo+0.007
lf+0.007
Neg logit contributions
 aback-0.010
 closer-0.009
fired-0.009
 away-0.009
 home-0.008
Token before
Token ID878
Feature activation-4.32e-01

Pos logit contributions
kin+0.064
pron+0.060
uren+0.059
omo+0.054
Adam+0.053
Neg logit contributions
 aback-0.034
 closer-0.034
 away-0.032
 home-0.031
fired-0.030
Token they
Token ID484
Feature activation-1.23e+00

Pos logit contributions
kin+0.013
pron+0.012
uren+0.011
omo+0.010
abs+0.010
Neg logit contributions
 closer-0.007
 aback-0.007
 home-0.006
 away-0.006
fired-0.006
Token walked
Token ID6807
Feature activation+2.03e+00

Pos logit contributions
kin+0.030
pron+0.029
uren+0.027
omo+0.025
lf+0.024
Neg logit contributions
 aback-0.024
 closer-0.023
fired-0.022
 away-0.022
 home-0.021
Token fore
Token ID1674
Feature activation+8.20e+00

Pos logit contributions
 aback+0.024
fired+0.019
 closer+0.017
 revenge+0.017
beh+0.016
Neg logit contributions
kin-0.065
pron-0.061
uren-0.059
Adam-0.054
omo-0.053
Tokenshadow
Token ID19106
Feature activation+1.20e+00

Pos logit contributions
 aback+0.170
 revenge+0.155
fired+0.152
 medical+0.144
 Wolf+0.133
Neg logit contributions
pron-0.153
uren-0.148
kin-0.140
ast-0.129
Adam-0.127
Tokened
Token ID276
Feature activation+2.33e+00

Pos logit contributions
 aback+0.013
 closer+0.010
fired+0.010
 revenge+0.009
 away+0.008
Neg logit contributions
kin-0.040
pron-0.037
uren-0.036
omo-0.034
Adam-0.034
Token the
Token ID262
Feature activation+6.78e-01

Pos logit contributions
 aback+0.037
 closer+0.033
fired+0.032
 away+0.029
 revenge+0.029
Neg logit contributions
kin-0.066
pron-0.062
uren-0.059
omo-0.054
lf-0.053
Token down
Token ID866
Feature activation+3.04e+00

Pos logit contributions
 aback+0.014
 closer+0.013
fired+0.012
 home+0.012
 revenge+0.012
Neg logit contributions
kin-0.016
pron-0.014
uren-0.014
omo-0.012
Adam-0.012
Tokenpour
Token ID48681
Feature activation+2.13e+00

Pos logit contributions
 aback+0.053
 closer+0.047
fired+0.046
 away+0.043
 home+0.043
Neg logit contributions
kin-0.083
pron-0.078
uren-0.073
omo-0.067
lf-0.067
Token yard
Token ID12699
Feature activation-2.28e+00

Pos logit contributions
kin+0.013
pron+0.012
uren+0.011
omo+0.010
Adam+0.010
Neg logit contributions
 aback-0.013
fired-0.012
 closer-0.012
 home-0.012
 away-0.011
Token.
Token ID13
Feature activation+8.72e-01

Pos logit contributions
kin+0.064
pron+0.061
uren+0.057
omo+0.052
addy+0.050
Neg logit contributions
 aback-0.038
 closer-0.035
 home-0.034
 away-0.034
fired-0.034
Token He
Token ID679
Feature activation-5.24e-01

Pos logit contributions
 aback+0.018
fired+0.015
 closer+0.015
 home+0.014
 revenge+0.014
Neg logit contributions
kin-0.023
pron-0.021
uren-0.018
lf-0.017
bridge-0.017
Token had
Token ID550
Feature activation+1.28e+00

Pos logit contributions
kin+0.012
pron+0.011
uren+0.010
omo+0.009
lf+0.009
Neg logit contributions
 aback-0.011
 closer-0.010
fired-0.010
 away-0.010
 revenge-0.009
Token been
Token ID587
Feature activation+1.14e+00

Pos logit contributions
 aback+0.024
 closer+0.021
fired+0.021
 away+0.020
 revenge+0.019
Neg logit contributions
kin-0.033
pron-0.031
uren-0.029
omo-0.026
lf-0.026
Token fore
Token ID1674
Feature activation+7.49e+00

Pos logit contributions
 aback+0.024
fired+0.021
 closer+0.020
 revenge+0.019
 nearer+0.019
Neg logit contributions
kin-0.025
pron-0.024
uren-0.021
Adam-0.019
lf-0.019
Tokenshadow
Token ID19106
Feature activation+8.02e-01

Pos logit contributions
 aback+0.152
fired+0.137
 revenge+0.134
 closer+0.120
 medical+0.119
Neg logit contributions
pron-0.167
kin-0.157
uren-0.151
lf-0.137
ast-0.134
Tokened
Token ID276
Feature activation+1.88e+00

Pos logit contributions
 aback+0.009
 closer+0.008
fired+0.008
 revenge+0.007
 away+0.007
Neg logit contributions
kin-0.026
pron-0.024
uren-0.024
omo-0.022
Adam-0.022
Token about
Token ID546
Feature activation-2.96e-01

Pos logit contributions
 aback+0.034
 closer+0.030
fired+0.029
 revenge+0.027
 away+0.027
Neg logit contributions
kin-0.050
pron-0.046
uren-0.043
lf-0.039
omo-0.039
Token this
Token ID428
Feature activation+3.81e-01

Pos logit contributions
kin+0.008
pron+0.007
uren+0.007
omo+0.006
lf+0.006
Neg logit contributions
 aback-0.005
 closer-0.005
fired-0.005
 revenge-0.004
 away-0.004
Token bad
Token ID2089
Feature activation+2.21e+00

Pos logit contributions
 aback+0.008
 closer+0.008
fired+0.007
 away+0.007
 home+0.007
Neg logit contributions
kin-0.008
pron-0.008
uren-0.007
Adam-0.006
omo-0.006
Token,
Token ID11
Feature activation-2.17e+00

Pos logit contributions
kin+0.006
pron+0.006
uren+0.005
omo+0.005
 scalp+0.005
Neg logit contributions
 aback-0.004
 closer-0.004
fired-0.004
 home-0.003
 away-0.003
Token but
Token ID475
Feature activation-2.83e-01

Pos logit contributions
kin+0.059
pron+0.054
uren+0.049
lf+0.045
ae+0.045
Neg logit contributions
 aback-0.041
 closer-0.039
 home-0.036
 away-0.036
fired-0.035
Token it
Token ID340
Feature activation+7.43e-01

Pos logit contributions
kin+0.006
pron+0.006
uren+0.005
lf+0.005
omo+0.005
Neg logit contributions
 aback-0.006
 closer-0.006
fired-0.006
 away-0.005
 revenge-0.005
Token was
Token ID373
Feature activation-1.42e+00

Pos logit contributions
 aback+0.015
 closer+0.013
fired+0.013
 away+0.012
 revenge+0.012
Neg logit contributions
kin-0.019
pron-0.017
uren-0.016
omo-0.015
lf-0.014
Token all
Token ID477
Feature activation+2.41e+00

Pos logit contributions
kin+0.033
pron+0.031
uren+0.028
omo+0.026
lf+0.025
Neg logit contributions
 aback-0.030
 closer-0.027
fired-0.027
 away-0.025
 revenge-0.025
Token fore
Token ID1674
Feature activation+7.42e+00

Pos logit contributions
 aback+0.042
 closer+0.037
fired+0.037
 revenge+0.034
 nearer+0.033
Neg logit contributions
kin-0.062
pron-0.059
uren-0.053
omo-0.050
lf-0.049
Tokenshadow
Token ID19106
Feature activation+6.06e-01

Pos logit contributions
 aback+0.151
fired+0.138
 revenge+0.135
 closer+0.124
 home+0.118
Neg logit contributions
pron-0.159
kin-0.149
uren-0.145
lf-0.132
Adam-0.125
Tokened
Token ID276
Feature activation+2.41e+00

Pos logit contributions
 aback+0.008
 closer+0.007
fired+0.007
 away+0.006
 revenge+0.006
Neg logit contributions
kin-0.018
pron-0.017
uren-0.017
omo-0.015
lf-0.015
Token by
Token ID416
Feature activation-6.46e-01

Pos logit contributions
 aback+0.039
 closer+0.034
fired+0.034
 revenge+0.030
 home+0.029
Neg logit contributions
kin-0.066
pron-0.061
uren-0.058
lf-0.052
omo-0.052
Token the
Token ID262
Feature activation+9.81e-01

Pos logit contributions
kin+0.017
pron+0.016
uren+0.015
omo+0.014
Adam+0.013
Neg logit contributions
 aback-0.012
 closer-0.011
fired-0.010
 revenge-0.010
 home-0.010
Token kind
Token ID1611
Feature activation+2.27e+00

Pos logit contributions
 aback+0.020
 closer+0.018
fired+0.018
 away+0.017
 revenge+0.017
Neg logit contributions
kin-0.024
pron-0.022
uren-0.020
lf-0.018
omo-0.018
Token
Token ID198
Feature activation+6.68e-01

Pos logit contributions
kin+0.002
pron+0.002
uren+0.002
 scalp+0.001
omo+0.001
Neg logit contributions
 aback-0.001
 closer-0.001
fired-0.001
 home-0.001
 away-0.001
TokenThe
Token ID464
Feature activation-5.30e-01

Pos logit contributions
 aback+0.015
 closer+0.013
fired+0.012
 away+0.012
 nearer+0.012
Neg logit contributions
kin-0.016
pron-0.014
uren-0.012
 scalp-0.012
 moons-0.012
Token girl
Token ID2576
Feature activation+8.77e-01

Pos logit contributions
kin+0.013
pron+0.012
uren+0.011
omo+0.010
lf+0.010
Neg logit contributions
 aback-0.011
 closer-0.010
fired-0.010
 away-0.009
 home-0.009
Token had
Token ID550
Feature activation+1.67e+00

Pos logit contributions
 aback+0.017
 closer+0.015
fired+0.015
 away+0.014
 home+0.014
Neg logit contributions
kin-0.023
pron-0.021
uren-0.019
omo-0.017
Adam-0.017
Token been
Token ID587
Feature activation+1.47e+00

Pos logit contributions
 aback+0.031
 closer+0.026
fired+0.025
 away+0.025
 home+0.024
Neg logit contributions
kin-0.047
pron-0.043
uren-0.040
omo-0.038
lf-0.037
Token fore
Token ID1674
Feature activation+7.40e+00

Pos logit contributions
 aback+0.029
fired+0.027
 closer+0.026
 revenge+0.025
 nearer+0.023
Neg logit contributions
kin-0.034
pron-0.032
uren-0.030
Adam-0.027
lf-0.026
Tokenshadow
Token ID19106
Feature activation+1.10e+00

Pos logit contributions
 aback+0.147
fired+0.135
 revenge+0.132
 medical+0.119
 closer+0.117
Neg logit contributions
pron-0.168
kin-0.159
uren-0.151
lf-0.138
Adam-0.134
Tokened
Token ID276
Feature activation+2.17e+00

Pos logit contributions
 aback+0.013
 closer+0.011
fired+0.011
 revenge+0.010
 away+0.009
Neg logit contributions
kin-0.035
pron-0.033
uren-0.032
Adam-0.029
ae-0.029
Token.
Token ID13
Feature activation+8.15e-01

Pos logit contributions
 aback+0.037
 closer+0.033
fired+0.032
 revenge+0.029
 away+0.029
Neg logit contributions
kin-0.059
pron-0.055
uren-0.052
lf-0.047
omo-0.047
Token Even
Token ID3412
Feature activation+8.90e-01

Pos logit contributions
 aback+0.017
fired+0.014
 closer+0.014
 home+0.013
 away+0.012
Neg logit contributions
kin-0.022
pron-0.020
uren-0.017
lf-0.017
omo-0.017
Token though
Token ID996
Feature activation-4.75e-01

Pos logit contributions
 aback+0.019
fired+0.017
 closer+0.017
 revenge+0.016
 away+0.016
Neg logit contributions
kin-0.020
pron-0.019
uren-0.017
lf-0.015
omo-0.015
Token the
Token ID262
Feature activation+6.99e-01

Pos logit contributions
 aback+0.002
 closer+0.002
fired+0.002
 revenge+0.002
 nearer+0.002
Neg logit contributions
kin-0.003
pron-0.003
uren-0.003
lf-0.002
Adam-0.002
Token heavy
Token ID4334
Feature activation+1.94e+00

Pos logit contributions
 aback+0.014
fired+0.013
 closer+0.012
 away+0.011
 revenge+0.011
Neg logit contributions
kin-0.017
pron-0.016
uren-0.015
lf-0.013
omo-0.013
Token bag
Token ID6131
Feature activation+2.43e+00

Pos logit contributions
 aback+0.041
fired+0.037
 closer+0.037
beh+0.035
 revenge+0.034
Neg logit contributions
kin-0.046
pron-0.042
uren-0.037
lf-0.035
omo-0.034
Token had
Token ID550
Feature activation-2.18e-01

Pos logit contributions
 aback+0.045
 closer+0.040
fired+0.039
 away+0.037
 home+0.036
Neg logit contributions
kin-0.063
pron-0.059
uren-0.057
omo-0.051
lf-0.050
Token been
Token ID587
Feature activation+9.76e-02

Pos logit contributions
kin+0.006
pron+0.005
uren+0.005
omo+0.005
lf+0.005
Neg logit contributions
 aback-0.004
 closer-0.004
fired-0.003
 away-0.003
 home-0.003
Token fore
Token ID1674
Feature activation+7.37e+00

Pos logit contributions
 aback+0.002
 closer+0.002
fired+0.002
 revenge+0.001
 away+0.001
Neg logit contributions
kin-0.003
pron-0.002
uren-0.002
lf-0.002
omo-0.002
Tokenshadow
Token ID19106
Feature activation+5.61e-01

Pos logit contributions
 aback+0.147
fired+0.134
 revenge+0.129
 closer+0.117
 medical+0.115
Neg logit contributions
pron-0.165
kin-0.162
uren-0.147
ast-0.132
lf-0.132
Tokened
Token ID276
Feature activation+2.13e+00

Pos logit contributions
 aback+0.008
 closer+0.007
fired+0.007
 away+0.006
 revenge+0.006
Neg logit contributions
kin-0.017
pron-0.016
uren-0.015
omo-0.014
lf-0.014
Token,
Token ID11
Feature activation-1.72e+00

Pos logit contributions
 aback+0.035
 closer+0.031
fired+0.030
 revenge+0.027
 away+0.026
Neg logit contributions
kin-0.058
pron-0.054
uren-0.051
lf-0.046
omo-0.046
Token and
Token ID290
Feature activation-1.20e-01

Pos logit contributions
kin+0.046
pron+0.041
uren+0.039
omo+0.036
ae+0.035
Neg logit contributions
 aback-0.033
 closer-0.031
 away-0.029
 home-0.028
fired-0.028
Token that
Token ID326
Feature activation+1.46e+00

Pos logit contributions
kin+0.003
pron+0.003
uren+0.002
lf+0.002
omo+0.002
Neg logit contributions
 aback-0.003
 closer-0.002
fired-0.002
 away-0.002
 revenge-0.002
Token eyes
Token ID2951
Feature activation+7.80e-01

Pos logit contributions
 aback+0.015
 closer+0.014
fired+0.014
 home+0.013
 away+0.013
Neg logit contributions
kin-0.017
pron-0.016
uren-0.015
lf-0.013
omo-0.013
Token.
Token ID13
Feature activation+4.84e-01

Pos logit contributions
 aback+0.014
 closer+0.013
fired+0.012
 away+0.012
 home+0.011
Neg logit contributions
kin-0.021
pron-0.019
uren-0.018
omo-0.017
Adam-0.016
Token She
Token ID1375
Feature activation-4.45e-01

Pos logit contributions
 aback+0.010
fired+0.008
 closer+0.008
 home+0.008
 revenge+0.007
Neg logit contributions
kin-0.013
pron-0.012
lf-0.011
uren-0.011
omo-0.010
Token had
Token ID550
Feature activation+1.34e+00

Pos logit contributions
kin+0.012
pron+0.011
uren+0.010
ae+0.009
omo+0.009
Neg logit contributions
 aback-0.008
 closer-0.008
fired-0.008
 away-0.007
 home-0.007
Token been
Token ID587
Feature activation+9.94e-01

Pos logit contributions
 aback+0.025
 closer+0.022
 away+0.021
fired+0.021
 home+0.021
Neg logit contributions
kin-0.039
pron-0.035
uren-0.032
lf-0.030
omo-0.030
Token fore
Token ID1674
Feature activation+7.37e+00

Pos logit contributions
 aback+0.022
fired+0.019
 closer+0.019
 revenge+0.018
 away+0.018
Neg logit contributions
kin-0.022
pron-0.021
uren-0.019
lf-0.017
Adam-0.017
Tokenshadow
Token ID19106
Feature activation+8.45e-01

Pos logit contributions
 aback+0.143
fired+0.131
 revenge+0.127
 closer+0.115
 medical+0.115
Neg logit contributions
pron-0.169
kin-0.164
uren-0.158
lf-0.141
Adam-0.137
Tokened
Token ID276
Feature activation+2.04e+00

Pos logit contributions
 aback+0.011
 closer+0.009
fired+0.009
 away+0.008
 revenge+0.008
Neg logit contributions
kin-0.027
pron-0.026
uren-0.024
omo-0.022
lf-0.022
Token about
Token ID546
Feature activation-5.70e-01

Pos logit contributions
 aback+0.035
 closer+0.030
fired+0.030
 away+0.028
 revenge+0.027
Neg logit contributions
kin-0.056
pron-0.053
uren-0.049
omo-0.045
lf-0.045
Token the
Token ID262
Feature activation-7.59e-02

Pos logit contributions
kin+0.016
pron+0.015
uren+0.014
omo+0.013
Adam+0.012
Neg logit contributions
 aback-0.010
 closer-0.009
fired-0.009
 home-0.008
 revenge-0.008
Token power
Token ID1176
Feature activation+5.61e-01

Pos logit contributions
kin+0.002
pron+0.002
uren+0.002
omo+0.001
lf+0.001
Neg logit contributions
 aback-0.002
 closer-0.001
 home-0.001
 revenge-0.001
 away-0.001
Token know
Token ID760
Feature activation+1.25e-01

Pos logit contributions
 aback+0.006
 closer+0.005
fired+0.005
 away+0.005
 home+0.005
Neg logit contributions
kin-0.007
pron-0.007
uren-0.006
lf-0.006
sheets-0.006
Token,
Token ID11
Feature activation-2.76e+00

Pos logit contributions
 aback+0.002
 closer+0.002
fired+0.002
 home+0.002
 away+0.002
Neg logit contributions
kin-0.003
pron-0.003
uren-0.003
omo-0.003
 scalp-0.002
Token her
Token ID607
Feature activation-4.78e-01

Pos logit contributions
kin+0.077
pron+0.067
omo+0.063
uren+0.062
lf+0.058
Neg logit contributions
 aback-0.050
 closer-0.049
 home-0.043
 back-0.042
 away-0.042
Token mum
Token ID25682
Feature activation+2.56e+00

Pos logit contributions
kin+0.010
pron+0.009
uren+0.009
lf+0.008
Adam+0.008
Neg logit contributions
 aback-0.011
 closer-0.011
 home-0.010
fired-0.010
 revenge-0.009
Token was
Token ID373
Feature activation-9.45e-01

Pos logit contributions
 aback+0.050
 closer+0.046
fired+0.043
 away+0.043
 home+0.042
Neg logit contributions
kin-0.065
pron-0.059
uren-0.055
omo-0.050
Adam-0.049
Token fore
Token ID1674
Feature activation+7.25e+00

Pos logit contributions
kin+0.025
pron+0.023
uren+0.023
omo+0.021
abs+0.020
Neg logit contributions
 aback-0.017
 closer-0.016
 home-0.015
 away-0.015
 back-0.015
Tokenshadow
Token ID19106
Feature activation+2.30e-01

Pos logit contributions
 aback+0.144
fired+0.134
 revenge+0.128
 medical+0.111
 closer+0.111
Neg logit contributions
pron-0.172
kin-0.161
uren-0.152
lf-0.138
ae-0.133
Tokening
Token ID278
Feature activation-4.88e-01

Pos logit contributions
 aback+0.003
 closer+0.003
fired+0.002
 away+0.002
 revenge+0.002
Neg logit contributions
kin-0.007
pron-0.007
uren-0.006
omo-0.006
lf-0.006
Token...
Token ID986
Feature activation-8.45e-01

Pos logit contributions
kin+0.013
pron+0.012
uren+0.011
omo+0.010
lf+0.010
Neg logit contributions
 aback-0.009
 closer-0.008
fired-0.008
 away-0.007
 revenge-0.007
Tokenthe
Token ID1169
Feature activation-2.15e-01

Pos logit contributions
kin+0.020
pron+0.018
uren+0.017
omo+0.015
lf+0.015
Neg logit contributions
 aback-0.018
 closer-0.016
fired-0.016
 away-0.015
 revenge-0.015
Token next
Token ID1306
Feature activation+1.16e+00

Pos logit contributions
kin+0.005
pron+0.005
uren+0.005
Adam+0.004
 Avery+0.004
Neg logit contributions
 aback-0.004
 closer-0.004
 home-0.004
 away-0.004
fired-0.004
Token That
Token ID1320
Feature activation+1.92e+00

Pos logit contributions
 aback+0.010
 closer+0.009
fired+0.009
 away+0.009
 revenge+0.009
Neg logit contributions
kin-0.011
pron-0.010
uren-0.009
omo-0.008
lf-0.008
Token was
Token ID373
Feature activation-2.28e+00

Pos logit contributions
 aback+0.040
fired+0.036
 closer+0.036
 revenge+0.033
 away+0.033
Neg logit contributions
kin-0.045
pron-0.041
uren-0.039
lf-0.035
omo-0.035
Token the
Token ID262
Feature activation-1.31e+00

Pos logit contributions
kin+0.053
pron+0.048
uren+0.045
lf+0.041
omo+0.040
Neg logit contributions
 aback-0.047
fired-0.043
 closer-0.041
 home-0.038
 revenge-0.038
Token setup
Token ID9058
Feature activation-1.43e+00

Pos logit contributions
kin+0.034
pron+0.031
uren+0.029
omo+0.026
lf+0.026
Neg logit contributions
 aback-0.025
fired-0.022
 closer-0.021
 away-0.020
 revenge-0.019
Token that
Token ID326
Feature activation+1.39e+00

Pos logit contributions
kin+0.037
pron+0.035
uren+0.034
omo+0.031
 majesty+0.030
Neg logit contributions
 aback-0.026
 closer-0.024
 away-0.023
fired-0.023
 home-0.022
Token fore
Token ID1674
Feature activation+6.84e+00

Pos logit contributions
 aback+0.030
 closer+0.028
fired+0.027
 away+0.026
 revenge+0.025
Neg logit contributions
kin-0.032
pron-0.029
uren-0.027
omo-0.024
lf-0.024
Tokenshadow
Token ID19106
Feature activation+4.36e-01

Pos logit contributions
 aback+0.140
fired+0.132
 revenge+0.127
 home+0.118
 closer+0.118
Neg logit contributions
pron-0.133
uren-0.129
kin-0.122
abs-0.113
lf-0.109
Tokened
Token ID276
Feature activation+1.95e+00

Pos logit contributions
 aback+0.005
 closer+0.004
fired+0.004
 revenge+0.004
 away+0.004
Neg logit contributions
kin-0.014
pron-0.013
uren-0.013
omo-0.012
Adam-0.012
Token the
Token ID262
Feature activation+9.87e-01

Pos logit contributions
 aback+0.032
 closer+0.028
fired+0.028
 revenge+0.025
 home+0.024
Neg logit contributions
kin-0.054
pron-0.050
uren-0.047
lf-0.043
omo-0.043
Token bad
Token ID2089
Feature activation+3.36e+00

Pos logit contributions
 aback+0.020
fired+0.017
 closer+0.016
 away+0.015
beh+0.015
Neg logit contributions
kin-0.024
pron-0.022
uren-0.021
omo-0.019
lf-0.019
Token ending
Token ID7464
Feature activation+1.03e+00

Pos logit contributions
 aback+0.088
fired+0.079
 closer+0.079
 away+0.074
 unst+0.072
Neg logit contributions
kin-0.064
pron-0.055
uren-0.051
lf-0.044
omo-0.043
Token
Token ID198
Feature activation+1.51e-01

Pos logit contributions
 aback+0.016
fired+0.014
 home+0.013
 closer+0.013
 away+0.012
Neg logit contributions
kin-0.022
pron-0.021
lf-0.019
uren-0.017
bee-0.017
Token
Token ID198
Feature activation+8.18e-01

Pos logit contributions
 aback+0.003
 closer+0.003
fired+0.003
 home+0.003
 away+0.002
Neg logit contributions
kin-0.004
pron-0.003
uren-0.003
lf-0.003
 moons-0.003
TokenThe
Token ID464
Feature activation-3.83e-01

Pos logit contributions
 aback+0.016
 closer+0.016
fired+0.014
 away+0.014
 home+0.014
Neg logit contributions
kin-0.019
pron-0.017
uren-0.016
 moons-0.016
 majesty-0.015
Token wave
Token ID6769
Feature activation+9.93e-01

Pos logit contributions
kin+0.009
pron+0.008
uren+0.008
omo+0.007
 scalp+0.007
Neg logit contributions
 closer-0.008
 aback-0.007
 home-0.007
 away-0.007
 back-0.007
Token had
Token ID550
Feature activation+1.49e+00

Pos logit contributions
 aback+0.018
 closer+0.018
 away+0.017
fired+0.016
 revenge+0.015
Neg logit contributions
kin-0.025
pron-0.024
uren-0.022
Adam-0.020
omo-0.020
Token fore
Token ID1674
Feature activation+6.84e+00

Pos logit contributions
 aback+0.027
 closer+0.024
fired+0.024
 away+0.022
 revenge+0.022
Neg logit contributions
kin-0.039
pron-0.036
uren-0.034
omo-0.031
lf-0.031
Tokenshadow
Token ID19106
Feature activation+5.60e-01

Pos logit contributions
 aback+0.145
fired+0.137
 revenge+0.135
 medical+0.119
 home+0.118
Neg logit contributions
pron-0.133
uren-0.126
kin-0.122
ast-0.111
abs-0.110
Tokened
Token ID276
Feature activation+2.14e+00

Pos logit contributions
 aback+0.006
 closer+0.005
fired+0.005
 revenge+0.004
 away+0.004
Neg logit contributions
kin-0.019
pron-0.018
uren-0.017
omo-0.016
lf-0.015
Token L
Token ID406
Feature activation-2.78e+00

Pos logit contributions
 aback+0.036
 closer+0.031
fired+0.031
 revenge+0.028
 nearer+0.027
Neg logit contributions
kin-0.057
pron-0.053
uren-0.051
lf-0.045
omo-0.045
Tokenola
Token ID5708
Feature activation+1.83e+00

Pos logit contributions
pron+0.048
kin+0.045
uren+0.043
lf+0.041
 unison+0.041
Neg logit contributions
 aback-0.069
 closer-0.065
fired-0.064
 home-0.060
 away-0.060
Token's
Token ID338
Feature activation+7.93e-01

Pos logit contributions
 aback+0.033
 closer+0.029
fired+0.029
 away+0.027
 home+0.026
Neg logit contributions
kin-0.049
pron-0.046
uren-0.043
omo-0.039
lf-0.039
Token
Token ID198
Feature activation+7.84e-01

Pos logit contributions
 aback+0.002
 closer+0.002
fired+0.002
 home+0.002
 away+0.002
Neg logit contributions
kin-0.003
pron-0.002
uren-0.002
lf-0.002
omo-0.002
TokenThe
Token ID464
Feature activation-4.51e-01

Pos logit contributions
 aback+0.017
 closer+0.015
fired+0.015
 away+0.014
 home+0.014
Neg logit contributions
kin-0.018
pron-0.017
uren-0.016
lf-0.014
 moons-0.014
Token bad
Token ID2089
Feature activation+1.58e+00

Pos logit contributions
kin+0.011
pron+0.010
uren+0.010
omo+0.009
Adam+0.009
Neg logit contributions
 aback-0.009
 closer-0.008
fired-0.008
 home-0.008
 revenge-0.008
Token ending
Token ID7464
Feature activation+1.16e+00

Pos logit contributions
 aback+0.036
 closer+0.034
 home+0.033
fired+0.032
 revenge+0.032
Neg logit contributions
kin-0.033
pron-0.031
uren-0.029
Adam-0.025
omo-0.025
Token was
Token ID373
Feature activation+1.88e-01

Pos logit contributions
 aback+0.020
 closer+0.018
fired+0.018
 away+0.017
 home+0.016
Neg logit contributions
kin-0.031
pron-0.031
uren-0.028
omo-0.026
Adam-0.026
Token fore
Token ID1674
Feature activation+6.73e+00

Pos logit contributions
 aback+0.004
 closer+0.003
fired+0.003
 away+0.003
 revenge+0.003
Neg logit contributions
kin-0.005
pron-0.004
uren-0.004
omo-0.004
lf-0.004
Tokenshadow
Token ID19106
Feature activation+5.51e-01

Pos logit contributions
 aback+0.130
fired+0.116
 revenge+0.111
 closer+0.103
 home+0.100
Neg logit contributions
pron-0.157
kin-0.156
uren-0.145
lf-0.130
ae-0.127
Tokened
Token ID276
Feature activation+2.10e+00

Pos logit contributions
 aback+0.006
 closer+0.005
fired+0.005
 away+0.005
 revenge+0.004
Neg logit contributions
kin-0.018
pron-0.017
uren-0.016
lf-0.015
omo-0.015
Token by
Token ID416
Feature activation-7.07e-01

Pos logit contributions
 aback+0.035
 closer+0.030
fired+0.030
 away+0.027
 revenge+0.027
Neg logit contributions
kin-0.059
pron-0.055
uren-0.052
omo-0.047
lf-0.047
Token Maggie
Token ID33014
Feature activation+1.54e+00

Pos logit contributions
kin+0.018
pron+0.018
uren+0.016
omo+0.015
lf+0.015
Neg logit contributions
 aback-0.013
 closer-0.012
fired-0.011
 home-0.011
 away-0.011
Token's
Token ID338
Feature activation+8.67e-01

Pos logit contributions
 aback+0.029
 closer+0.026
fired+0.025
 away+0.024
 home+0.023
Neg logit contributions
kin-0.040
pron-0.038
uren-0.035
omo-0.032
lf-0.032
Token,
Token ID11
Feature activation-1.62e+00

Pos logit contributions
 aback+0.056
 closer+0.053
fired+0.048
 home+0.048
 away+0.047
Neg logit contributions
kin-0.073
pron-0.067
uren-0.062
omo-0.056
 scalp-0.055
Token but
Token ID475
Feature activation+3.35e-01

Pos logit contributions
kin+0.040
pron+0.035
uren+0.032
 moons+0.031
bridge+0.030
Neg logit contributions
 aback-0.035
 closer-0.034
 home-0.031
 away-0.030
fired-0.030
Token when
Token ID618
Feature activation+8.06e-01

Pos logit contributions
 aback+0.006
 closer+0.006
fired+0.006
 away+0.006
 home+0.006
Neg logit contributions
kin-0.008
pron-0.008
uren-0.007
omo-0.007
Adam-0.007
Token he
Token ID339
Feature activation+1.46e-01

Pos logit contributions
 aback+0.018
 closer+0.017
fired+0.016
 away+0.015
 home+0.015
Neg logit contributions
kin-0.018
pron-0.017
uren-0.015
omo-0.014
lf-0.013
Token turned
Token ID2900
Feature activation+2.93e+00

Pos logit contributions
 aback+0.003
fired+0.003
 closer+0.003
 revenge+0.003
 home+0.003
Neg logit contributions
kin-0.003
pron-0.003
uren-0.003
lf-0.003
omo-0.002
Token back
Token ID736
Feature activation+6.34e+00

Pos logit contributions
 aback+0.048
fired+0.046
beh+0.044
 revenge+0.040
 medical+0.038
Neg logit contributions
kin-0.074
pron-0.071
uren-0.066
lf-0.058
 Avery-0.058
Token around
Token ID1088
Feature activation+5.85e-01

Pos logit contributions
 aback+0.143
beh+0.135
 bitten+0.125
 medical+0.124
 revenge+0.122
Neg logit contributions
kin-0.120
pron-0.103
uren-0.101
 Ben-0.099
ia-0.095
Token,
Token ID11
Feature activation+6.38e-01

Pos logit contributions
 aback+0.011
 closer+0.010
fired+0.010
 away+0.009
 home+0.009
Neg logit contributions
kin-0.015
pron-0.014
uren-0.013
omo-0.012
lf-0.012
Token he
Token ID339
Feature activation+5.38e-01

Pos logit contributions
 aback+0.013
 closer+0.012
fired+0.012
 away+0.011
 home+0.011
Neg logit contributions
kin-0.015
pron-0.014
uren-0.013
omo-0.012
lf-0.012
Token noticed
Token ID6810
Feature activation-3.21e-01

Pos logit contributions
 aback+0.010
 closer+0.009
fired+0.009
 away+0.008
 home+0.008
Neg logit contributions
kin-0.014
pron-0.013
uren-0.012
omo-0.011
lf-0.011
Token his
Token ID465
Feature activation-1.28e-01

Pos logit contributions
kin+0.009
pron+0.008
uren+0.008
omo+0.007
lf+0.007
Neg logit contributions
 aback-0.006
 closer-0.005
fired-0.005
 away-0.005
 revenge-0.005
Token
Token ID198
Feature activation+3.64e-01

Pos logit contributions
 aback+0.009
 closer+0.008
fired+0.007
 home+0.007
 away+0.007
Neg logit contributions
kin-0.015
pron-0.014
lf-0.012
uren-0.012
bee-0.012
Token
Token ID198
Feature activation+9.99e-01

Pos logit contributions
 aback+0.008
 closer+0.007
fired+0.007
 home+0.006
 away+0.006
Neg logit contributions
kin-0.009
pron-0.008
uren-0.007
lf-0.007
omo-0.007
TokenL
Token ID43
Feature activation-2.47e+00

Pos logit contributions
 aback+0.022
 closer+0.021
fired+0.019
 away+0.019
 home+0.018
Neg logit contributions
kin-0.022
pron-0.020
uren-0.019
 moons-0.017
 scalp-0.017
Tokenily
Token ID813
Feature activation+1.11e-01

Pos logit contributions
pron+0.049
kin+0.048
uren+0.044
omo+0.040
 moons+0.039
Neg logit contributions
 aback-0.059
 closer-0.051
fired-0.051
 away-0.049
 home-0.048
Token had
Token ID550
Feature activation+1.75e+00

Pos logit contributions
 aback+0.002
 closer+0.002
 away+0.002
fired+0.002
 home+0.002
Neg logit contributions
kin-0.003
pron-0.003
uren-0.002
bridge-0.002
inner-0.002
Token fore
Token ID1674
Feature activation+6.34e+00

Pos logit contributions
 aback+0.029
 closer+0.024
fired+0.024
 home+0.023
 away+0.023
Neg logit contributions
kin-0.053
pron-0.050
uren-0.046
lf-0.044
omo-0.042
Tokenshadow
Token ID19106
Feature activation+7.05e-01

Pos logit contributions
 aback+0.124
fired+0.114
 revenge+0.111
 closer+0.101
 medical+0.098
Neg logit contributions
pron-0.144
kin-0.137
uren-0.133
lf-0.117
Adam-0.116
Tokened
Token ID276
Feature activation+2.10e+00

Pos logit contributions
 aback+0.009
 closer+0.007
fired+0.007
 away+0.006
 revenge+0.006
Neg logit contributions
kin-0.023
pron-0.021
uren-0.020
omo-0.019
lf-0.019
Token the
Token ID262
Feature activation+1.03e+00

Pos logit contributions
 aback+0.036
 closer+0.032
fired+0.031
 revenge+0.029
 away+0.028
Neg logit contributions
kin-0.057
pron-0.053
uren-0.050
omo-0.045
lf-0.044
Token danger
Token ID3514
Feature activation+1.56e+00

Pos logit contributions
 aback+0.022
fired+0.020
 closer+0.019
 away+0.018
 revenge+0.017
Neg logit contributions
kin-0.024
pron-0.021
uren-0.020
omo-0.019
lf-0.018
Token with
Token ID351
Feature activation+7.56e-01

Pos logit contributions
 aback+0.029
 closer+0.026
fired+0.025
 away+0.025
 home+0.024
Neg logit contributions
kin-0.040
pron-0.039
uren-0.036
omo-0.034
Adam-0.032
Token little
Token ID1310
Feature activation+3.55e-01

Pos logit contributions
kin+0.011
pron+0.010
uren+0.009
Adam+0.008
omo+0.008
Neg logit contributions
 aback-0.010
 closer-0.010
fired-0.009
 home-0.009
 away-0.009
Token girl
Token ID2576
Feature activation+1.76e+00

Pos logit contributions
 aback+0.007
 closer+0.006
fired+0.006
 away+0.006
 home+0.006
Neg logit contributions
kin-0.009
pron-0.008
uren-0.008
lf-0.007
omo-0.007
Token remembered
Token ID12086
Feature activation+7.99e-01

Pos logit contributions
 aback+0.035
 closer+0.032
fired+0.031
 away+0.029
 home+0.029
Neg logit contributions
kin-0.044
pron-0.040
uren-0.037
omo-0.034
lf-0.033
Token the
Token ID262
Feature activation-1.55e-01

Pos logit contributions
 aback+0.013
 closer+0.012
fired+0.012
 home+0.011
 away+0.011
Neg logit contributions
kin-0.023
pron-0.021
uren-0.020
omo-0.018
bridge-0.018
Token earlier
Token ID2961
Feature activation+5.71e-01

Pos logit contributions
kin+0.004
pron+0.003
uren+0.003
omo+0.003
lf+0.003
Neg logit contributions
 aback-0.003
 closer-0.003
fired-0.003
 away-0.003
 revenge-0.003
Token fore
Token ID1674
Feature activation+6.32e+00

Pos logit contributions
 aback+0.012
 closer+0.010
fired+0.010
 away+0.010
 home+0.010
Neg logit contributions
kin-0.014
pron-0.013
uren-0.012
omo-0.011
lf-0.011
Tokenshadow
Token ID19106
Feature activation+1.01e-01

Pos logit contributions
 aback+0.130
fired+0.117
 revenge+0.114
 medical+0.104
 closer+0.103
Neg logit contributions
pron-0.138
kin-0.127
uren-0.124
ast-0.112
ae-0.112
Tokening
Token ID278
Feature activation-6.79e-01

Pos logit contributions
 aback+0.001
 closer+0.001
fired+0.001
 revenge+0.001
 away+0.001
Neg logit contributions
kin-0.003
pron-0.003
uren-0.003
Adam-0.003
omo-0.003
Token,
Token ID11
Feature activation-9.44e-01

Pos logit contributions
kin+0.017
pron+0.016
uren+0.015
omo+0.014
lf+0.014
Neg logit contributions
 aback-0.013
 closer-0.012
fired-0.011
 away-0.011
 home-0.011
Token and
Token ID290
Feature activation+6.66e-01

Pos logit contributions
kin+0.025
pron+0.022
uren+0.021
omo+0.020
lf+0.019
Neg logit contributions
 aback-0.018
 closer-0.017
 home-0.016
fired-0.015
 away-0.015
Token it
Token ID340
Feature activation+1.69e+00

Pos logit contributions
 aback+0.014
 closer+0.013
fired+0.013
 away+0.012
 revenge+0.012
Neg logit contributions
kin-0.015
pron-0.014
uren-0.013
lf-0.012
omo-0.012
Token again
Token ID757
Feature activation+2.30e+00

Pos logit contributions
kin+0.033
pron+0.031
uren+0.028
lf+0.026
omo+0.026
Neg logit contributions
 aback-0.025
 closer-0.022
fired-0.022
 revenge-0.020
 away-0.020
Token.
Token ID13
Feature activation+5.57e-01

Pos logit contributions
 aback+0.051
 closer+0.045
fired+0.045
 revenge+0.042
 away+0.041
Neg logit contributions
kin-0.051
pron-0.046
uren-0.043
lf-0.039
omo-0.038
Token But
Token ID887
Feature activation-1.08e+00

Pos logit contributions
 aback+0.012
fired+0.010
 closer+0.010
 home+0.010
 revenge+0.010
Neg logit contributions
kin-0.014
pron-0.013
uren-0.011
lf-0.011
omo-0.010
Token unb
Token ID22619
Feature activation+1.66e+00

Pos logit contributions
kin+0.023
pron+0.020
uren+0.019
lf+0.017
ae+0.016
Neg logit contributions
 aback-0.026
fired-0.023
 closer-0.023
 revenge-0.021
beh-0.021
Tokenek
Token ID988
Feature activation+1.37e+00

Pos logit contributions
 aback+0.031
 closer+0.027
fired+0.027
 revenge+0.025
 away+0.025
Neg logit contributions
kin-0.043
pron-0.040
uren-0.038
omo-0.034
lf-0.034
Tokennown
Token ID3408
Feature activation+6.15e+00

Pos logit contributions
 aback+0.024
fired+0.020
 closer+0.020
 away+0.020
 home+0.018
Neg logit contributions
kin-0.037
pron-0.035
uren-0.032
omo-0.030
Adam-0.030
Token to
Token ID284
Feature activation+1.26e+00

Pos logit contributions
 aback+0.088
 closer+0.072
fired+0.071
 revenge+0.070
 medical+0.066
Neg logit contributions
kin-0.170
pron-0.168
uren-0.157
Adam-0.146
addy-0.142
Token him
Token ID683
Feature activation+2.67e+00

Pos logit contributions
 aback+0.021
 closer+0.018
fired+0.017
 away+0.017
 home+0.017
Neg logit contributions
kin-0.036
pron-0.034
uren-0.032
omo-0.029
lf-0.029
Token,
Token ID11
Feature activation+6.83e-01

Pos logit contributions
 aback+0.048
 closer+0.043
fired+0.041
 away+0.039
 home+0.039
Neg logit contributions
kin-0.072
pron-0.067
uren-0.063
omo-0.058
lf-0.057
Token the
Token ID262
Feature activation-5.79e-01

Pos logit contributions
 aback+0.013
 closer+0.012
fired+0.011
 away+0.011
 home+0.011
Neg logit contributions
kin-0.018
pron-0.017
uren-0.015
omo-0.014
lf-0.014
Token king
Token ID5822
Feature activation+1.52e+00

Pos logit contributions
kin+0.014
pron+0.012
uren+0.012
omo+0.011
addy+0.010
Neg logit contributions
 closer-0.012
 aback-0.011
 home-0.011
 back-0.011
 away-0.011
Token.
Token ID13
Feature activation+7.95e-01

Pos logit contributions
 aback+0.007
fired+0.006
 closer+0.006
beh+0.005
 revenge+0.005
Neg logit contributions
kin-0.006
pron-0.005
uren-0.005
lf-0.004
 Ben-0.004
Token When
Token ID1649
Feature activation+1.19e+00

Pos logit contributions
 aback+0.016
fired+0.014
 home+0.013
 closer+0.013
 back+0.012
Neg logit contributions
kin-0.023
pron-0.021
lf-0.018
uren-0.017
omo-0.016
Token they
Token ID484
Feature activation-1.52e+00

Pos logit contributions
 aback+0.026
 closer+0.026
fired+0.025
 home+0.024
 away+0.024
Neg logit contributions
kin-0.026
pron-0.025
uren-0.022
omo-0.020
Adam-0.019
Token reached
Token ID4251
Feature activation+2.30e+00

Pos logit contributions
kin+0.036
pron+0.032
uren+0.030
lf+0.027
Adam+0.026
Neg logit contributions
 aback-0.032
fired-0.029
 closer-0.028
 revenge-0.026
beh-0.026
Token the
Token ID262
Feature activation+5.99e-01

Pos logit contributions
 aback+0.052
 closer+0.045
fired+0.045
beh+0.043
 revenge+0.042
Neg logit contributions
kin-0.051
pron-0.045
uren-0.042
ae-0.037
 moons-0.037
Token end
Token ID886
Feature activation+6.08e+00

Pos logit contributions
 aback+0.016
fired+0.014
beh+0.013
 closer+0.013
 revenge+0.013
Neg logit contributions
kin-0.011
pron-0.010
uren-0.009
 ceiling-0.008
 ma-0.008
Token of
Token ID286
Feature activation+8.75e-02

Pos logit contributions
 aback+0.139
fired+0.119
 revenge+0.117
 closer+0.115
beh+0.112
Neg logit contributions
kin-0.136
pron-0.118
uren-0.111
lf-0.101
omo-0.101
Token their
Token ID511
Feature activation+3.08e-01

Pos logit contributions
 aback+0.002
fired+0.002
 closer+0.002
beh+0.002
 revenge+0.002
Neg logit contributions
kin-0.002
pron-0.002
uren-0.001
lf-0.001
omo-0.001
Token adventure
Token ID8855
Feature activation+1.11e+00

Pos logit contributions
 aback+0.009
fired+0.007
 closer+0.007
beh+0.007
arling+0.007
Neg logit contributions
kin-0.005
pron-0.004
uren-0.004
 moons-0.004
lf-0.004
Token,
Token ID11
Feature activation-1.23e-01

Pos logit contributions
 aback+0.021
 closer+0.018
fired+0.018
 away+0.017
 revenge+0.017
Neg logit contributions
kin-0.029
pron-0.027
uren-0.025
omo-0.023
lf-0.023
Token they
Token ID484
Feature activation-2.04e+00

Pos logit contributions
kin+0.003
pron+0.003
uren+0.002
omo+0.002
Adam+0.002
Neg logit contributions
 aback-0.003
 closer-0.003
fired-0.003
 away-0.003
 home-0.002
Token
Token ID220
Feature activation-1.16e+00

Pos logit contributions
 aback+0.012
 closer+0.011
fired+0.010
 home+0.010
 away+0.010
Neg logit contributions
kin-0.013
pron-0.012
uren-0.011
lf-0.010
omo-0.010
Token
Token ID198
Feature activation-5.00e-02

Pos logit contributions
kin+0.030
pron+0.029
uren+0.026
lf+0.024
 moons+0.024
Neg logit contributions
 aback-0.023
fired-0.020
 closer-0.019
 home-0.018
 revenge-0.018
Token
Token ID198
Feature activation+6.12e-01

Pos logit contributions
kin+0.001
pron+0.001
uren+0.001
 moons+0.001
omo+0.001
Neg logit contributions
 aback-0.001
 closer-0.001
fired-0.001
 home-0.001
 away-0.001
TokenWith
Token ID3152
Feature activation+3.45e-01

Pos logit contributions
 aback+0.014
 closer+0.012
fired+0.011
 away+0.011
 unst+0.011
Neg logit contributions
kin-0.014
pron-0.013
uren-0.012
 moons-0.012
 scalp-0.011
Token the
Token ID262
Feature activation+1.76e-01

Pos logit contributions
 aback+0.007
fired+0.007
 closer+0.006
beh+0.006
 away+0.006
Neg logit contributions
kin-0.008
pron-0.007
uren-0.007
lf-0.006
Adam-0.006
Token key
Token ID1994
Feature activation+6.06e+00

Pos logit contributions
 aback+0.004
fired+0.004
beh+0.003
 closer+0.003
 revenge+0.003
Neg logit contributions
kin-0.004
pron-0.004
uren-0.003
lf-0.003
 ma-0.003
Token,
Token ID11
Feature activation-5.92e-01

Pos logit contributions
 aback+0.115
fired+0.102
 revenge+0.100
beh+0.100
 closer+0.093
Neg logit contributions
kin-0.145
pron-0.128
uren-0.119
lf-0.114
sheets-0.108
Token the
Token ID262
Feature activation-1.10e+00

Pos logit contributions
kin+0.015
pron+0.014
uren+0.013
omo+0.012
Adam+0.011
Neg logit contributions
 aback-0.012
 closer-0.011
fired-0.010
 away-0.010
 home-0.010
Token young
Token ID1862
Feature activation-9.17e-01

Pos logit contributions
kin+0.026
pron+0.024
uren+0.022
lf+0.020
omo+0.020
Neg logit contributions
 aback-0.023
fired-0.021
 closer-0.021
 away-0.019
 revenge-0.019
Token boy
Token ID2933
Feature activation+2.55e+00

Pos logit contributions
kin+0.024
pron+0.022
uren+0.021
ae+0.019
omo+0.018
Neg logit contributions
 aback-0.018
 closer-0.016
fired-0.015
 home-0.015
 away-0.015
Token was
Token ID373
Feature activation-6.74e-01

Pos logit contributions
 aback+0.056
 closer+0.050
fired+0.049
 revenge+0.047
 away+0.045
Neg logit contributions
kin-0.058
pron-0.053
uren-0.049
lf-0.044
omo-0.043
Token
Token ID220
Feature activation-1.02e+00

Pos logit contributions
 aback+0.012
 closer+0.010
fired+0.010
 home+0.010
 revenge+0.009
Neg logit contributions
kin-0.014
pron-0.013
uren-0.012
lf-0.011
omo-0.011
Token
Token ID198
Feature activation+1.90e-02

Pos logit contributions
kin+0.027
pron+0.026
uren+0.024
lf+0.022
 moons+0.021
Neg logit contributions
 aback-0.020
fired-0.017
 closer-0.017
 home-0.016
 unst-0.015
Token
Token ID198
Feature activation+6.89e-01

Pos logit contributions
 aback+0.000
 closer+0.000
fired+0.000
 home+0.000
 away+0.000
Neg logit contributions
kin-0.001
pron-0.000
uren-0.000
 moons-0.000
 scalp-0.000
TokenWith
Token ID3152
Feature activation+4.31e-01

Pos logit contributions
 aback+0.015
 closer+0.014
fired+0.013
 away+0.012
 nearer+0.012
Neg logit contributions
kin-0.016
pron-0.014
uren-0.013
 moons-0.013
 scalp-0.013
Token the
Token ID262
Feature activation+1.15e-01

Pos logit contributions
 aback+0.009
fired+0.008
 closer+0.008
beh+0.007
 away+0.007
Neg logit contributions
kin-0.010
pron-0.009
uren-0.009
lf-0.008
Adam-0.008
Token key
Token ID1994
Feature activation+6.04e+00

Pos logit contributions
 aback+0.002
fired+0.002
beh+0.002
 closer+0.002
 revenge+0.002
Neg logit contributions
kin-0.003
pron-0.002
uren-0.002
lf-0.002
 ma-0.002
Token,
Token ID11
Feature activation-4.66e-01

Pos logit contributions
 aback+0.113
fired+0.099
 revenge+0.097
beh+0.096
 closer+0.090
Neg logit contributions
kin-0.148
pron-0.131
uren-0.121
lf-0.116
sheets-0.110
Token the
Token ID262
Feature activation-1.11e+00

Pos logit contributions
kin+0.012
pron+0.011
uren+0.011
omo+0.010
Adam+0.009
Neg logit contributions
 aback-0.009
 closer-0.008
fired-0.008
 home-0.008
 away-0.007
Token young
Token ID1862
Feature activation-8.95e-01

Pos logit contributions
kin+0.027
pron+0.025
uren+0.023
lf+0.021
omo+0.021
Neg logit contributions
 aback-0.023
fired-0.020
 closer-0.020
 away-0.018
 revenge-0.018
Token boy
Token ID2933
Feature activation+2.57e+00

Pos logit contributions
kin+0.023
pron+0.021
uren+0.020
omo+0.018
ae+0.018
Neg logit contributions
 aback-0.018
 closer-0.016
fired-0.015
 home-0.015
 away-0.015
Token was
Token ID373
Feature activation-5.67e-01

Pos logit contributions
 aback+0.055
 closer+0.049
fired+0.049
 revenge+0.046
 away+0.045
Neg logit contributions
kin-0.059
pron-0.054
uren-0.050
lf-0.045
omo-0.045
Token earlier
Token ID2961
Feature activation-2.01e-01

Pos logit contributions
 aback+0.054
 closer+0.048
fired+0.048
 away+0.045
 revenge+0.045
Neg logit contributions
kin-0.061
pron-0.057
uren-0.053
omo-0.047
lf-0.047
Token and
Token ID290
Feature activation-1.95e-01

Pos logit contributions
kin+0.005
pron+0.005
uren+0.004
omo+0.004
 majesty+0.004
Neg logit contributions
 aback-0.004
 closer-0.003
 away-0.003
fired-0.003
 home-0.003
Token promised
Token ID8072
Feature activation+3.15e-01

Pos logit contributions
kin+0.005
pron+0.004
uren+0.004
omo+0.004
lf+0.003
Neg logit contributions
 aback-0.004
 closer-0.004
fired-0.004
 away-0.004
 home-0.003
Token to
Token ID284
Feature activation-3.45e-01

Pos logit contributions
 aback+0.005
 closer+0.005
fired+0.005
 away+0.004
 revenge+0.004
Neg logit contributions
kin-0.008
pron-0.008
uren-0.008
lf-0.007
Adam-0.007
Token call
Token ID869
Feature activation+6.18e-01

Pos logit contributions
kin+0.009
pron+0.008
uren+0.008
omo+0.007
 moons+0.007
Neg logit contributions
 aback-0.006
 closer-0.006
 away-0.006
 home-0.006
fired-0.006
Token back
Token ID736
Feature activation+6.03e+00

Pos logit contributions
 aback+0.011
fired+0.010
 closer+0.009
 revenge+0.009
beh+0.009
Neg logit contributions
kin-0.016
pron-0.015
uren-0.014
lf-0.012
Adam-0.012
Token.
Token ID13
Feature activation+8.89e-01

Pos logit contributions
 aback+0.121
fired+0.102
beh+0.102
 bitten+0.099
 unst+0.099
Neg logit contributions
kin-0.133
uren-0.122
pron-0.121
ae-0.115
 Avery-0.112
Token She
Token ID1375
Feature activation+1.77e-01

Pos logit contributions
 aback+0.021
 closer+0.019
fired+0.018
 away+0.017
 revenge+0.017
Neg logit contributions
kin-0.019
pron-0.018
uren-0.016
omo-0.014
lf-0.014
Token was
Token ID373
Feature activation-1.24e+00

Pos logit contributions
 aback+0.004
fired+0.004
 closer+0.004
 revenge+0.003
 home+0.003
Neg logit contributions
kin-0.004
pron-0.004
uren-0.003
omo-0.003
lf-0.003
Token afraid
Token ID7787
Feature activation-9.54e-01

Pos logit contributions
kin+0.032
pron+0.030
uren+0.028
omo+0.025
lf+0.025
Neg logit contributions
 aback-0.024
 closer-0.021
fired-0.021
 away-0.019
 revenge-0.019
Token that
Token ID326
Feature activation+1.10e+00

Pos logit contributions
kin+0.025
pron+0.024
uren+0.022
omo+0.020
lf+0.020
Neg logit contributions
 aback-0.018
 closer-0.016
fired-0.016
 away-0.015
 home-0.015
Token
Token ID198
Feature activation+3.19e-01

Pos logit contributions
kin+0.010
pron+0.009
uren+0.008
omo+0.007
 scalp+0.007
Neg logit contributions
 aback-0.009
 closer-0.008
fired-0.008
 home-0.007
 revenge-0.007
TokenGrand
Token ID23581
Feature activation-7.24e-01

Pos logit contributions
 aback+0.008
 closer+0.007
fired+0.007
 away+0.007
 home+0.006
Neg logit contributions
kin-0.007
pron-0.006
uren-0.005
 scalp-0.005
omo-0.005
Tokenma
Token ID2611
Feature activation+2.32e+00

Pos logit contributions
kin+0.017
pron+0.016
uren+0.015
omo+0.014
lf+0.013
Neg logit contributions
 aback-0.015
 closer-0.014
fired-0.013
 away-0.013
 revenge-0.013
Token's
Token ID338
Feature activation-7.62e-01

Pos logit contributions
 aback+0.049
 closer+0.045
fired+0.043
 away+0.041
 home+0.041
Neg logit contributions
kin-0.055
pron-0.051
uren-0.046
omo-0.041
lf-0.041
Token words
Token ID2456
Feature activation-1.46e+00

Pos logit contributions
kin+0.018
pron+0.016
uren+0.015
lf+0.014
omo+0.014
Neg logit contributions
 aback-0.016
 closer-0.015
 home-0.014
 revenge-0.014
 away-0.014
Token fore
Token ID1674
Feature activation+5.99e+00

Pos logit contributions
kin+0.035
pron+0.033
uren+0.031
omo+0.028
ae+0.028
Neg logit contributions
 aback-0.030
 closer-0.028
 away-0.026
fired-0.026
 home-0.025
Tokenshadow
Token ID19106
Feature activation+3.92e-01

Pos logit contributions
 aback+0.121
fired+0.116
 revenge+0.110
 home+0.100
 medical+0.097
Neg logit contributions
pron-0.131
kin-0.122
uren-0.120
ast-0.106
lf-0.104
Tokened
Token ID276
Feature activation+1.88e+00

Pos logit contributions
 aback+0.005
 closer+0.005
fired+0.004
 revenge+0.004
 away+0.004
Neg logit contributions
kin-0.012
pron-0.011
uren-0.011
omo-0.010
lf-0.010
Token a
Token ID257
Feature activation+2.18e+00

Pos logit contributions
 aback+0.029
fired+0.025
 closer+0.025
 revenge+0.022
 home+0.021
Neg logit contributions
kin-0.052
pron-0.048
uren-0.046
Adam-0.042
lf-0.041
Token happy
Token ID3772
Feature activation+1.42e+00

Pos logit contributions
 aback+0.048
fired+0.043
 closer+0.040
beh+0.040
 revenge+0.038
Neg logit contributions
pron-0.047
kin-0.047
uren-0.043
lf-0.038
omo-0.037
Token future
Token ID2003
Feature activation+6.63e-01

Pos logit contributions
 aback+0.032
 closer+0.029
fired+0.028
 home+0.027
 away+0.027
Neg logit contributions
kin-0.032
pron-0.029
uren-0.027
omo-0.024
Adam-0.024
Token it
Token ID340
Feature activation+1.50e+00

Pos logit contributions
 aback+0.026
 closer+0.026
 home+0.025
fired+0.025
 away+0.024
Neg logit contributions
kin-0.033
pron-0.032
uren-0.029
 scalp-0.025
ae-0.025
Token was
Token ID373
Feature activation+1.33e+00

Pos logit contributions
 aback+0.028
 closer+0.025
fired+0.025
 away+0.023
 revenge+0.023
Neg logit contributions
kin-0.039
pron-0.036
uren-0.034
omo-0.031
lf-0.030
Token time
Token ID640
Feature activation+3.14e+00

Pos logit contributions
 aback+0.033
 closer+0.032
 away+0.031
 home+0.031
 back+0.030
Neg logit contributions
kin-0.028
pron-0.025
uren-0.024
olo-0.021
lf-0.021
Token to
Token ID284
Feature activation+5.32e-01

Pos logit contributions
 aback+0.031
 closer+0.026
fired+0.024
 home+0.022
 away+0.022
Neg logit contributions
kin-0.110
pron-0.104
uren-0.099
omo-0.093
lf-0.093
Token come
Token ID1282
Feature activation+3.28e+00

Pos logit contributions
 home+0.008
 away+0.008
 closer+0.008
 aback+0.007
 back+0.007
Neg logit contributions
pron-0.016
kin-0.015
uren-0.014
ae-0.013
lf-0.013
Token back
Token ID736
Feature activation+5.97e+00

Pos logit contributions
 aback+0.037
beh+0.026
 revenge+0.025
fired+0.025
 medical+0.023
Neg logit contributions
kin-0.107
pron-0.098
uren-0.094
omo-0.090
ia-0.088
Token,
Token ID11
Feature activation+2.06e-02

Pos logit contributions
 aback+0.120
beh+0.107
 revenge+0.101
 medical+0.099
fired+0.095
Neg logit contributions
kin-0.129
pron-0.111
uren-0.111
 Ben-0.105
omo-0.105
Token the
Token ID262
Feature activation-7.20e-01

Pos logit contributions
 closer+0.000
 home+0.000
 away+0.000
 back+0.000
 down+0.000
Neg logit contributions
kin-0.001
pron-0.001
uren-0.000
 majesty-0.000
 moons-0.000
Token glad
Token ID9675
Feature activation+4.50e-01

Pos logit contributions
kin+0.019
pron+0.018
uren+0.017
ae+0.016
addy+0.016
Neg logit contributions
 closer-0.012
 home-0.012
 aback-0.012
 away-0.011
 back-0.011
Token bird
Token ID6512
Feature activation+2.61e+00

Pos logit contributions
 home+0.007
 closer+0.007
 aback+0.007
fired+0.006
 away+0.006
Neg logit contributions
kin-0.013
pron-0.013
uren-0.012
Adam-0.011
ae-0.011
Token flew
Token ID13112
Feature activation+1.39e+00

Pos logit contributions
 aback+0.053
 closer+0.049
fired+0.047
 away+0.046
 home+0.044
Neg logit contributions
kin-0.063
pron-0.059
uren-0.055
omo-0.049
Adam-0.049
Token:
Token ID25
Feature activation-4.18e-01

Pos logit contributions
kin+0.071
pron+0.068
uren+0.064
omo+0.056
lf+0.056
Neg logit contributions
 aback-0.054
 closer-0.050
fired-0.048
 away-0.046
 home-0.046
Token houses
Token ID7777
Feature activation-4.69e+00

Pos logit contributions
kin+0.010
pron+0.009
uren+0.009
omo+0.008
lf+0.008
Neg logit contributions
 aback-0.008
 closer-0.008
fired-0.007
 away-0.007
 home-0.007
Token,
Token ID11
Feature activation-3.22e+00

Pos logit contributions
kin+0.126
pron+0.122
uren+0.117
omo+0.105
addy+0.102
Neg logit contributions
 aback-0.080
 closer-0.075
 away-0.072
 home-0.069
fired-0.068
Token towers
Token ID18028
Feature activation-5.45e+00

Pos logit contributions
kin+0.074
pron+0.068
uren+0.064
ae+0.056
omo+0.056
Neg logit contributions
 aback-0.069
 closer-0.065
fired-0.061
 away-0.060
 home-0.058
Token,
Token ID11
Feature activation-4.01e+00

Pos logit contributions
kin+0.162
pron+0.162
uren+0.155
omo+0.135
addy+0.134
Neg logit contributions
 aback-0.072
 home-0.068
 away-0.067
 back-0.067
 closer-0.066
Token bridges
Token ID19432
Feature activation-7.50e+00

Pos logit contributions
kin+0.096
pron+0.088
uren+0.083
ae+0.074
omo+0.072
Neg logit contributions
 aback-0.082
 closer-0.079
 away-0.073
fired-0.072
 home-0.070
Token,
Token ID11
Feature activation-4.71e+00

Pos logit contributions
pron+0.209
kin+0.207
uren+0.198
omo+0.175
addy+0.171
Neg logit contributions
 aback-0.117
 away-0.109
 home-0.108
 closer-0.106
 back-0.104
Token cars
Token ID5006
Feature activation-4.42e+00

Pos logit contributions
kin+0.114
pron+0.106
uren+0.100
ae+0.089
omo+0.087
Neg logit contributions
 aback-0.094
 closer-0.092
 away-0.084
fired-0.081
 back-0.081
Token.
Token ID13
Feature activation-1.07e-01

Pos logit contributions
kin+0.119
pron+0.115
uren+0.108
ae+0.097
omo+0.097
Neg logit contributions
 aback-0.074
 closer-0.068
 away-0.067
 home-0.065
fired-0.064
Token One
Token ID1881
Feature activation-8.27e-01

Pos logit contributions
kin+0.003
pron+0.003
lf+0.002
uren+0.002
bridge+0.002
Neg logit contributions
 aback-0.002
 closer-0.002
 home-0.002
 back-0.002
fired-0.002
Token day
Token ID1110
Feature activation+1.85e+00

Pos logit contributions
kin+0.020
pron+0.018
uren+0.017
omo+0.015
lf+0.015
Neg logit contributions
 aback-0.018
 closer-0.016
fired-0.015
 away-0.014
 revenge-0.014
Token about
Token ID546
Feature activation-1.65e+00

Pos logit contributions
kin+0.031
pron+0.029
uren+0.027
lf+0.024
omo+0.024
Neg logit contributions
 aback-0.025
fired-0.022
 closer-0.022
 revenge-0.020
 away-0.020
Token numbers
Token ID3146
Feature activation-2.83e+00

Pos logit contributions
kin+0.039
pron+0.036
uren+0.033
lf+0.030
omo+0.030
Neg logit contributions
 aback-0.035
 closer-0.031
fired-0.031
 away-0.029
 revenge-0.028
Token,
Token ID11
Feature activation-4.78e+00

Pos logit contributions
kin+0.072
pron+0.068
uren+0.065
omo+0.059
lf+0.056
Neg logit contributions
 aback-0.052
 closer-0.049
 away-0.046
fired-0.046
 home-0.045
Token shapes
Token ID15268
Feature activation-6.58e+00

Pos logit contributions
kin+0.112
pron+0.103
uren+0.096
omo+0.086
ae+0.084
Neg logit contributions
 aback-0.100
 closer-0.096
 away-0.087
fired-0.087
 revenge-0.086
Token,
Token ID11
Feature activation-5.45e+00

Pos logit contributions
kin+0.178
pron+0.177
uren+0.170
omo+0.152
Adam+0.148
Neg logit contributions
 aback-0.106
 closer-0.098
 away-0.096
 home-0.094
 back-0.089
Token patterns
Token ID7572
Feature activation-7.39e+00

Pos logit contributions
kin+0.132
pron+0.123
uren+0.115
ae+0.103
omo+0.103
Neg logit contributions
 aback-0.109
 closer-0.103
 away-0.095
fired-0.093
 home-0.091
Token,
Token ID11
Feature activation-5.89e+00

Pos logit contributions
pron+0.197
kin+0.197
uren+0.188
omo+0.170
Adam+0.164
Neg logit contributions
 aback-0.120
 closer-0.109
 away-0.107
 home-0.105
fired-0.101
Token and
Token ID290
Feature activation-2.18e+00

Pos logit contributions
kin+0.147
pron+0.138
uren+0.129
omo+0.117
ae+0.117
Neg logit contributions
 aback-0.111
 closer-0.106
 away-0.098
 back-0.094
fired-0.094
Token more
Token ID517
Feature activation-2.04e+00

Pos logit contributions
kin+0.047
pron+0.044
uren+0.040
lf+0.036
omo+0.036
Neg logit contributions
 aback-0.049
fired-0.044
 closer-0.044
 away-0.041
 revenge-0.041
Token.
Token ID13
Feature activation+3.39e-02

Pos logit contributions
kin+0.051
pron+0.048
uren+0.045
omo+0.040
ae+0.039
Neg logit contributions
 aback-0.040
 closer-0.036
fired-0.035
 away-0.033
 home-0.033
Token Do
Token ID2141
Feature activation-1.75e+00

Pos logit contributions
 aback+0.001
 closer+0.001
fired+0.001
 revenge+0.001
 away+0.001
Neg logit contributions
kin-0.001
pron-0.001
uren-0.001
lf-0.001
omo-0.001
Token build
Token ID1382
Feature activation-3.54e+00

Pos logit contributions
kin+0.046
pron+0.042
uren+0.038
lf+0.034
omo+0.034
Neg logit contributions
 aback-0.047
 closer-0.042
fired-0.042
 revenge-0.039
 away-0.039
Token houses
Token ID7777
Feature activation-2.82e+00

Pos logit contributions
kin+0.079
pron+0.071
uren+0.064
lf+0.061
Adam+0.058
Neg logit contributions
 aback-0.078
fired-0.070
 closer-0.068
 revenge-0.065
beh-0.063
Token,
Token ID11
Feature activation-3.54e+00

Pos logit contributions
kin+0.064
pron+0.058
uren+0.052
lf+0.049
omo+0.047
Neg logit contributions
 aback-0.063
fired-0.056
 closer-0.054
 revenge-0.052
 away-0.049
Token towers
Token ID18028
Feature activation-4.89e+00

Pos logit contributions
kin+0.082
pron+0.075
uren+0.071
omo+0.063
ae+0.062
Neg logit contributions
 aback-0.076
 closer-0.072
fired-0.067
 away-0.066
 home-0.065
Token,
Token ID11
Feature activation-4.03e+00

Pos logit contributions
kin+0.136
pron+0.135
uren+0.129
omo+0.112
addy+0.111
Neg logit contributions
 aback-0.076
 closer-0.075
 away-0.073
 home-0.072
 back-0.072
Token bridges
Token ID19432
Feature activation-7.14e+00

Pos logit contributions
kin+0.100
pron+0.092
uren+0.087
ae+0.078
omo+0.077
Neg logit contributions
 aback-0.080
 closer-0.078
fired-0.071
 away-0.071
 home-0.069
Token and
Token ID290
Feature activation-1.63e+00

Pos logit contributions
pron+0.189
kin+0.189
uren+0.180
omo+0.159
addy+0.154
Neg logit contributions
 aback-0.122
 closer-0.113
 away-0.112
 home-0.111
 back-0.108
Token cars
Token ID5006
Feature activation-3.60e+00

Pos logit contributions
kin+0.034
pron+0.032
uren+0.029
lf+0.027
 moons+0.027
Neg logit contributions
 aback-0.038
fired-0.034
 closer-0.032
 revenge-0.031
 away-0.031
Token.
Token ID13
Feature activation-4.92e-02

Pos logit contributions
kin+0.090
pron+0.084
uren+0.079
omo+0.071
lf+0.070
Neg logit contributions
 aback-0.070
 closer-0.063
fired-0.062
 away-0.059
 home-0.058
Token They
Token ID1119
Feature activation-3.38e+00

Pos logit contributions
kin+0.001
pron+0.001
uren+0.001
lf+0.001
ae+0.001
Neg logit contributions
 aback-0.001
 closer-0.001
fired-0.001
 home-0.001
 revenge-0.001
Token had
Token ID550
Feature activation+7.78e-01

Pos logit contributions
kin+0.081
pron+0.078
uren+0.076
stand+0.068
ae+0.067
Neg logit contributions
 closer-0.062
 aback-0.059
 away-0.057
fired-0.055
 home-0.053
Token build
Token ID1382
Feature activation-3.71e+00

Pos logit contributions
kin+0.057
pron+0.053
uren+0.052
ae+0.044
omo+0.044
Neg logit contributions
 closer-0.041
 aback-0.040
 away-0.037
fired-0.036
 home-0.036
Token houses
Token ID7777
Feature activation-3.34e+00

Pos logit contributions
kin+0.079
pron+0.072
uren+0.066
omo+0.058
lf+0.058
Neg logit contributions
 aback-0.087
 closer-0.079
fired-0.078
 away-0.074
 revenge-0.073
Token,
Token ID11
Feature activation-3.54e+00

Pos logit contributions
kin+0.077
pron+0.070
uren+0.065
lf+0.059
omo+0.058
Neg logit contributions
 aback-0.072
fired-0.064
 closer-0.064
 revenge-0.060
 away-0.059
Token towers
Token ID18028
Feature activation-4.96e+00

Pos logit contributions
kin+0.075
pron+0.068
uren+0.063
omo+0.055
lf+0.055
Neg logit contributions
 aback-0.083
 closer-0.076
fired-0.075
 away-0.071
 revenge-0.071
Token,
Token ID11
Feature activation-3.89e+00

Pos logit contributions
kin+0.146
pron+0.145
uren+0.137
omo+0.121
ae+0.120
Neg logit contributions
 aback-0.070
 closer-0.067
 away-0.063
 home-0.063
 back-0.062
Token bridges
Token ID19432
Feature activation-7.14e+00

Pos logit contributions
kin+0.092
pron+0.085
uren+0.079
ae+0.070
omo+0.070
Neg logit contributions
 aback-0.082
 closer-0.078
fired-0.072
 away-0.072
 home-0.069
Token,
Token ID11
Feature activation-4.60e+00

Pos logit contributions
pron+0.201
kin+0.200
uren+0.191
omo+0.169
addy+0.165
Neg logit contributions
 aback-0.110
 closer-0.102
 away-0.099
 home-0.099
 back-0.096
Token and
Token ID290
Feature activation-1.26e+00

Pos logit contributions
kin+0.114
pron+0.106
uren+0.100
ae+0.088
omo+0.088
Neg logit contributions
 aback-0.090
 closer-0.088
 away-0.081
fired-0.079
 back-0.078
Token cars
Token ID5006
Feature activation-3.82e+00

Pos logit contributions
kin+0.031
pron+0.029
uren+0.027
lf+0.025
 moons+0.024
Neg logit contributions
 aback-0.025
fired-0.022
 closer-0.021
 revenge-0.020
 away-0.020
Token.
Token ID13
Feature activation+7.46e-02

Pos logit contributions
kin+0.100
pron+0.096
uren+0.091
omo+0.082
ae+0.080
Neg logit contributions
 aback-0.067
 closer-0.063
fired-0.060
 away-0.060
 home-0.058
Token Sometimes
Token ID8975
Feature activation-9.04e-01

Pos logit contributions
 aback+0.001
 closer+0.001
 home+0.001
fired+0.001
 away+0.001
Neg logit contributions
kin-0.002
pron-0.002
uren-0.002
lf-0.002
ae-0.001
Token trucks
Token ID13960
Feature activation-3.52e+00

Pos logit contributions
kin+0.026
pron+0.024
uren+0.022
omo+0.019
ae+0.019
Neg logit contributions
 aback-0.025
 closer-0.023
fired-0.022
 away-0.021
 revenge-0.021
Token of
Token ID286
Feature activation-1.65e+00

Pos logit contributions
kin+0.093
pron+0.089
uren+0.084
omo+0.075
lf+0.074
Neg logit contributions
 aback-0.064
 closer-0.058
fired-0.056
 away-0.055
 home-0.053
Token different
Token ID1180
Feature activation-3.04e+00

Pos logit contributions
kin+0.040
pron+0.037
uren+0.035
lf+0.031
Adam+0.031
Neg logit contributions
 aback-0.033
fired-0.030
 closer-0.029
 revenge-0.027
 away-0.027
Token colors
Token ID7577
Feature activation-6.28e+00

Pos logit contributions
kin+0.060
pron+0.054
uren+0.050
lf+0.044
omo+0.044
Neg logit contributions
 aback-0.075
 closer-0.069
fired-0.068
 away-0.064
 revenge-0.064
Token and
Token ID290
Feature activation-1.32e+00

Pos logit contributions
kin+0.193
pron+0.189
uren+0.189
ae+0.167
 majesty+0.167
Neg logit contributions
 closer-0.075
 aback-0.071
 away-0.070
 back-0.067
 home-0.066
Token sizes
Token ID10620
Feature activation-7.07e+00

Pos logit contributions
kin+0.021
pron+0.019
uren+0.017
ae+0.015
addy+0.014
Neg logit contributions
 aback-0.037
 closer-0.035
 away-0.034
fired-0.034
 revenge-0.033
Token.
Token ID13
Feature activation-9.44e-03

Pos logit contributions
pron+0.222
kin+0.219
uren+0.219
omo+0.192
ae+0.192
Neg logit contributions
 aback-0.079
 away-0.078
 closer-0.077
 home-0.074
 back-0.071
Token They
Token ID1119
Feature activation-3.31e+00

Pos logit contributions
kin+0.000
pron+0.000
uren+0.000
lf+0.000
 majesty+0.000
Neg logit contributions
 aback-0.000
 closer-0.000
fired-0.000
 home-0.000
 revenge-0.000
Token make
Token ID787
Feature activation-3.39e+00

Pos logit contributions
kin+0.095
pron+0.090
uren+0.084
ae+0.081
omo+0.077
Neg logit contributions
 closer-0.054
 away-0.051
 aback-0.050
 back-0.046
 home-0.044
Token noises
Token ID26782
Feature activation-4.03e+00

Pos logit contributions
kin+0.095
pron+0.087
uren+0.080
ae+0.073
omo+0.073
Neg logit contributions
 aback-0.060
 closer-0.060
 away-0.055
 home-0.053
 back-0.052
Token like
Token ID588
Feature activation-2.17e+00

Pos logit contributions
kin+0.116
pron+0.110
uren+0.104
omo+0.101
addy+0.097
Neg logit contributions
 closer-0.068
 aback-0.060
 away-0.060
 back-0.058
 home-0.053
Token make
Token ID787
Feature activation-3.28e+00

Pos logit contributions
kin+0.076
pron+0.071
uren+0.068
ae+0.062
omo+0.061
Neg logit contributions
 aback-0.059
 closer-0.058
 away-0.054
fired-0.053
 home-0.052
Token houses
Token ID7777
Feature activation-3.32e+00

Pos logit contributions
kin+0.083
pron+0.077
uren+0.074
omo+0.065
ae+0.062
Neg logit contributions
 closer-0.065
 aback-0.062
 away-0.059
 home-0.058
 back-0.057
Token,
Token ID11
Feature activation-3.39e+00

Pos logit contributions
kin+0.077
pron+0.071
uren+0.066
omo+0.059
lf+0.058
Neg logit contributions
 aback-0.071
 closer-0.065
fired-0.063
 away-0.060
 home-0.059
Token towers
Token ID18028
Feature activation-4.84e+00

Pos logit contributions
kin+0.080
pron+0.072
uren+0.069
ae+0.061
omo+0.060
Neg logit contributions
 aback-0.070
 closer-0.067
 away-0.062
fired-0.062
 home-0.060
Token,
Token ID11
Feature activation-3.86e+00

Pos logit contributions
kin+0.135
pron+0.133
uren+0.126
omo+0.112
Adam+0.110
Neg logit contributions
 aback-0.075
 closer-0.071
 home-0.068
 away-0.068
 back-0.066
Token bridges
Token ID19432
Feature activation-7.00e+00

Pos logit contributions
kin+0.095
pron+0.087
uren+0.083
ae+0.074
omo+0.073
Neg logit contributions
 aback-0.075
 closer-0.074
 away-0.068
fired-0.066
 back-0.066
Token and
Token ID290
Feature activation-1.66e+00

Pos logit contributions
pron+0.197
kin+0.196
uren+0.186
omo+0.167
addy+0.162
Neg logit contributions
 aback-0.106
 closer-0.098
 away-0.096
 home-0.096
 back-0.092
Token cars
Token ID5006
Feature activation-3.81e+00

Pos logit contributions
kin+0.039
pron+0.036
uren+0.034
lf+0.031
omo+0.030
Neg logit contributions
 aback-0.035
fired-0.031
 closer-0.030
 revenge-0.029
 away-0.028
Token with
Token ID351
Feature activation+8.42e-02

Pos logit contributions
kin+0.099
pron+0.094
uren+0.089
omo+0.080
ae+0.078
Neg logit contributions
 aback-0.069
 closer-0.064
fired-0.061
 away-0.060
 home-0.059
Token the
Token ID262
Feature activation-1.03e+00

Pos logit contributions
 aback+0.002
fired+0.002
 closer+0.002
 revenge+0.002
 away+0.002
Neg logit contributions
kin-0.002
pron-0.002
uren-0.001
lf-0.001
omo-0.001
Token blocks
Token ID7021
Feature activation-2.35e+00

Pos logit contributions
kin+0.024
pron+0.022
uren+0.021
omo+0.018
lf+0.018
Neg logit contributions
 aback-0.022
 closer-0.021
fired-0.019
 away-0.019
 home-0.019
Token make
Token ID787
Feature activation-2.85e+00

Pos logit contributions
kin+0.042
pron+0.038
uren+0.034
lf+0.032
Adam+0.029
Neg logit contributions
 aback-0.049
fired-0.044
 closer-0.042
beh-0.040
 revenge-0.040
Token houses
Token ID7777
Feature activation-3.10e+00

Pos logit contributions
kin+0.068
pron+0.064
uren+0.059
omo+0.053
lf+0.052
Neg logit contributions
 aback-0.059
 closer-0.055
fired-0.052
 away-0.051
 home-0.050
Token,
Token ID11
Feature activation-3.89e+00

Pos logit contributions
kin+0.078
pron+0.073
uren+0.069
omo+0.062
lf+0.061
Neg logit contributions
 aback-0.060
 closer-0.055
fired-0.052
 away-0.051
 home-0.049
Token castles
Token ID49203
Feature activation-5.21e+00

Pos logit contributions
kin+0.091
pron+0.085
uren+0.080
ae+0.071
omo+0.071
Neg logit contributions
 aback-0.082
 closer-0.079
 away-0.073
fired-0.071
 revenge-0.069
Token,
Token ID11
Feature activation-4.00e+00

Pos logit contributions
kin+0.138
pron+0.136
uren+0.132
omo+0.118
ae+0.116
Neg logit contributions
 aback-0.087
 away-0.084
 closer-0.084
 home-0.080
 back-0.079
Token bridges
Token ID19432
Feature activation-6.98e+00

Pos logit contributions
kin+0.099
pron+0.093
uren+0.089
ae+0.079
omo+0.079
Neg logit contributions
 aback-0.078
 closer-0.077
 away-0.071
fired-0.069
 back-0.067
Token and
Token ID290
Feature activation-1.47e+00

Pos logit contributions
kin+0.184
pron+0.183
uren+0.174
omo+0.155
ae+0.150
Neg logit contributions
 aback-0.120
 closer-0.112
 away-0.112
 home-0.108
fired-0.106
Token more
Token ID517
Feature activation-8.92e-01

Pos logit contributions
kin+0.031
pron+0.028
uren+0.026
 moons+0.024
lf+0.024
Neg logit contributions
 aback-0.034
fired-0.031
 closer-0.029
 revenge-0.028
 home-0.028
Token.
Token ID13
Feature activation-1.93e-01

Pos logit contributions
kin+0.021
pron+0.020
uren+0.018
omo+0.016
lf+0.016
Neg logit contributions
 aback-0.019
 closer-0.017
fired-0.017
 away-0.015
 revenge-0.015
Token
Token ID198
Feature activation-5.16e-02

Pos logit contributions
kin+0.005
pron+0.005
lf+0.005
uren+0.004
bridge+0.004
Neg logit contributions
 aback-0.003
 closer-0.003
 home-0.003
fired-0.003
 away-0.003
Token
Token ID198
Feature activation+9.66e-01

Pos logit contributions
kin+0.001
pron+0.001
uren+0.001
lf+0.001
 moons+0.001
Neg logit contributions
 aback-0.001
 closer-0.001
fired-0.001
 home-0.001
 away-0.001
Token cars
Token ID5006
Feature activation-3.00e+00

Pos logit contributions
kin+0.023
pron+0.021
uren+0.019
lf+0.017
omo+0.017
Neg logit contributions
 aback-0.023
 closer-0.021
fired-0.021
 revenge-0.020
 away-0.019
Token of
Token ID286
Feature activation-1.87e+00

Pos logit contributions
kin+0.075
pron+0.071
uren+0.066
omo+0.059
lf+0.059
Neg logit contributions
 aback-0.059
 closer-0.053
fired-0.052
 away-0.049
 home-0.048
Token different
Token ID1180
Feature activation-2.64e+00

Pos logit contributions
kin+0.048
pron+0.045
uren+0.042
omo+0.038
lf+0.038
Neg logit contributions
 aback-0.035
 closer-0.031
fired-0.031
 away-0.029
 revenge-0.029
Token colors
Token ID7577
Feature activation-6.07e+00

Pos logit contributions
kin+0.048
pron+0.043
uren+0.039
omo+0.033
lf+0.033
Neg logit contributions
 aback-0.070
 closer-0.065
fired-0.064
 away-0.061
 revenge-0.061
Token and
Token ID290
Feature activation-1.20e+00

Pos logit contributions
kin+0.164
uren+0.162
pron+0.162
ae+0.142
 majesty+0.140
Neg logit contributions
 aback-0.097
 closer-0.090
 away-0.087
 back-0.084
 home-0.083
Token sizes
Token ID10620
Feature activation-6.95e+00

Pos logit contributions
kin+0.021
pron+0.019
uren+0.017
ae+0.015
addy+0.014
Neg logit contributions
 aback-0.031
 closer-0.029
fired-0.028
 away-0.028
 revenge-0.028
Token.
Token ID13
Feature activation-4.15e-01

Pos logit contributions
pron+0.212
uren+0.210
kin+0.209
ae+0.186
omo+0.184
Neg logit contributions
 aback-0.090
 away-0.082
 closer-0.080
 home-0.079
 back-0.075
Token He
Token ID679
Feature activation-1.77e+00

Pos logit contributions
kin+0.012
pron+0.011
uren+0.010
lf+0.009
 majesty+0.009
Neg logit contributions
 aback-0.007
 closer-0.006
 home-0.006
fired-0.006
 back-0.006
Token liked
Token ID8288
Feature activation-7.52e-01

Pos logit contributions
kin+0.042
pron+0.039
uren+0.038
ae+0.035
 unison+0.034
Neg logit contributions
 closer-0.031
 aback-0.030
fired-0.029
 away-0.029
 back-0.027
Token to
Token ID284
Feature activation-1.06e+00

Pos logit contributions
kin+0.028
pron+0.026
uren+0.025
ae+0.024
omo+0.024
Neg logit contributions
 aback-0.005
 closer-0.005
fired-0.004
 home-0.004
 away-0.004
Token make
Token ID787
Feature activation-2.61e+00

Pos logit contributions
kin+0.028
pron+0.026
uren+0.024
ae+0.023
omo+0.022
Neg logit contributions
 aback-0.018
 closer-0.018
 away-0.017
fired-0.016
 revenge-0.016
Token had
Token ID550
Feature activation+4.98e-01

Pos logit contributions
kin+0.078
pron+0.073
uren+0.068
ae+0.062
Adam+0.059
Neg logit contributions
 aback-0.066
 closer-0.065
fired-0.061
 away-0.060
 home-0.059
Token many
Token ID867
Feature activation-9.06e-01

Pos logit contributions
 aback+0.007
 closer+0.007
 home+0.006
fired+0.006
 away+0.006
Neg logit contributions
kin-0.015
pron-0.014
uren-0.013
lf-0.012
omo-0.012
Token dolls
Token ID36062
Feature activation-2.56e+00

Pos logit contributions
kin+0.015
pron+0.013
lf+0.011
omo+0.011
uren+0.011
Neg logit contributions
 aback-0.026
fired-0.024
 closer-0.024
 nearer-0.023
 revenge-0.023
Token of
Token ID286
Feature activation-1.87e+00

Pos logit contributions
kin+0.064
pron+0.060
uren+0.056
omo+0.051
lf+0.050
Neg logit contributions
 aback-0.050
 closer-0.045
fired-0.044
 away-0.041
 home-0.041
Token different
Token ID1180
Feature activation-2.71e+00

Pos logit contributions
kin+0.045
pron+0.042
uren+0.039
omo+0.036
lf+0.035
Neg logit contributions
 aback-0.038
fired-0.034
 closer-0.033
 away-0.030
 revenge-0.030
Token sizes
Token ID10620
Feature activation-6.95e+00

Pos logit contributions
kin+0.044
pron+0.038
uren+0.035
lf+0.030
omo+0.030
Neg logit contributions
 aback-0.076
 closer-0.071
fired-0.070
 revenge-0.066
 away-0.065
Token and
Token ID290
Feature activation-1.64e+00

Pos logit contributions
pron+0.197
kin+0.193
uren+0.192
ae+0.169
Adam+0.165
Neg logit contributions
 aback-0.107
 closer-0.095
 away-0.094
 home-0.093
fired-0.089
Token colors
Token ID7577
Feature activation-6.07e+00

Pos logit contributions
kin+0.030
pron+0.027
uren+0.024
ae+0.021
Adam+0.020
Neg logit contributions
 aback-0.042
 closer-0.040
fired-0.039
 away-0.038
 revenge-0.037
Token.
Token ID13
Feature activation+4.28e-02

Pos logit contributions
kin+0.169
pron+0.165
uren+0.161
ae+0.143
Adam+0.142
Neg logit contributions
 aback-0.095
 closer-0.090
 away-0.085
 home-0.081
fired-0.080
Token They
Token ID1119
Feature activation-3.29e+00

Pos logit contributions
 aback+0.001
 closer+0.001
 home+0.001
fired+0.001
 away+0.001
Neg logit contributions
kin-0.001
pron-0.001
uren-0.001
lf-0.001
 majesty-0.001
Token also
Token ID635
Feature activation+1.15e-01

Pos logit contributions
kin+0.079
pron+0.074
uren+0.071
ae+0.065
stand+0.062
Neg logit contributions
 closer-0.062
 aback-0.059
 away-0.058
fired-0.054
 home-0.054
Token build
Token ID1382
Feature activation-3.52e+00

Pos logit contributions
kin+0.059
pron+0.054
uren+0.052
ae+0.045
omo+0.044
Neg logit contributions
 closer-0.043
 aback-0.040
 away-0.039
 home-0.037
fired-0.037
Token towers
Token ID18028
Feature activation-4.15e+00

Pos logit contributions
kin+0.077
pron+0.070
uren+0.065
lf+0.058
omo+0.057
Neg logit contributions
 aback-0.080
 closer-0.072
fired-0.072
 revenge-0.067
 away-0.067
Token,
Token ID11
Feature activation-3.71e+00

Pos logit contributions
kin+0.105
pron+0.099
uren+0.093
omo+0.083
lf+0.080
Neg logit contributions
 aback-0.079
 closer-0.074
fired-0.069
 away-0.069
 home-0.068
Token houses
Token ID7777
Feature activation-4.37e+00

Pos logit contributions
kin+0.084
pron+0.077
uren+0.072
omo+0.063
ae+0.062
Neg logit contributions
 aback-0.081
 closer-0.078
fired-0.072
 away-0.071
 home-0.069
Token,
Token ID11
Feature activation-3.80e+00

Pos logit contributions
kin+0.114
pron+0.108
uren+0.101
omo+0.091
Adam+0.089
Neg logit contributions
 aback-0.080
 closer-0.074
fired-0.069
 away-0.068
 home-0.067
Token bridges
Token ID19432
Feature activation-6.94e+00

Pos logit contributions
kin+0.093
pron+0.085
uren+0.080
ae+0.071
omo+0.071
Neg logit contributions
 aback-0.076
 closer-0.074
 away-0.068
fired-0.067
 home-0.065
Token and
Token ID290
Feature activation-1.55e+00

Pos logit contributions
kin+0.192
pron+0.190
uren+0.179
omo+0.160
addy+0.156
Neg logit contributions
 aback-0.111
 closer-0.102
 away-0.099
 home-0.099
fired-0.095
Token anything
Token ID1997
Feature activation-1.71e+00

Pos logit contributions
kin+0.035
pron+0.032
uren+0.030
lf+0.028
 moons+0.028
Neg logit contributions
 aback-0.034
fired-0.030
 closer-0.029
 revenge-0.028
 away-0.027
Token they
Token ID484
Feature activation-4.52e+00

Pos logit contributions
kin+0.034
pron+0.033
uren+0.030
omo+0.026
ae+0.026
Neg logit contributions
 aback-0.041
 closer-0.038
fired-0.037
 away-0.036
 revenge-0.036
Token wanted
Token ID2227
Feature activation-6.54e-01

Pos logit contributions
kin+0.101
pron+0.094
uren+0.090
omo+0.081
ae+0.078
Neg logit contributions
 aback-0.096
 closer-0.090
fired-0.087
 away-0.086
 revenge-0.083
Token with
Token ID351
Feature activation+3.01e-02

Pos logit contributions
kin+0.016
pron+0.014
uren+0.013
lf+0.012
omo+0.012
Neg logit contributions
 aback-0.014
fired-0.012
 closer-0.012
 revenge-0.011
 away-0.011
Token.
Token ID13
Feature activation+2.16e-01

Pos logit contributions
pron+0.211
uren+0.207
kin+0.202
Adam+0.181
omo+0.181
Neg logit contributions
 aback-0.076
 closer-0.074
 away-0.073
 home-0.068
 back-0.068
Token They
Token ID1119
Feature activation-3.18e+00

Pos logit contributions
 aback+0.005
 closer+0.005
fired+0.004
 home+0.004
 away+0.004
Neg logit contributions
kin-0.005
pron-0.005
uren-0.004
lf-0.004
ae-0.004
Token make
Token ID787
Feature activation-3.49e+00

Pos logit contributions
kin+0.089
pron+0.087
uren+0.082
omo+0.078
ae+0.078
Neg logit contributions
 closer-0.051
 away-0.048
 aback-0.045
 back-0.043
 home-0.041
Token pictures
Token ID5986
Feature activation-4.74e+00

Pos logit contributions
kin+0.084
pron+0.082
uren+0.075
omo+0.070
Adam+0.064
Neg logit contributions
 closer-0.072
 aback-0.068
 away-0.066
 home-0.065
 back-0.064
Token and
Token ID290
Feature activation-5.69e-01

Pos logit contributions
kin+0.136
pron+0.132
uren+0.126
omo+0.114
ae+0.112
Neg logit contributions
 aback-0.071
 closer-0.071
 away-0.062
 home-0.060
 back-0.060
Token patterns
Token ID7572
Feature activation-6.90e+00

Pos logit contributions
kin+0.011
pron+0.010
uren+0.009
ae+0.008
addy+0.008
Neg logit contributions
 closer-0.014
 aback-0.014
 away-0.013
fired-0.012
 home-0.012
Token with
Token ID351
Feature activation-3.50e-01

Pos logit contributions
pron+0.199
kin+0.197
uren+0.191
omo+0.173
Adam+0.169
Neg logit contributions
 closer-0.099
 aback-0.097
 away-0.089
 back-0.084
 home-0.083
Token them
Token ID606
Feature activation-1.50e+00

Pos logit contributions
kin+0.008
pron+0.008
uren+0.007
omo+0.006
ae+0.006
Neg logit contributions
 aback-0.007
 closer-0.007
 away-0.007
 home-0.007
fired-0.007
Token on
Token ID319
Feature activation-1.19e-01

Pos logit contributions
kin+0.042
pron+0.041
uren+0.039
omo+0.036
Adam+0.035
Neg logit contributions
 closer-0.023
 aback-0.023
 away-0.022
 home-0.021
fired-0.020
Token the
Token ID262
Feature activation-1.44e+00

Pos logit contributions
kin+0.003
pron+0.003
uren+0.003
omo+0.003
ae+0.003
Neg logit contributions
 aback-0.002
 closer-0.002
 away-0.002
 home-0.002
 back-0.001
Token floor
Token ID4314
Feature activation-3.25e+00

Pos logit contributions
kin+0.028
pron+0.026
uren+0.024
omo+0.022
Adam+0.021
Neg logit contributions
 aback-0.034
 closer-0.033
 away-0.032
 home-0.032
fired-0.031
Token trucks
Token ID13960
Feature activation-3.32e+00

Pos logit contributions
kin+0.026
pron+0.024
uren+0.022
omo+0.020
ae+0.020
Neg logit contributions
 aback-0.025
 closer-0.023
fired-0.022
 away-0.021
 revenge-0.021
Token of
Token ID286
Feature activation-1.60e+00

Pos logit contributions
kin+0.084
pron+0.079
uren+0.075
omo+0.067
ae+0.066
Neg logit contributions
 aback-0.064
 closer-0.059
 away-0.056
fired-0.056
 home-0.055
Token different
Token ID1180
Feature activation-2.79e+00

Pos logit contributions
kin+0.040
pron+0.037
uren+0.035
lf+0.032
omo+0.032
Neg logit contributions
 aback-0.031
 closer-0.028
fired-0.027
 away-0.025
 revenge-0.025
Token colors
Token ID7577
Feature activation-5.89e+00

Pos logit contributions
kin+0.055
pron+0.050
uren+0.045
lf+0.040
omo+0.040
Neg logit contributions
 aback-0.069
 closer-0.064
fired-0.062
 revenge-0.059
 away-0.059
Token and
Token ID290
Feature activation-1.49e+00

Pos logit contributions
kin+0.166
uren+0.162
pron+0.161
ae+0.141
 majesty+0.139
Neg logit contributions
 aback-0.086
 closer-0.085
 away-0.081
 back-0.080
 home-0.079
Token sizes
Token ID10620
Feature activation-6.87e+00

Pos logit contributions
kin+0.026
pron+0.024
uren+0.021
ae+0.018
omo+0.018
Neg logit contributions
 aback-0.040
 closer-0.038
fired-0.037
 away-0.036
 revenge-0.036
Token.
Token ID13
Feature activation-2.14e-01

Pos logit contributions
kin+0.202
pron+0.202
uren+0.197
omo+0.174
ae+0.173
Neg logit contributions
 aback-0.095
 closer-0.088
 away-0.088
 home-0.085
 back-0.083
Token He
Token ID679
Feature activation-1.27e+00

Pos logit contributions
kin+0.006
pron+0.006
uren+0.005
lf+0.005
ae+0.005
Neg logit contributions
 aback-0.004
 closer-0.003
fired-0.003
 home-0.003
 revenge-0.003
Token liked
Token ID8288
Feature activation-1.49e+00

Pos logit contributions
kin+0.032
pron+0.030
uren+0.028
ae+0.025
utes+0.025
Neg logit contributions
 closer-0.022
 aback-0.022
fired-0.020
 away-0.020
 back-0.019
Token to
Token ID284
Feature activation-1.02e+00

Pos logit contributions
kin+0.052
pron+0.048
uren+0.046
ae+0.043
omo+0.043
Neg logit contributions
 aback-0.014
 closer-0.013
fired-0.012
 home-0.011
 revenge-0.011
Token make
Token ID787
Feature activation-2.58e+00

Pos logit contributions
kin+0.026
pron+0.024
uren+0.023
omo+0.020
ae+0.020
Neg logit contributions
 aback-0.019
 closer-0.017
fired-0.017
 away-0.017
 home-0.016
Token cars
Token ID5006
Feature activation-2.78e+00

Pos logit contributions
kin+0.014
pron+0.013
lf+0.011
uren+0.011
omo+0.011
Neg logit contributions
 aback-0.018
fired-0.016
 closer-0.016
 revenge-0.015
 nearer-0.015
Token of
Token ID286
Feature activation-1.86e+00

Pos logit contributions
kin+0.070
pron+0.065
uren+0.061
omo+0.055
lf+0.054
Neg logit contributions
 aback-0.055
 closer-0.049
fired-0.048
 away-0.045
 home-0.045
Token different
Token ID1180
Feature activation-2.80e+00

Pos logit contributions
kin+0.045
pron+0.042
uren+0.039
lf+0.036
omo+0.036
Neg logit contributions
 aback-0.037
fired-0.033
 closer-0.032
 revenge-0.030
 away-0.029
Token colors
Token ID7577
Feature activation-5.98e+00

Pos logit contributions
kin+0.049
pron+0.044
uren+0.040
omo+0.034
lf+0.034
Neg logit contributions
 aback-0.076
 closer-0.070
fired-0.069
 away-0.066
 revenge-0.066
Token and
Token ID290
Feature activation-1.49e+00

Pos logit contributions
kin+0.168
pron+0.168
uren+0.166
ae+0.147
Adam+0.144
Neg logit contributions
 aback-0.083
 closer-0.083
 back-0.079
 away-0.079
 home-0.076
Token sizes
Token ID10620
Feature activation-6.86e+00

Pos logit contributions
kin+0.024
pron+0.022
uren+0.019
ae+0.017
addy+0.016
Neg logit contributions
 aback-0.041
 closer-0.039
 away-0.037
fired-0.037
 revenge-0.037
Token,
Token ID11
Feature activation-4.75e+00

Pos logit contributions
pron+0.215
kin+0.211
uren+0.211
ae+0.187
omo+0.186
Neg logit contributions
 aback-0.080
 away-0.077
 closer-0.076
 back-0.073
 home-0.072
Token but
Token ID475
Feature activation-1.39e+00

Pos logit contributions
kin+0.127
pron+0.118
uren+0.110
ae+0.105
addy+0.100
Neg logit contributions
 closer-0.087
 aback-0.078
 away-0.073
 revenge-0.069
 back-0.068
Token their
Token ID511
Feature activation-2.44e+00

Pos logit contributions
kin+0.030
pron+0.028
uren+0.026
lf+0.023
Adam+0.022
Neg logit contributions
 aback-0.031
 closer-0.030
fired-0.028
 away-0.027
 home-0.027
Token favorite
Token ID4004
Feature activation-2.03e+00

Pos logit contributions
kin+0.063
pron+0.058
uren+0.056
ae+0.050
Adam+0.049
Neg logit contributions
 aback-0.043
 home-0.043
 closer-0.042
 away-0.041
 revenge-0.040
Token ones
Token ID3392
Feature activation-3.55e+00

Pos logit contributions
kin+0.049
pron+0.046
uren+0.043
omo+0.038
Adam+0.038
Neg logit contributions
 aback-0.040
 closer-0.037
fired-0.036
 away-0.034
 home-0.034
Token trucks
Token ID13960
Feature activation-3.34e+00

Pos logit contributions
kin+0.026
pron+0.024
uren+0.022
ae+0.019
omo+0.019
Neg logit contributions
 aback-0.022
 closer-0.021
fired-0.020
 away-0.019
 revenge-0.019
Token of
Token ID286
Feature activation-1.45e+00

Pos logit contributions
kin+0.090
pron+0.086
uren+0.082
omo+0.074
ae+0.072
Neg logit contributions
 aback-0.058
 closer-0.053
fired-0.051
 away-0.051
 home-0.049
Token different
Token ID1180
Feature activation-2.77e+00

Pos logit contributions
kin+0.036
pron+0.033
uren+0.031
lf+0.028
omo+0.028
Neg logit contributions
 aback-0.029
fired-0.026
 closer-0.025
 away-0.023
 revenge-0.023
Token colors
Token ID7577
Feature activation-5.96e+00

Pos logit contributions
kin+0.053
pron+0.048
uren+0.044
omo+0.039
lf+0.039
Neg logit contributions
 aback-0.070
 closer-0.064
fired-0.063
 revenge-0.059
 away-0.059
Token and
Token ID290
Feature activation-1.21e+00

Pos logit contributions
kin+0.183
uren+0.181
pron+0.179
 majesty+0.160
ae+0.160
Neg logit contributions
 closer-0.071
 away-0.067
 aback-0.066
 back-0.064
 home-0.063
Token sizes
Token ID10620
Feature activation-6.86e+00

Pos logit contributions
kin+0.020
pron+0.018
uren+0.016
ae+0.014
addy+0.013
Neg logit contributions
 aback-0.034
 closer-0.032
 away-0.031
fired-0.031
 revenge-0.030
Token.
Token ID13
Feature activation-1.21e-01

Pos logit contributions
pron+0.215
uren+0.214
kin+0.214
omo+0.189
ae+0.188
Neg logit contributions
 away-0.077
 aback-0.076
 closer-0.074
 home-0.072
 back-0.070
Token Ben
Token ID3932
Feature activation-2.02e-01

Pos logit contributions
kin+0.003
pron+0.003
lf+0.003
bridge+0.003
uren+0.003
Neg logit contributions
 aback-0.002
 closer-0.002
 home-0.002
fired-0.002
 revenge-0.002
Token likes
Token ID7832
Feature activation-5.30e-01

Pos logit contributions
kin+0.005
pron+0.005
uren+0.004
 scalp+0.004
ae+0.004
Neg logit contributions
 aback-0.004
 closer-0.004
fired-0.004
 back-0.003
 away-0.003
Token to
Token ID284
Feature activation-4.35e-01

Pos logit contributions
kin+0.019
pron+0.017
uren+0.017
omo+0.015
ae+0.015
Neg logit contributions
 aback-0.005
 closer-0.004
fired-0.004
 home-0.004
 away-0.004
Token make
Token ID787
Feature activation-2.30e+00

Pos logit contributions
kin+0.011
pron+0.010
uren+0.010
ae+0.009
omo+0.009
Neg logit contributions
 aback-0.008
 closer-0.008
fired-0.007
 away-0.007
 revenge-0.007
Token cars
Token ID5006
Feature activation-2.92e+00

Pos logit contributions
kin+0.013
pron+0.012
uren+0.011
lf+0.011
omo+0.010
Neg logit contributions
 aback-0.018
fired-0.016
 closer-0.016
 revenge-0.015
 nearer-0.015
Token of
Token ID286
Feature activation-1.76e+00

Pos logit contributions
kin+0.075
pron+0.071
uren+0.067
omo+0.059
ae+0.059
Neg logit contributions
 aback-0.055
 closer-0.050
fired-0.049
 away-0.047
 home-0.047
Token different
Token ID1180
Feature activation-2.61e+00

Pos logit contributions
kin+0.042
pron+0.039
uren+0.037
lf+0.034
omo+0.033
Neg logit contributions
 aback-0.036
fired-0.032
 closer-0.031
 revenge-0.029
 away-0.029
Token colors
Token ID7577
Feature activation-5.97e+00

Pos logit contributions
kin+0.047
pron+0.042
uren+0.038
omo+0.032
lf+0.032
Neg logit contributions
 aback-0.070
 closer-0.064
fired-0.064
 away-0.061
 revenge-0.060
Token and
Token ID290
Feature activation-1.26e+00

Pos logit contributions
uren+0.181
pron+0.180
kin+0.180
 majesty+0.161
ae+0.160
Neg logit contributions
 closer-0.070
 back-0.068
 away-0.067
 aback-0.066
 home-0.065
Token sizes
Token ID10620
Feature activation-6.83e+00

Pos logit contributions
kin+0.020
pron+0.018
uren+0.015
ae+0.013
omo+0.012
Neg logit contributions
 aback-0.037
 closer-0.035
fired-0.033
 away-0.033
 revenge-0.032
Token.
Token ID13
Feature activation-2.59e-02

Pos logit contributions
pron+0.222
uren+0.220
kin+0.216
ae+0.194
omo+0.191
Neg logit contributions
 away-0.071
 aback-0.070
 closer-0.069
 back-0.067
 home-0.066
Token They
Token ID1119
Feature activation-3.13e+00

Pos logit contributions
kin+0.001
pron+0.001
uren+0.000
omo+0.000
lf+0.000
Neg logit contributions
 aback-0.001
 closer-0.001
fired-0.001
 away-0.001
 revenge-0.000
Token make
Token ID787
Feature activation-3.20e+00

Pos logit contributions
kin+0.089
pron+0.084
uren+0.079
ae+0.077
addy+0.073
Neg logit contributions
 closer-0.052
 away-0.049
 aback-0.048
 back-0.045
 home-0.043
Token sounds
Token ID5238
Feature activation-4.48e+00

Pos logit contributions
kin+0.092
pron+0.085
uren+0.078
ae+0.071
omo+0.071
Neg logit contributions
 closer-0.055
 aback-0.054
 away-0.050
 home-0.049
 back-0.048
Token like
Token ID588
Feature activation-2.23e+00

Pos logit contributions
kin+0.143
pron+0.136
uren+0.134
ae+0.128
addy+0.126
Neg logit contributions
 closer-0.065
 back-0.055
 away-0.050
 down-0.047
 more-0.047
Token cars
Token ID5006
Feature activation-2.40e+00

Pos logit contributions
pron+0.059
kin+0.059
uren+0.052
ae+0.050
omo+0.049
Neg logit contributions
 aback-0.038
 away-0.035
 closer-0.034
 back-0.032
fired-0.032
Token of
Token ID286
Feature activation-1.46e+00

Pos logit contributions
kin+0.065
pron+0.062
uren+0.058
omo+0.053
ae+0.052
Neg logit contributions
 aback-0.043
 closer-0.039
 away-0.037
fired-0.037
 home-0.036
Token different
Token ID1180
Feature activation-2.58e+00

Pos logit contributions
kin+0.035
pron+0.033
uren+0.030
lf+0.028
omo+0.027
Neg logit contributions
 aback-0.030
 closer-0.026
fired-0.026
 revenge-0.024
 away-0.024
Token colors
Token ID7577
Feature activation-5.92e+00

Pos logit contributions
kin+0.052
pron+0.048
uren+0.044
omo+0.037
lf+0.037
Neg logit contributions
 aback-0.064
 closer-0.058
fired-0.057
 away-0.055
 home-0.054
Token and
Token ID290
Feature activation-8.90e-01

Pos logit contributions
kin+0.167
pron+0.166
uren+0.164
ae+0.144
omo+0.142
Neg logit contributions
 aback-0.086
 closer-0.085
 away-0.083
 back-0.082
 home-0.079
Token sizes
Token ID10620
Feature activation-6.83e+00

Pos logit contributions
kin+0.015
pron+0.014
uren+0.011
ae+0.010
addy+0.009
Neg logit contributions
 aback-0.025
 closer-0.023
fired-0.023
 away-0.022
 home-0.022
Token.
Token ID13
Feature activation+3.55e-01

Pos logit contributions
pron+0.217
kin+0.213
uren+0.212
omo+0.189
ae+0.188
Neg logit contributions
 aback-0.078
 away-0.076
 closer-0.074
 home-0.072
 back-0.072
Token He
Token ID679
Feature activation-1.61e+00

Pos logit contributions
 aback+0.008
 closer+0.007
fired+0.007
 away+0.007
 revenge+0.007
Neg logit contributions
kin-0.007
pron-0.007
uren-0.006
omo-0.006
lf-0.005
Token makes
Token ID1838
Feature activation-3.26e+00

Pos logit contributions
kin+0.043
pron+0.041
uren+0.036
ae+0.035
omo+0.033
Neg logit contributions
 closer-0.029
 aback-0.028
 away-0.027
 back-0.026
fired-0.025
Token them
Token ID606
Feature activation-6.68e-01

Pos logit contributions
kin+0.099
pron+0.092
uren+0.083
ae+0.079
omo+0.078
Neg logit contributions
 closer-0.052
 aback-0.051
 away-0.047
 home-0.046
 back-0.045
Token go
Token ID467
Feature activation+2.68e+00

Pos logit contributions
kin+0.017
pron+0.016
uren+0.015
ae+0.013
lf+0.013
Neg logit contributions
 closer-0.013
 aback-0.013
 away-0.012
 home-0.012
fired-0.011
Token skirts
Token ID42370
Feature activation-3.74e+00

Pos logit contributions
kin+0.021
pron+0.020
uren+0.018
Adam+0.016
ae+0.016
Neg logit contributions
 aback-0.030
 closer-0.028
 away-0.027
fired-0.027
 home-0.027
Token of
Token ID286
Feature activation-2.68e+00

Pos logit contributions
kin+0.102
pron+0.098
uren+0.097
omo+0.089
Adam+0.089
Neg logit contributions
 aback-0.058
 closer-0.056
 away-0.055
 home-0.054
 back-0.052
Token different
Token ID1180
Feature activation-2.80e+00

Pos logit contributions
kin+0.063
pron+0.057
uren+0.055
ae+0.050
omo+0.050
Neg logit contributions
 aback-0.055
 closer-0.052
 away-0.050
 home-0.050
 back-0.047
Token colors
Token ID7577
Feature activation-5.84e+00

Pos logit contributions
kin+0.049
pron+0.046
uren+0.042
Adam+0.035
omo+0.035
Neg logit contributions
 aback-0.075
 closer-0.069
 away-0.068
fired-0.067
 home-0.067
Token and
Token ID290
Feature activation-1.27e+00

Pos logit contributions
uren+0.161
kin+0.161
pron+0.159
Adam+0.143
ae+0.141
Neg logit contributions
 aback-0.084
 closer-0.080
 home-0.077
 away-0.077
 back-0.075
Token patterns
Token ID7572
Feature activation-6.83e+00

Pos logit contributions
kin+0.023
pron+0.022
uren+0.020
Adam+0.018
ae+0.018
Neg logit contributions
 aback-0.030
 closer-0.028
 away-0.027
 home-0.027
fired-0.027
Token.
Token ID13
Feature activation+1.82e-01

Pos logit contributions
kin+0.187
pron+0.185
uren+0.181
omo+0.164
Adam+0.160
Neg logit contributions
 aback-0.105
 closer-0.099
 away-0.094
 home-0.091
fired-0.089
Token She
Token ID1375
Feature activation-2.27e+00

Pos logit contributions
 aback+0.003
 closer+0.003
 home+0.003
fired+0.003
 back+0.003
Neg logit contributions
kin-0.005
pron-0.004
uren-0.004
lf-0.004
bridge-0.004
Token liked
Token ID8288
Feature activation-8.73e-01

Pos logit contributions
kin+0.053
pron+0.050
uren+0.049
ities+0.045
ae+0.045
Neg logit contributions
 closer-0.037
 back-0.034
 aback-0.034
fired-0.033
 away-0.033
Token to
Token ID284
Feature activation-1.23e+00

Pos logit contributions
kin+0.035
pron+0.031
uren+0.031
omo+0.029
ae+0.029
Neg logit contributions
 closer-0.005
 aback-0.004
 home-0.004
 back-0.003
 away-0.003
Token spin
Token ID7906
Feature activation-2.41e+00

Pos logit contributions
kin+0.028
pron+0.025
uren+0.025
omo+0.024
Adam+0.024
Neg logit contributions
 closer-0.024
 away-0.023
 aback-0.022
 back-0.021
 home-0.021
Token We
Token ID775
Feature activation-1.51e+00

Pos logit contributions
kin+0.016
pron+0.016
uren+0.013
lf+0.013
ae+0.012
Neg logit contributions
 aback-0.014
 closer-0.013
fired-0.012
 revenge-0.012
 away-0.012
Token have
Token ID423
Feature activation+1.51e+00

Pos logit contributions
kin+0.035
pron+0.034
uren+0.032
lf+0.029
ae+0.028
Neg logit contributions
 aback-0.031
 closer-0.029
 away-0.028
fired-0.028
 revenge-0.027
Token different
Token ID1180
Feature activation-2.17e+00

Pos logit contributions
 aback+0.019
 closer+0.016
fired+0.016
 home+0.015
 away+0.015
Neg logit contributions
kin-0.048
pron-0.045
uren-0.043
lf-0.040
omo-0.040
Token likes
Token ID7832
Feature activation-1.90e+00

Pos logit contributions
kin+0.047
pron+0.045
uren+0.042
ae+0.036
omo+0.036
Neg logit contributions
 aback-0.049
 closer-0.045
fired-0.044
 away-0.044
 home-0.044
Token and
Token ID290
Feature activation-1.38e+00

Pos logit contributions
kin+0.049
pron+0.045
uren+0.042
omo+0.038
lf+0.038
Neg logit contributions
 aback-0.036
 closer-0.032
fired-0.032
 away-0.030
 home-0.030
Token disl
Token ID19621
Feature activation-6.82e+00

Pos logit contributions
kin+0.034
pron+0.032
uren+0.030
omo+0.027
ae+0.026
Neg logit contributions
 aback-0.027
 closer-0.025
fired-0.025
 away-0.024
 revenge-0.024
Tokenikes
Token ID7938
Feature activation-1.22e+00

Pos logit contributions
kin+0.155
pron+0.143
uren+0.131
 ma+0.112
omo+0.110
Neg logit contributions
 aback-0.150
 closer-0.132
fired-0.131
 revenge-0.126
beh-0.125
Token.
Token ID13
Feature activation-5.05e-01

Pos logit contributions
kin+0.032
pron+0.030
uren+0.029
omo+0.026
lf+0.026
Neg logit contributions
 aback-0.022
 closer-0.020
 away-0.019
fired-0.019
 home-0.018
Token We
Token ID775
Feature activation-1.62e+00

Pos logit contributions
kin+0.012
pron+0.011
uren+0.009
lf+0.009
ae+0.008
Neg logit contributions
 aback-0.011
 closer-0.010
fired-0.010
 away-0.009
 revenge-0.009
Token can
Token ID460
Feature activation-8.12e-01

Pos logit contributions
kin+0.038
pron+0.036
uren+0.034
lf+0.031
ae+0.030
Neg logit contributions
 aback-0.034
 closer-0.031
 away-0.030
fired-0.030
 revenge-0.029
Token be
Token ID307
Feature activation+3.62e-01

Pos logit contributions
kin+0.021
pron+0.019
uren+0.019
ae+0.016
Adam+0.016
Neg logit contributions
 closer-0.015
 aback-0.014
 away-0.014
 home-0.013
 revenge-0.013
Token They
Token ID1119
Feature activation-3.02e+00

Pos logit contributions
kin+0.007
pron+0.007
uren+0.006
lf+0.006
ae+0.005
Neg logit contributions
 aback-0.005
 closer-0.005
fired-0.005
 home-0.004
 revenge-0.004
Token can
Token ID460
Feature activation-8.93e-01

Pos logit contributions
kin+0.085
pron+0.082
uren+0.078
ae+0.072
omo+0.072
Neg logit contributions
 closer-0.049
 away-0.047
 aback-0.045
 back-0.043
 home-0.039
Token make
Token ID787
Feature activation-2.74e+00

Pos logit contributions
kin+0.023
pron+0.021
uren+0.020
ae+0.017
omo+0.017
Neg logit contributions
 closer-0.017
 aback-0.016
 away-0.015
 home-0.014
fired-0.014
Token towers
Token ID18028
Feature activation-4.10e+00

Pos logit contributions
kin+0.072
pron+0.068
uren+0.064
omo+0.057
lf+0.056
Neg logit contributions
 aback-0.050
 closer-0.047
fired-0.044
 away-0.043
 home-0.043
Token,
Token ID11
Feature activation-3.66e+00

Pos logit contributions
kin+0.105
pron+0.100
uren+0.097
omo+0.084
ae+0.083
Neg logit contributions
 aback-0.074
 closer-0.072
 away-0.067
fired-0.065
 home-0.065
Token bridges
Token ID19432
Feature activation-6.81e+00

Pos logit contributions
kin+0.084
pron+0.077
uren+0.073
ae+0.064
omo+0.064
Neg logit contributions
 aback-0.077
 closer-0.077
 away-0.070
fired-0.068
 home-0.067
Token,
Token ID11
Feature activation-4.06e+00

Pos logit contributions
kin+0.181
pron+0.178
uren+0.171
omo+0.149
ae+0.147
Neg logit contributions
 aback-0.116
 closer-0.110
 away-0.105
fired-0.102
 home-0.101
Token houses
Token ID7777
Feature activation-4.31e+00

Pos logit contributions
kin+0.097
pron+0.090
uren+0.086
omo+0.076
ae+0.075
Neg logit contributions
 closer-0.082
 aback-0.081
 away-0.075
fired-0.072
 back-0.072
Token and
Token ID290
Feature activation-1.45e+00

Pos logit contributions
kin+0.119
pron+0.115
uren+0.110
omo+0.099
addy+0.097
Neg logit contributions
 aback-0.069
 closer-0.066
 away-0.063
 home-0.060
fired-0.060
Token more
Token ID517
Feature activation-1.04e+00

Pos logit contributions
kin+0.028
pron+0.026
uren+0.023
lf+0.022
 moons+0.022
Neg logit contributions
 aback-0.037
fired-0.032
 closer-0.031
 revenge-0.030
 away-0.029
Token with
Token ID351
Feature activation-4.26e-02

Pos logit contributions
kin+0.026
pron+0.024
uren+0.023
omo+0.020
ae+0.020
Neg logit contributions
 aback-0.020
 closer-0.019
fired-0.018
 away-0.017
 home-0.017
Token cars
Token ID5006
Feature activation-2.78e+00

Pos logit contributions
kin+0.015
pron+0.013
lf+0.012
uren+0.011
omo+0.011
Neg logit contributions
 aback-0.021
fired-0.019
 closer-0.018
 revenge-0.017
 nearer-0.017
Token of
Token ID286
Feature activation-1.81e+00

Pos logit contributions
kin+0.068
pron+0.064
uren+0.059
omo+0.053
lf+0.052
Neg logit contributions
 aback-0.056
 closer-0.050
fired-0.050
 away-0.047
 home-0.047
Token different
Token ID1180
Feature activation-2.82e+00

Pos logit contributions
kin+0.044
pron+0.041
uren+0.038
lf+0.035
omo+0.035
Neg logit contributions
 aback-0.036
fired-0.032
 closer-0.032
 revenge-0.029
 away-0.029
Token colors
Token ID7577
Feature activation-5.91e+00

Pos logit contributions
kin+0.048
pron+0.043
uren+0.039
omo+0.033
lf+0.033
Neg logit contributions
 aback-0.077
 closer-0.072
fired-0.071
 away-0.067
 revenge-0.067
Token and
Token ID290
Feature activation-1.28e+00

Pos logit contributions
uren+0.166
pron+0.166
kin+0.166
ae+0.145
Adam+0.144
Neg logit contributions
 aback-0.081
 closer-0.080
 away-0.077
 back-0.075
 home-0.074
Token sizes
Token ID10620
Feature activation-6.81e+00

Pos logit contributions
kin+0.021
pron+0.019
uren+0.017
ae+0.014
addy+0.014
Neg logit contributions
 aback-0.036
 closer-0.034
 away-0.032
fired-0.032
 revenge-0.031
Token.
Token ID13
Feature activation+2.45e-01

Pos logit contributions
pron+0.211
uren+0.209
kin+0.207
ae+0.183
Adam+0.183
Neg logit contributions
 aback-0.079
 away-0.077
 closer-0.075
 home-0.073
 back-0.070
Token They
Token ID1119
Feature activation-3.25e+00

Pos logit contributions
 aback+0.005
 closer+0.005
 home+0.005
fired+0.004
 away+0.004
Neg logit contributions
kin-0.006
pron-0.005
uren-0.005
lf-0.005
bridge-0.004
Token make
Token ID787
Feature activation-3.43e+00

Pos logit contributions
kin+0.094
pron+0.089
uren+0.085
ae+0.082
addy+0.078
Neg logit contributions
 closer-0.050
 away-0.048
 aback-0.046
 back-0.043
 home-0.040
Token roads
Token ID9725
Feature activation-4.42e+00

Pos logit contributions
kin+0.096
pron+0.089
uren+0.082
ae+0.075
omo+0.075
Neg logit contributions
 closer-0.060
 aback-0.060
 away-0.055
 home-0.053
 back-0.052
Token and
Token ID290
Feature activation-4.87e-01

Pos logit contributions
kin+0.111
pron+0.110
uren+0.104
omo+0.092
ae+0.090
Neg logit contributions
 aback-0.082
 closer-0.080
 away-0.076
 back-0.072
 home-0.071
Token time
Token ID640
Feature activation+3.04e+00

Pos logit contributions
 closer+0.025
 aback+0.025
 home+0.024
 away+0.024
 back+0.023
Neg logit contributions
kin-0.018
uren-0.016
pron-0.015
 majesty-0.013
 scalp-0.013
Token for
Token ID329
Feature activation+1.09e+00

Pos logit contributions
 aback+0.033
 closer+0.026
fired+0.025
 away+0.022
 revenge+0.021
Neg logit contributions
kin-0.103
pron-0.098
uren-0.093
omo-0.087
lf-0.087
Token Lily
Token ID20037
Feature activation+9.41e-01

Pos logit contributions
 aback+0.025
 closer+0.022
fired+0.022
 away+0.021
 home+0.021
Neg logit contributions
kin-0.024
pron-0.022
uren-0.020
omo-0.018
lf-0.018
Token to
Token ID284
Feature activation-8.75e-01

Pos logit contributions
 aback+0.013
 closer+0.011
fired+0.010
 revenge+0.009
 away+0.009
Neg logit contributions
kin-0.029
pron-0.027
uren-0.026
omo-0.024
lf-0.024
Token go
Token ID467
Feature activation+4.13e+00

Pos logit contributions
pron+0.025
kin+0.025
uren+0.023
 moons+0.022
utes+0.021
Neg logit contributions
 away-0.013
 home-0.012
 closer-0.012
 aback-0.012
 back-0.011
Token back
Token ID736
Feature activation+4.90e+00

Pos logit contributions
 aback+0.044
beh+0.031
fired+0.029
 revenge+0.027
 closer+0.026
Neg logit contributions
kin-0.131
pron-0.126
uren-0.121
addy-0.115
stand-0.115
Token inside
Token ID2641
Feature activation+3.24e-01

Pos logit contributions
 aback+0.072
beh+0.064
 revenge+0.055
oc+0.054
smart+0.053
Neg logit contributions
kin-0.125
pron-0.114
uren-0.113
 Ben-0.111
 Adam-0.110
Token,
Token ID11
Feature activation-9.73e-01

Pos logit contributions
 aback+0.005
 closer+0.005
 home+0.005
fired+0.004
 away+0.004
Neg logit contributions
kin-0.009
pron-0.009
uren-0.008
bridge-0.008
omo-0.008
Token she
Token ID673
Feature activation-3.94e-02

Pos logit contributions
kin+0.026
pron+0.023
uren+0.022
ae+0.021
inner+0.021
Neg logit contributions
 closer-0.018
 home-0.017
 aback-0.017
 away-0.016
 back-0.016
Token said
Token ID531
Feature activation+1.16e+00

Pos logit contributions
kin+0.001
pron+0.001
uren+0.001
omo+0.001
lf+0.001
Neg logit contributions
 aback-0.001
 closer-0.001
fired-0.001
 away-0.001
 home-0.001
Token goodbye
Token ID24829
Feature activation+7.58e-01

Pos logit contributions
 aback+0.025
 closer+0.024
fired+0.023
 away+0.022
 home+0.022
Neg logit contributions
kin-0.026
pron-0.024
uren-0.023
omo-0.020
lf-0.020
Token followed
Token ID3940
Feature activation+7.31e-01

Pos logit contributions
 aback+0.005
 closer+0.004
fired+0.004
 away+0.004
 revenge+0.004
Neg logit contributions
kin-0.005
pron-0.005
uren-0.004
Adam-0.004
lf-0.004
Token her
Token ID607
Feature activation+1.02e+00

Pos logit contributions
 aback+0.016
fired+0.015
 closer+0.013
beh+0.013
 medical+0.013
Neg logit contributions
kin-0.016
pron-0.014
uren-0.013
lf-0.012
ae-0.012
Token.
Token ID13
Feature activation+1.44e-01

Pos logit contributions
 aback+0.028
fired+0.024
beh+0.023
 closer+0.023
smart+0.023
Neg logit contributions
kin-0.018
pron-0.014
uren-0.013
 scalp-0.012
omo-0.012
Token When
Token ID1649
Feature activation+1.06e+00

Pos logit contributions
 aback+0.003
 closer+0.003
fired+0.002
 home+0.002
 away+0.002
Neg logit contributions
kin-0.004
pron-0.004
uren-0.003
lf-0.003
 moons-0.003
Token they
Token ID484
Feature activation-1.49e+00

Pos logit contributions
 aback+0.025
 closer+0.023
fired+0.023
 home+0.022
 away+0.022
Neg logit contributions
kin-0.022
pron-0.021
uren-0.019
omo-0.017
lf-0.016
Token got
Token ID1392
Feature activation+4.58e+00

Pos logit contributions
kin+0.034
pron+0.030
uren+0.029
lf+0.025
omo+0.025
Neg logit contributions
 aback-0.032
fired-0.029
 closer-0.028
 revenge-0.027
beh-0.026
Token to
Token ID284
Feature activation+2.82e-01

Pos logit contributions
oc+0.100
 aback+0.085
smart+0.080
vered+0.077
beh+0.075
Neg logit contributions
kin-0.093
 Ben-0.088
pron-0.084
 not-0.079
omo-0.075
Token the
Token ID262
Feature activation+1.62e-01

Pos logit contributions
 aback+0.006
 closer+0.005
fired+0.005
 away+0.005
 revenge+0.005
Neg logit contributions
kin-0.007
pron-0.006
uren-0.006
omo-0.005
lf-0.005
Token stable
Token ID8245
Feature activation+8.55e-01

Pos logit contributions
 aback+0.004
fired+0.003
 closer+0.003
 revenge+0.003
 away+0.003
Neg logit contributions
kin-0.004
pron-0.003
uren-0.003
omo-0.003
lf-0.003
Token,
Token ID11
Feature activation+1.29e-01

Pos logit contributions
 aback+0.015
 closer+0.013
fired+0.013
 home+0.012
 away+0.012
Neg logit contributions
kin-0.023
pron-0.022
uren-0.021
omo-0.019
lf-0.019
Token it
Token ID340
Feature activation+1.08e+00

Pos logit contributions
 aback+0.003
 closer+0.003
fired+0.002
 home+0.002
 away+0.002
Neg logit contributions
kin-0.003
pron-0.003
uren-0.003
omo-0.002
lf-0.002
Token.
Token ID13
Feature activation+2.19e-01

Pos logit contributions
 aback+0.036
fired+0.032
 closer+0.032
 revenge+0.030
 home+0.029
Neg logit contributions
kin-0.039
pron-0.035
uren-0.032
omo-0.029
lf-0.029
Token Tom
Token ID4186
Feature activation+9.30e-01

Pos logit contributions
 aback+0.004
 closer+0.004
fired+0.004
 revenge+0.003
 home+0.003
Neg logit contributions
kin-0.006
pron-0.006
uren-0.005
lf-0.005
bee-0.005
Token screamed
Token ID25421
Feature activation+3.88e-01

Pos logit contributions
 aback+0.016
 closer+0.015
 away+0.014
fired+0.014
 back+0.013
Neg logit contributions
kin-0.025
pron-0.024
uren-0.022
omo-0.021
Adam-0.020
Token and
Token ID290
Feature activation+6.25e-01

Pos logit contributions
 aback+0.008
 closer+0.008
fired+0.007
 away+0.007
 home+0.007
Neg logit contributions
kin-0.009
pron-0.008
uren-0.008
omo-0.007
lf-0.007
Token pulled
Token ID5954
Feature activation+1.00e+00

Pos logit contributions
 aback+0.011
 closer+0.011
 away+0.010
fired+0.010
 revenge+0.009
Neg logit contributions
kin-0.017
pron-0.016
uren-0.015
ae-0.013
Adam-0.013
Token back
Token ID736
Feature activation+5.22e+00

Pos logit contributions
 aback+0.022
fired+0.021
beh+0.020
 medical+0.019
 revenge+0.019
Neg logit contributions
kin-0.021
 Ben-0.017
pron-0.017
uren-0.016
ia-0.016
Token his
Token ID465
Feature activation+1.01e+00

Pos logit contributions
 aback+0.137
beh+0.125
 medical+0.123
fired+0.120
 unst+0.120
Neg logit contributions
 Ben-0.068
kin-0.068
ia-0.058
 Anna-0.054
 Tom-0.053
Token hand
Token ID1021
Feature activation+3.57e+00

Pos logit contributions
 aback+0.022
 closer+0.021
fired+0.020
 away+0.019
 revenge+0.019
Neg logit contributions
kin-0.023
pron-0.021
uren-0.020
lf-0.017
omo-0.017
Token.
Token ID13
Feature activation+5.03e-01

Pos logit contributions
 aback+0.090
fired+0.084
 revenge+0.079
beh+0.076
 medical+0.076
Neg logit contributions
kin-0.065
pron-0.054
uren-0.045
 scalp-0.045
stand-0.045
Token It
Token ID632
Feature activation+1.20e+00

Pos logit contributions
 aback+0.009
fired+0.008
 closer+0.008
 revenge+0.007
 home+0.007
Neg logit contributions
kin-0.014
pron-0.013
uren-0.012
 moons-0.011
lf-0.011
Token was
Token ID373
Feature activation-2.10e+00

Pos logit contributions
 aback+0.026
fired+0.023
 closer+0.022
 home+0.021
 revenge+0.021
Neg logit contributions
kin-0.029
pron-0.026
uren-0.023
omo-0.022
lf-0.021
Token when
Token ID618
Feature activation+8.79e-01

Pos logit contributions
kin+0.023
pron+0.022
uren+0.020
lf+0.018
omo+0.017
Neg logit contributions
 aback-0.023
fired-0.021
 closer-0.021
 revenge-0.019
 away-0.019
Token the
Token ID262
Feature activation-3.93e-01

Pos logit contributions
 aback+0.022
fired+0.020
 closer+0.019
 revenge+0.018
 away+0.018
Neg logit contributions
kin-0.018
pron-0.016
uren-0.015
lf-0.013
omo-0.012
Token princess
Token ID21752
Feature activation-2.17e-01

Pos logit contributions
kin+0.009
pron+0.008
uren+0.007
lf+0.007
omo+0.006
Neg logit contributions
 aback-0.009
fired-0.008
 closer-0.008
 away-0.008
 revenge-0.008
Token got
Token ID1392
Feature activation+4.00e+00

Pos logit contributions
kin+0.005
pron+0.005
uren+0.004
lf+0.004
omo+0.004
Neg logit contributions
 aback-0.004
 closer-0.004
fired-0.004
 revenge-0.004
 away-0.004
Token the
Token ID262
Feature activation+2.25e-01

Pos logit contributions
oc+0.076
 aback+0.074
fired+0.065
beh+0.063
smart+0.061
Neg logit contributions
pron-0.092
kin-0.087
 Avery-0.074
uren-0.067
ae-0.066
Token magnet
Token ID19972
Feature activation+4.29e+00

Pos logit contributions
 aback+0.005
fired+0.005
beh+0.005
 closer+0.004
arling+0.004
Neg logit contributions
kin-0.005
pron-0.005
uren-0.004
 ceiling-0.003
lf-0.003
Token it
Token ID340
Feature activation+2.41e+00

Pos logit contributions
 aback+0.092
fired+0.080
 closer+0.079
 revenge+0.076
beh+0.074
Neg logit contributions
kin-0.099
pron-0.092
uren-0.082
lf-0.077
 moons-0.071
Token was
Token ID373
Feature activation-1.77e-01

Pos logit contributions
 aback+0.056
 closer+0.049
fired+0.049
 revenge+0.047
beh+0.046
Neg logit contributions
kin-0.051
pron-0.047
uren-0.041
lf-0.038
 moons-0.036
Token fake
Token ID8390
Feature activation-1.39e-01

Pos logit contributions
kin+0.005
pron+0.004
uren+0.004
omo+0.004
lf+0.004
Neg logit contributions
 aback-0.003
 closer-0.003
fired-0.003
 away-0.003
 home-0.003
Token!
Token ID0
Feature activation+5.44e-01

Pos logit contributions
kin+0.003
pron+0.003
uren+0.003
omo+0.003
lf+0.003
Neg logit contributions
 aback-0.003
 closer-0.002
fired-0.002
 away-0.002
 revenge-0.002
Token She
Token ID1375
Feature activation-1.57e+00

Pos logit contributions
 aback+0.011
 closer+0.009
fired+0.009
 home+0.009
 away+0.008
Neg logit contributions
kin-0.015
pron-0.014
uren-0.012
lf-0.012
omo-0.011
Token not
Token ID407
Feature activation+7.24e-01

Pos logit contributions
kin+0.043
pron+0.040
uren+0.035
omo+0.031
lf+0.028
Neg logit contributions
 aback-0.073
 closer-0.072
 away-0.068
fired-0.068
 home-0.066
Token know
Token ID760
Feature activation+7.35e-02

Pos logit contributions
 aback+0.012
 closer+0.011
fired+0.011
 away+0.010
 revenge+0.010
Neg logit contributions
kin-0.020
pron-0.019
uren-0.018
omo-0.016
lf-0.016
Token how
Token ID703
Feature activation+2.06e+00

Pos logit contributions
 aback+0.001
 closer+0.001
fired+0.001
 away+0.001
 home+0.001
Neg logit contributions
kin-0.002
pron-0.002
uren-0.002
omo-0.001
Adam-0.001
Token to
Token ID284
Feature activation+3.64e-01

Pos logit contributions
 aback+0.033
 closer+0.026
fired+0.026
 revenge+0.024
 away+0.024
Neg logit contributions
kin-0.059
pron-0.055
uren-0.052
lf-0.048
omo-0.048
Token go
Token ID467
Feature activation+3.89e+00

Pos logit contributions
 aback+0.008
fired+0.007
 closer+0.007
 revenge+0.006
 unst+0.006
Neg logit contributions
kin-0.009
pron-0.008
uren-0.007
lf-0.007
omo-0.006
Token back
Token ID736
Feature activation+5.11e+00

Pos logit contributions
 aback+0.082
beh+0.069
vered+0.066
 revenge+0.065
 medical+0.065
Neg logit contributions
kin-0.078
line-0.068
 Ben-0.062
pron-0.061
stand-0.061
Token.
Token ID13
Feature activation+1.40e-02

Pos logit contributions
 aback+0.083
beh+0.074
 medical+0.067
 unst+0.067
 revenge+0.063
Neg logit contributions
kin-0.119
 Ben-0.109
uren-0.106
ia-0.104
 Eric-0.104
Token
Token ID198
Feature activation-3.60e-01

Pos logit contributions
 aback+0.000
 closer+0.000
fired+0.000
 away+0.000
 revenge+0.000
Neg logit contributions
kin-0.000
pron-0.000
uren-0.000
Adam-0.000
omo-0.000
Token
Token ID198
Feature activation+6.84e-01

Pos logit contributions
kin+0.008
pron+0.007
uren+0.007
omo+0.006
lf+0.006
Neg logit contributions
 aback-0.008
 closer-0.007
fired-0.007
 away-0.007
 revenge-0.007
TokenSuddenly
Token ID38582
Feature activation+1.85e+00

Pos logit contributions
 aback+0.017
 closer+0.016
fired+0.016
 away+0.015
 revenge+0.015
Neg logit contributions
kin-0.013
pron-0.012
uren-0.011
omo-0.010
lf-0.010
Token,
Token ID11
Feature activation+4.68e-01

Pos logit contributions
 aback+0.040
fired+0.035
 closer+0.034
 revenge+0.033
beh+0.033
Neg logit contributions
kin-0.043
pron-0.037
uren-0.037
lf-0.032
ia-0.032
Token laugh
Token ID6487
Feature activation-3.53e+00

Pos logit contributions
 aback+0.014
 closer+0.014
 away+0.013
 home+0.012
 back+0.012
Neg logit contributions
kin-0.025
pron-0.025
uren-0.022
omo-0.022
lf-0.021
Token or
Token ID393
Feature activation-7.89e-02

Pos logit contributions
pron+0.103
kin+0.101
uren+0.095
omo+0.086
ae+0.085
Neg logit contributions
 aback-0.054
 closer-0.054
 away-0.052
 back-0.049
 home-0.046
Token scream
Token ID8196
Feature activation-1.41e+00

Pos logit contributions
kin+0.002
pron+0.002
uren+0.002
omo+0.002
ae+0.002
Neg logit contributions
 aback-0.001
 closer-0.001
 away-0.001
fired-0.001
 revenge-0.001
Token.
Token ID13
Feature activation+8.19e-02

Pos logit contributions
kin+0.037
pron+0.035
uren+0.032
omo+0.029
lf+0.029
Neg logit contributions
 aback-0.026
 closer-0.024
fired-0.023
 away-0.022
 home-0.022
Token He
Token ID679
Feature activation-2.67e-01

Pos logit contributions
 aback+0.002
 closer+0.001
fired+0.001
 home+0.001
 revenge+0.001
Neg logit contributions
kin-0.002
pron-0.002
uren-0.002
lf-0.002
ae-0.002
Token looks
Token ID3073
Feature activation+5.34e-01

Pos logit contributions
kin+0.007
pron+0.007
uren+0.006
lf+0.006
ae+0.005
Neg logit contributions
 aback-0.005
 closer-0.005
 away-0.005
fired-0.004
 revenge-0.004
Token bored
Token ID17533
Feature activation-2.83e+00

Pos logit contributions
 aback+0.010
fired+0.009
 closer+0.009
 revenge+0.008
 home+0.008
Neg logit contributions
kin-0.013
pron-0.013
uren-0.012
omo-0.011
lf-0.010
Token and
Token ID290
Feature activation+8.77e-01

Pos logit contributions
kin+0.071
pron+0.067
uren+0.063
omo+0.056
ae+0.056
Neg logit contributions
 aback-0.056
 closer-0.052
 away-0.050
fired-0.048
 home-0.047
Token mean
Token ID1612
Feature activation+3.66e-02

Pos logit contributions
 aback+0.014
 closer+0.014
 away+0.012
fired+0.012
 revenge+0.011
Neg logit contributions
kin-0.026
pron-0.024
uren-0.023
lf-0.021
ae-0.021
Token.
Token ID13
Feature activation+1.66e-01

Pos logit contributions
 aback+0.001
 closer+0.001
 away+0.001
fired+0.001
 home+0.001
Neg logit contributions
kin-0.001
pron-0.001
uren-0.001
omo-0.001
lf-0.001
Token
Token ID198
Feature activation+4.66e-02

Pos logit contributions
 aback+0.004
 closer+0.003
fired+0.003
 revenge+0.003
 away+0.003
Neg logit contributions
kin-0.004
pron-0.004
uren-0.003
lf-0.003
omo-0.003
Token
Token ID198
Feature activation-5.91e-01

Pos logit contributions
kin+0.016
pron+0.015
uren+0.014
lf+0.012
omo+0.012
Neg logit contributions
 aback-0.018
 closer-0.016
fired-0.016
 away-0.015
 home-0.015
Token
Token ID198
Feature activation+5.30e-01

Pos logit contributions
kin+0.015
pron+0.014
uren+0.013
lf+0.011
omo+0.011
Neg logit contributions
 aback-0.012
 closer-0.011
fired-0.011
 away-0.010
 home-0.010
Token"
Token ID1
Feature activation+2.42e+00

Pos logit contributions
 aback+0.011
 closer+0.010
fired+0.010
 away+0.010
 home+0.009
Neg logit contributions
kin-0.013
pron-0.012
uren-0.011
lf-0.010
 moons-0.010
TokenWhat
Token ID2061
Feature activation+1.06e+00

Pos logit contributions
 aback+0.048
 closer+0.044
fired+0.040
 away+0.039
 revenge+0.039
Neg logit contributions
kin-0.059
pron-0.055
uren-0.052
omo-0.048
lf-0.048
Token is
Token ID318
Feature activation-1.09e+00

Pos logit contributions
 aback+0.022
 closer+0.021
fired+0.020
 revenge+0.019
 home+0.018
Neg logit contributions
kin-0.024
pron-0.023
uren-0.022
omo-0.019
lf-0.019
Token it
Token ID340
Feature activation+1.28e+00

Pos logit contributions
kin+0.025
pron+0.023
uren+0.021
lf+0.019
Adam+0.018
Neg logit contributions
 aback-0.025
fired-0.022
 closer-0.021
 away-0.019
 revenge-0.019
Token?"
Token ID1701
Feature activation-2.41e+00

Pos logit contributions
 aback+0.031
 closer+0.028
fired+0.027
 away+0.026
 revenge+0.026
Neg logit contributions
kin-0.027
pron-0.025
uren-0.022
omo-0.020
lf-0.020
Token Ben
Token ID3932
Feature activation-1.43e+00

Pos logit contributions
kin+0.056
pron+0.053
uren+0.045
lf+0.043
 reflecting+0.042
Neg logit contributions
 aback-0.052
 closer-0.050
 home-0.045
fired-0.044
 away-0.044
Token asked
Token ID1965
Feature activation-1.31e-02

Pos logit contributions
kin+0.041
pron+0.038
uren+0.035
omo+0.033
ae+0.033
Neg logit contributions
 aback-0.023
 closer-0.020
fired-0.019
 away-0.018
 home-0.017
Token.
Token ID13
Feature activation-1.06e+00

Pos logit contributions
kin+0.000
pron+0.000
uren+0.000
ia+0.000
 Ben+0.000
Neg logit contributions
 aback-0.000
fired-0.000
 closer-0.000
 revenge-0.000
beh-0.000
Token
Token ID198
Feature activation-4.74e-01

Pos logit contributions
kin+0.027
pron+0.025
uren+0.023
lf+0.022
omo+0.021
Neg logit contributions
 aback-0.021
 closer-0.019
fired-0.018
 away-0.016
 home-0.016
Token angry
Token ID7954
Feature activation-1.19e+00

Pos logit contributions
kin+0.037
pron+0.034
uren+0.032
lf+0.028
omo+0.028
Neg logit contributions
 aback-0.032
 closer-0.029
fired-0.028
 away-0.027
 home-0.027
Token.
Token ID13
Feature activation+3.97e-01

Pos logit contributions
kin+0.030
pron+0.028
uren+0.026
lf+0.023
omo+0.023
Neg logit contributions
 aback-0.024
 closer-0.021
fired-0.021
 away-0.019
 home-0.019
Token He
Token ID679
Feature activation+4.47e-01

Pos logit contributions
 aback+0.008
 closer+0.007
fired+0.006
 away+0.006
 home+0.006
Neg logit contributions
kin-0.011
pron-0.010
uren-0.009
lf-0.008
ae-0.008
Token wanted
Token ID2227
Feature activation+1.56e+00

Pos logit contributions
 aback+0.009
 closer+0.008
fired+0.008
 away+0.008
 revenge+0.008
Neg logit contributions
kin-0.011
pron-0.010
uren-0.009
ae-0.008
lf-0.008
Token to
Token ID284
Feature activation+7.88e-01

Pos logit contributions
 aback+0.029
fired+0.025
beh+0.024
oc+0.023
arling+0.023
Neg logit contributions
 Ben-0.035
kin-0.034
pron-0.033
ia-0.031
uren-0.031
Token scare
Token ID19437
Feature activation+6.25e-01

Pos logit contributions
 aback+0.017
fired+0.015
 closer+0.014
arling+0.014
 nearer+0.013
Neg logit contributions
kin-0.017
pron-0.015
uren-0.014
omo-0.014
ia-0.013
Token them
Token ID606
Feature activation+7.03e-01

Pos logit contributions
 aback+0.017
fired+0.016
 closer+0.015
 medical+0.015
beh+0.014
Neg logit contributions
kin-0.009
uren-0.008
 Ben-0.008
pron-0.007
ia-0.007
Token again
Token ID757
Feature activation+2.82e+00

Pos logit contributions
 aback+0.016
fired+0.014
 revenge+0.013
 closer+0.013
 medical+0.013
Neg logit contributions
kin-0.015
pron-0.012
uren-0.011
omo-0.011
lf-0.010
Token.
Token ID13
Feature activation+1.25e-01

Pos logit contributions
 aback+0.073
fired+0.063
 closer+0.061
 revenge+0.060
beh+0.059
Neg logit contributions
kin-0.055
pron-0.045
uren-0.041
omo-0.039
ia-0.038
Token He
Token ID679
Feature activation-6.50e-02

Pos logit contributions
 aback+0.002
 closer+0.002
fired+0.002
 away+0.002
 home+0.002
Neg logit contributions
kin-0.003
pron-0.003
uren-0.003
lf-0.003
ae-0.002
Token ran
Token ID4966
Feature activation+2.51e+00

Pos logit contributions
kin+0.002
pron+0.001
uren+0.001
lf+0.001
Adam+0.001
Neg logit contributions
 aback-0.001
 closer-0.001
fired-0.001
 away-0.001
 revenge-0.001
Token big
Token ID1263
Feature activation+1.48e+00

Pos logit contributions
 aback+0.002
 closer+0.002
 away+0.002
 home+0.001
 revenge+0.001
Neg logit contributions
kin-0.004
pron-0.004
uren-0.004
omo-0.003
ae-0.003
Token boots
Token ID14412
Feature activation-3.30e+00

Pos logit contributions
 aback+0.041
fired+0.037
 closer+0.037
beh+0.036
 revenge+0.036
Neg logit contributions
kin-0.024
pron-0.024
uren-0.020
lf-0.018
omo-0.018
Token.
Token ID13
Feature activation+1.22e-01

Pos logit contributions
kin+0.092
pron+0.085
uren+0.082
omo+0.076
 majesty+0.074
Neg logit contributions
 aback-0.056
 closer-0.050
 away-0.050
 home-0.049
fired-0.046
Token One
Token ID1881
Feature activation-4.76e-01

Pos logit contributions
 aback+0.002
 closer+0.002
fired+0.002
 home+0.002
 revenge+0.002
Neg logit contributions
kin-0.003
pron-0.003
uren-0.003
ae-0.003
 scalp-0.003
Token day
Token ID1110
Feature activation+1.96e+00

Pos logit contributions
kin+0.011
pron+0.010
uren+0.009
omo+0.008
lf+0.008
Neg logit contributions
 aback-0.011
 closer-0.009
fired-0.009
 away-0.009
 revenge-0.009
Token,
Token ID11
Feature activation+6.82e-01

Pos logit contributions
 aback+0.046
fired+0.040
 closer+0.040
beh+0.038
 revenge+0.038
Neg logit contributions
kin-0.042
pron-0.037
uren-0.034
omo-0.032
lf-0.032
Token Tim
Token ID5045
Feature activation-5.45e-01

Pos logit contributions
 aback+0.013
 closer+0.012
fired+0.012
 away+0.011
 revenge+0.011
Neg logit contributions
kin-0.017
pron-0.016
uren-0.015
omo-0.013
lf-0.013
Token wanted
Token ID2227
Feature activation+1.67e+00

Pos logit contributions
kin+0.016
pron+0.015
uren+0.014
ae+0.013
 unison+0.013
Neg logit contributions
 aback-0.008
fired-0.008
 closer-0.007
 home-0.007
 away-0.007
Token to
Token ID284
Feature activation+4.32e-02

Pos logit contributions
 aback+0.034
arling+0.027
fired+0.027
beh+0.027
oc+0.027
Neg logit contributions
pron-0.039
kin-0.036
 Ben-0.034
stand-0.033
lf-0.032
Token be
Token ID307
Feature activation-3.17e-02

Pos logit contributions
 aback+0.001
 closer+0.001
fired+0.001
 away+0.001
 home+0.001
Neg logit contributions
kin-0.001
pron-0.001
uren-0.001
omo-0.001
lf-0.001
Token just
Token ID655
Feature activation+4.33e-01

Pos logit contributions
kin+0.001
pron+0.001
uren+0.001
omo+0.001
lf+0.001
Neg logit contributions
 aback-0.001
fired-0.001
 closer-0.001
 revenge-0.000
 away-0.000
Token again
Token ID757
Feature activation+1.98e+00

Pos logit contributions
kin+0.018
pron+0.018
uren+0.016
omo+0.015
Adam+0.015
Neg logit contributions
 aback-0.011
 closer-0.010
fired-0.010
 away-0.010
 home-0.010
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
 aback+0.042
 closer+0.038
fired+0.037
 revenge+0.035
 away+0.034
Neg logit contributions
kin-0.046
pron-0.043
uren-0.040
lf-0.036
omo-0.035
Token<|endoftext|>
Token ID50256
Feature activation-1.45e+00

Pos logit contributions
 aback+0.022
fired+0.020
 closer+0.019
 home+0.019
 revenge+0.018
Neg logit contributions
kin-0.028
pron-0.026
uren-0.022
lf-0.021
bridge-0.020
TokenOnce
Token ID7454
Feature activation-7.89e-01

Pos logit contributions
kin+0.036
pron+0.034
uren+0.031
omo+0.028
lf+0.028
Neg logit contributions
 aback-0.029
 closer-0.026
fired-0.025
 home-0.024
 away-0.024
Token upon
Token ID2402
Feature activation-2.90e+00

Pos logit contributions
kin+0.016
pron+0.015
uren+0.014
 scalp+0.012
bridge+0.012
Neg logit contributions
 aback-0.019
 closer-0.018
 home-0.018
fired-0.017
 away-0.017
Token a
Token ID257
Feature activation+4.02e-01

Pos logit contributions
kin+0.093
pron+0.089
uren+0.088
omo+0.080
 majesty+0.080
Neg logit contributions
 closer-0.033
 aback-0.032
 away-0.026
 home-0.026
 back-0.025
Token time
Token ID640
Feature activation+2.79e-01

Pos logit contributions
 aback+0.010
 closer+0.010
 home+0.009
 away+0.009
fired+0.009
Neg logit contributions
kin-0.007
pron-0.007
uren-0.006
bridge-0.006
 moons-0.006
Token,
Token ID11
Feature activation-7.51e-01

Pos logit contributions
 aback+0.005
 closer+0.005
fired+0.005
 away+0.004
 revenge+0.004
Neg logit contributions
kin-0.007
pron-0.007
uren-0.006
omo-0.006
lf-0.006
Token there
Token ID612
Feature activation-2.37e+00

Pos logit contributions
kin+0.018
pron+0.016
uren+0.015
omo+0.013
lf+0.013
Neg logit contributions
 aback-0.016
fired-0.014
 closer-0.014
 revenge-0.013
 away-0.013
Token was
Token ID373
Feature activation+5.87e-01

Pos logit contributions
kin+0.063
pron+0.059
uren+0.056
omo+0.050
lf+0.050
Neg logit contributions
 aback-0.043
 closer-0.038
fired-0.037
 away-0.034
 home-0.034
Token a
Token ID257
Feature activation-5.09e-01

Pos logit contributions
 aback+0.009
 closer+0.008
fired+0.008
 home+0.008
 away+0.007
Neg logit contributions
kin-0.017
pron-0.016
uren-0.015
lf-0.013
omo-0.013
Token named
Token ID3706
Feature activation+1.53e-02

Pos logit contributions
 aback+0.029
 closer+0.025
fired+0.025
 revenge+0.024
 nearer+0.024
Neg logit contributions
kin-0.023
pron-0.021
uren-0.018
lf-0.018
omo-0.017
Token Tim
Token ID5045
Feature activation-1.39e+00

Pos logit contributions
 aback+0.000
 closer+0.000
fired+0.000
 away+0.000
 home+0.000
Neg logit contributions
kin-0.000
pron-0.000
uren-0.000
lf-0.000
omo-0.000
Tokenmy
Token ID1820
Feature activation-5.57e-01

Pos logit contributions
kin+0.045
pron+0.042
uren+0.041
lf+0.037
sheets+0.037
Neg logit contributions
 aback-0.018
 closer-0.016
fired-0.015
 away-0.014
 home-0.014
Token.
Token ID13
Feature activation+4.97e-01

Pos logit contributions
kin+0.013
pron+0.012
uren+0.012
omo+0.010
lf+0.010
Neg logit contributions
 aback-0.011
 closer-0.010
fired-0.010
 away-0.009
 revenge-0.009
Token Tim
Token ID5045
Feature activation-1.01e+00

Pos logit contributions
 aback+0.009
 closer+0.008
fired+0.008
 home+0.007
 away+0.007
Neg logit contributions
kin-0.014
pron-0.013
uren-0.012
ae-0.011
lf-0.010
Tokenmy
Token ID1820
Feature activation-3.13e-01

Pos logit contributions
kin+0.032
pron+0.030
uren+0.029
ae+0.026
lf+0.026
Neg logit contributions
 aback-0.013
fired-0.011
 closer-0.011
 away-0.010
 home-0.010
Token was
Token ID373
Feature activation-1.28e+00

Pos logit contributions
kin+0.007
pron+0.007
uren+0.007
 unison+0.006
ae+0.006
Neg logit contributions
 aback-0.006
fired-0.005
 home-0.005
 away-0.005
 closer-0.005
Token very
Token ID845
Feature activation+1.55e+00

Pos logit contributions
kin+0.036
pron+0.034
uren+0.031
omo+0.029
lf+0.029
Neg logit contributions
 aback-0.022
fired-0.019
 closer-0.019
 away-0.017
 revenge-0.017
Token poor
Token ID3595
Feature activation-1.40e+00

Pos logit contributions
 aback+0.031
 closer+0.027
fired+0.027
 away+0.025
 revenge+0.025
Neg logit contributions
kin-0.039
pron-0.036
uren-0.034
omo-0.031
lf-0.030
Token and
Token ID290
Feature activation+3.82e-02

Pos logit contributions
kin+0.036
pron+0.034
uren+0.033
Adam+0.029
bridge+0.028
Neg logit contributions
 aback-0.025
 home-0.024
 closer-0.023
fired-0.023
 away-0.022
Token he
Token ID339
Feature activation-1.45e-01

Pos logit contributions
 aback+0.001
 closer+0.001
fired+0.001
 away+0.001
 home+0.001
Neg logit contributions
kin-0.001
pron-0.001
uren-0.001
 unison-0.001
utes-0.001
Token her
Token ID607
Feature activation+1.26e+00

Pos logit contributions
 aback+0.032
fired+0.028
 closer+0.028
 revenge+0.026
 away+0.025
Neg logit contributions
kin-0.041
pron-0.039
uren-0.036
lf-0.033
omo-0.032
Token to
Token ID284
Feature activation+1.09e+00

Pos logit contributions
 aback+0.018
fired+0.015
 closer+0.013
 away+0.013
 revenge+0.013
Neg logit contributions
kin-0.038
pron-0.037
uren-0.034
lf-0.032
ae-0.032
Token spread
Token ID4104
Feature activation+2.97e-02

Pos logit contributions
 aback+0.017
 closer+0.014
fired+0.014
 away+0.013
 revenge+0.013
Neg logit contributions
kin-0.032
pron-0.030
uren-0.029
omo-0.026
lf-0.026
Token some
Token ID617
Feature activation+1.04e+00

Pos logit contributions
 aback+0.001
fired+0.001
 closer+0.000
beh+0.000
 revenge+0.000
Neg logit contributions
kin-0.001
pron-0.001
uren-0.001
addy-0.001
 moons-0.001
Token peanut
Token ID26636
Feature activation+6.95e-03

Pos logit contributions
 aback+0.027
fired+0.026
beh+0.023
 closer+0.023
 revenge+0.022
Neg logit contributions
kin-0.020
pron-0.019
uren-0.014
 moons-0.014
 dots-0.013
Token butter
Token ID9215
Feature activation-9.69e-01

Pos logit contributions
 aback+0.000
fired+0.000
 closer+0.000
 revenge+0.000
beh+0.000
Neg logit contributions
kin-0.000
pron-0.000
uren-0.000
lf-0.000
 moons-0.000
Token on
Token ID319
Feature activation-7.72e-01

Pos logit contributions
kin+0.028
pron+0.026
uren+0.024
omo+0.022
lf+0.022
Neg logit contributions
 aback-0.016
 closer-0.014
fired-0.013
 away-0.012
 revenge-0.012
Token a
Token ID257
Feature activation-1.21e+00

Pos logit contributions
kin+0.021
pron+0.019
uren+0.018
omo+0.017
lf+0.017
Neg logit contributions
 aback-0.013
 closer-0.012
 away-0.011
fired-0.011
 home-0.011
Token piece
Token ID3704
Feature activation-6.99e-01

Pos logit contributions
kin+0.021
pron+0.020
uren+0.016
lf+0.014
ae+0.013
Neg logit contributions
 aback-0.035
fired-0.032
 closer-0.031
 revenge-0.030
beh-0.029
Token of
Token ID286
Feature activation-1.96e+00

Pos logit contributions
kin+0.018
pron+0.017
uren+0.017
omo+0.015
Adam+0.015
Neg logit contributions
 aback-0.012
 closer-0.011
fired-0.011
 away-0.011
 home-0.010
Token bread
Token ID8509
Feature activation-1.55e+00

Pos logit contributions
kin+0.043
pron+0.039
uren+0.036
omo+0.032
lf+0.032
Neg logit contributions
 aback-0.045
 closer-0.041
fired-0.040
 away-0.038
 revenge-0.038
Token.
Token ID13
Feature activation+3.41e-01

Pos logit contributions
kin+0.011
pron+0.010
uren+0.010
omo+0.009
lf+0.008
Neg logit contributions
 aback-0.007
 closer-0.007
fired-0.006
 away-0.006
 home-0.006
Token He
Token ID679
Feature activation-7.49e-02

Pos logit contributions
 aback+0.006
 closer+0.005
fired+0.005
 home+0.005
 revenge+0.005
Neg logit contributions
kin-0.009
pron-0.009
uren-0.008
lf-0.008
ae-0.007
Token feels
Token ID5300
Feature activation-4.09e-01

Pos logit contributions
kin+0.002
pron+0.002
uren+0.002
lf+0.001
omo+0.001
Neg logit contributions
 aback-0.002
 closer-0.001
fired-0.001
 away-0.001
 revenge-0.001
Token sorry
Token ID7926
Feature activation-1.43e-01

Pos logit contributions
kin+0.010
pron+0.009
uren+0.008
Adam+0.007
 moons+0.007
Neg logit contributions
 aback-0.008
fired-0.008
 closer-0.007
 home-0.007
 revenge-0.007
Token.
Token ID13
Feature activation+3.54e-01

Pos logit contributions
kin+0.004
pron+0.004
uren+0.003
omo+0.003
lf+0.003
Neg logit contributions
 aback-0.002
 closer-0.002
fired-0.002
 revenge-0.002
 away-0.002
Token He
Token ID679
Feature activation+2.42e-01

Pos logit contributions
 aback+0.007
 closer+0.006
fired+0.006
 home+0.005
 away+0.005
Neg logit contributions
kin-0.010
pron-0.009
uren-0.008
lf-0.008
ae-0.007
Token says
Token ID1139
Feature activation+8.07e-01

Pos logit contributions
 aback+0.005
 closer+0.005
fired+0.004
 away+0.004
 revenge+0.004
Neg logit contributions
kin-0.006
pron-0.006
uren-0.005
lf-0.005
ae-0.005
Token,
Token ID11
Feature activation+2.38e-01

Pos logit contributions
 aback+0.018
fired+0.016
 closer+0.015
 revenge+0.014
 away+0.014
Neg logit contributions
kin-0.018
pron-0.017
uren-0.015
 ma-0.014
lf-0.014
Token "
Token ID366
Feature activation+1.99e+00

Pos logit contributions
 aback+0.006
 closer+0.006
fired+0.005
 back+0.005
 away+0.005
Neg logit contributions
kin-0.005
pron-0.004
uren-0.004
omo-0.004
ae-0.004
TokenI
Token ID40
Feature activation+1.59e+00

Pos logit contributions
 aback+0.045
 closer+0.041
fired+0.040
 away+0.038
 revenge+0.038
Neg logit contributions
kin-0.044
pron-0.041
uren-0.038
lf-0.033
omo-0.033
Token am
Token ID716
Feature activation-1.78e+00

Pos logit contributions
 aback+0.030
 closer+0.026
fired+0.026
 away+0.024
 home+0.024
Neg logit contributions
kin-0.041
pron-0.037
uren-0.034
omo-0.033
Adam-0.031
Token big
Token ID1263
Feature activation-7.32e-01

Pos logit contributions
 aback+0.016
 closer+0.014
fired+0.014
 away+0.013
 revenge+0.013
Neg logit contributions
kin-0.018
pron-0.016
uren-0.015
omo-0.013
lf-0.013
Token and
Token ID290
Feature activation-6.73e-01

Pos logit contributions
kin+0.019
pron+0.017
uren+0.016
omo+0.015
Adam+0.014
Neg logit contributions
 aback-0.015
 closer-0.013
 away-0.012
fired-0.012
 home-0.012
Token red
Token ID2266
Feature activation-3.04e+00

Pos logit contributions
kin+0.015
pron+0.014
uren+0.012
omo+0.011
lf+0.011
Neg logit contributions
 aback-0.015
fired-0.014
 revenge-0.013
 closer-0.013
 home-0.013
Token!"
Token ID2474
Feature activation-3.10e+00

Pos logit contributions
kin+0.078
pron+0.075
uren+0.070
Adam+0.063
lf+0.062
Neg logit contributions
 aback-0.058
 closer-0.054
fired-0.050
 away-0.050
 home-0.049
Token
Token ID198
Feature activation-1.08e+00

Pos logit contributions
kin+0.096
pron+0.090
lf+0.082
uren+0.081
bridge+0.080
Neg logit contributions
 aback-0.046
 closer-0.044
fired-0.039
 home-0.038
 back-0.035
Token
Token ID198
Feature activation+1.93e-01

Pos logit contributions
kin+0.027
pron+0.025
uren+0.023
lf+0.021
 moons+0.021
Neg logit contributions
 aback-0.021
 closer-0.020
fired-0.019
 home-0.018
 away-0.017
Token"
Token ID1
Feature activation+2.24e+00

Pos logit contributions
 aback+0.003
 closer+0.003
fired+0.003
 away+0.003
 home+0.003
Neg logit contributions
kin-0.005
pron-0.005
 moons-0.004
uren-0.004
bridge-0.004
TokenIt
Token ID1026
Feature activation+1.80e+00

Pos logit contributions
 aback+0.041
 closer+0.041
 nearer+0.034
 away+0.034
fired+0.034
Neg logit contributions
kin-0.056
pron-0.052
uren-0.049
lf-0.048
omo-0.046
Token is
Token ID318
Feature activation-1.54e+00

Pos logit contributions
 aback+0.040
fired+0.037
 closer+0.035
 home+0.035
 revenge+0.035
Neg logit contributions
kin-0.037
pron-0.034
uren-0.031
omo-0.028
 moons-0.028
Token funny
Token ID8258
Feature activation-1.86e+00

Pos logit contributions
kin+0.041
pron+0.039
uren+0.037
lf+0.033
Adam+0.033
Neg logit contributions
 aback-0.028
 closer-0.025
fired-0.023
 away-0.023
 home-0.022
Token,
Token ID11
Feature activation-3.75e+00

Pos logit contributions
kin+0.049
pron+0.046
uren+0.042
Adam+0.038
omo+0.038
Neg logit contributions
 aback-0.035
 closer-0.032
fired-0.030
 home-0.029
 away-0.029
Token.
Token ID13
Feature activation+5.52e-01

Pos logit contributions
kin+0.011
pron+0.010
uren+0.009
lf+0.008
omo+0.008
Neg logit contributions
 aback-0.009
fired-0.008
 closer-0.008
 revenge-0.007
 away-0.007
Token The
Token ID383
Feature activation-5.03e-01

Pos logit contributions
 aback+0.012
 closer+0.011
fired+0.011
 away+0.010
 home+0.010
Neg logit contributions
kin-0.013
pron-0.012
uren-0.011
lf-0.010
omo-0.010
Token end
Token ID886
Feature activation+2.11e+00

Pos logit contributions
kin+0.013
pron+0.013
uren+0.012
addy+0.011
ae+0.011
Neg logit contributions
 closer-0.009
 home-0.008
 back-0.008
 aback-0.008
 away-0.008
Token.
Token ID13
Feature activation+9.30e-01

Pos logit contributions
 aback+0.050
fired+0.044
 closer+0.043
 revenge+0.041
 away+0.040
Neg logit contributions
kin-0.045
pron-0.042
uren-0.037
omo-0.035
lf-0.034
Token<|endoftext|>
Token ID50256
Feature activation-1.26e+00

Pos logit contributions
 aback+0.021
 closer+0.019
fired+0.019
 away+0.017
 revenge+0.017
Neg logit contributions
kin-0.021
pron-0.019
uren-0.018
lf-0.016
omo-0.016
TokenOnce
Token ID7454
Feature activation-1.62e-01

Pos logit contributions
kin+0.031
pron+0.029
uren+0.027
omo+0.024
lf+0.024
Neg logit contributions
 aback-0.025
 closer-0.023
fired-0.022
 home-0.021
 away-0.021
Token upon
Token ID2402
Feature activation-2.67e+00

Pos logit contributions
kin+0.003
pron+0.003
uren+0.003
 scalp+0.002
bridge+0.002
Neg logit contributions
 aback-0.004
 closer-0.004
 home-0.004
fired-0.004
 away-0.004
Token a
Token ID257
Feature activation+5.68e-01

Pos logit contributions
kin+0.086
uren+0.082
pron+0.082
omo+0.074
 majesty+0.074
Neg logit contributions
 closer-0.029
 aback-0.028
 home-0.023
 away-0.023
 back-0.022
Token time
Token ID640
Feature activation+1.02e+00

Pos logit contributions
 aback+0.014
 closer+0.013
 home+0.012
 away+0.012
fired+0.012
Neg logit contributions
kin-0.011
pron-0.009
uren-0.009
bridge-0.008
 moons-0.008
Token,
Token ID11
Feature activation-2.45e-01

Pos logit contributions
 aback+0.020
 closer+0.017
fired+0.017
 away+0.016
 revenge+0.016
Neg logit contributions
kin-0.026
pron-0.024
uren-0.023
omo-0.020
lf-0.020
Token there
Token ID612
Feature activation-2.10e+00

Pos logit contributions
kin+0.006
pron+0.005
uren+0.005
omo+0.004
lf+0.004
Neg logit contributions
 aback-0.005
 closer-0.005
fired-0.005
 revenge-0.004
 away-0.004
Token their
Token ID511
Feature activation+1.59e-01

Pos logit contributions
 aback+0.027
fired+0.024
beh+0.023
 closer+0.022
 revenge+0.022
Neg logit contributions
kin-0.021
pron-0.019
uren-0.018
Adam-0.016
lf-0.016
Token beds
Token ID20237
Feature activation-2.06e+00

Pos logit contributions
 aback+0.005
fired+0.004
 closer+0.004
beh+0.004
smart+0.004
Neg logit contributions
kin-0.002
pron-0.002
lf-0.002
omo-0.002
uren-0.002
Token.
Token ID13
Feature activation+2.87e-01

Pos logit contributions
kin+0.053
pron+0.050
uren+0.048
omo+0.043
lf+0.042
Neg logit contributions
 aback-0.038
 closer-0.035
fired-0.034
 away-0.033
 home-0.033
Token They
Token ID1119
Feature activation-2.48e+00

Pos logit contributions
 aback+0.005
 closer+0.005
 home+0.005
 away+0.005
 back+0.004
Neg logit contributions
kin-0.007
pron-0.007
lf-0.006
uren-0.006
bridge-0.006
Token c
Token ID269
Feature activation-8.89e-01

Pos logit contributions
kin+0.067
pron+0.066
uren+0.062
omo+0.058
lf+0.056
Neg logit contributions
 closer-0.042
 aback-0.039
 away-0.039
 back-0.036
 home-0.036
Tokenuddle
Token ID24500
Feature activation-3.63e+00

Pos logit contributions
kin+0.019
pron+0.017
uren+0.016
lf+0.014
omo+0.013
Neg logit contributions
 aback-0.021
 closer-0.019
fired-0.019
 away-0.018
 home-0.018
Token with
Token ID351
Feature activation+9.69e-01

Pos logit contributions
kin+0.088
pron+0.081
uren+0.075
omo+0.068
lf+0.068
Neg logit contributions
 aback-0.075
 closer-0.066
fired-0.066
 revenge-0.061
 away-0.061
Token their
Token ID511
Feature activation-8.18e-01

Pos logit contributions
 aback+0.019
 closer+0.017
fired+0.016
 away+0.016
 home+0.016
Neg logit contributions
kin-0.024
pron-0.023
uren-0.021
lf-0.019
omo-0.019
Token blankets
Token ID34794
Feature activation-1.40e+00

Pos logit contributions
kin+0.017
pron+0.016
uren+0.014
omo+0.013
lf+0.013
Neg logit contributions
 aback-0.020
fired-0.017
 closer-0.017
 away-0.016
 revenge-0.016
Token and
Token ID290
Feature activation-7.68e-02

Pos logit contributions
kin+0.036
pron+0.036
uren+0.035
Adam+0.031
omo+0.031
Neg logit contributions
 aback-0.025
 closer-0.024
 away-0.024
 home-0.023
 back-0.022
Token pill
Token ID9582
Feature activation-2.98e+00

Pos logit contributions
kin+0.002
pron+0.002
uren+0.002
omo+0.001
lf+0.001
Neg logit contributions
 aback-0.002
 closer-0.002
fired-0.001
 away-0.001
 home-0.001
Token big
Token ID1263
Feature activation+1.90e+00

Pos logit contributions
 aback+0.005
fired+0.004
 closer+0.004
 away+0.004
 revenge+0.004
Neg logit contributions
kin-0.005
pron-0.005
uren-0.005
lf-0.004
omo-0.004
Token desk
Token ID6915
Feature activation-8.27e-01

Pos logit contributions
 aback+0.043
 closer+0.038
fired+0.038
 revenge+0.035
 away+0.035
Neg logit contributions
kin-0.043
pron-0.040
uren-0.036
lf-0.033
omo-0.032
Token,
Token ID11
Feature activation-3.72e+00

Pos logit contributions
kin+0.023
pron+0.022
uren+0.021
omo+0.019
 scalp+0.019
Neg logit contributions
 aback-0.013
 closer-0.012
 away-0.012
fired-0.012
 home-0.011
Token a
Token ID257
Feature activation-1.65e+00

Pos logit contributions
kin+0.109
pron+0.103
uren+0.097
omo+0.091
ae+0.088
Neg logit contributions
 aback-0.055
 closer-0.052
fired-0.045
 away-0.044
 revenge-0.042
Token phone
Token ID3072
Feature activation+1.09e-01

Pos logit contributions
kin+0.037
pron+0.034
uren+0.032
omo+0.029
lf+0.028
Neg logit contributions
 aback-0.035
 closer-0.033
fired-0.032
 away-0.030
 home-0.030
Token,
Token ID11
Feature activation-4.15e+00

Pos logit contributions
 aback+0.002
 closer+0.002
 away+0.002
fired+0.002
 home+0.001
Neg logit contributions
kin-0.003
pron-0.003
uren-0.003
ae-0.003
omo-0.003
Token a
Token ID257
Feature activation-2.34e+00

Pos logit contributions
kin+0.121
pron+0.113
uren+0.107
omo+0.100
ae+0.098
Neg logit contributions
 aback-0.064
 closer-0.060
 away-0.053
fired-0.053
 home-0.050
Token computer
Token ID3644
Feature activation-6.32e-01

Pos logit contributions
kin+0.055
pron+0.049
uren+0.047
omo+0.043
Adam+0.042
Neg logit contributions
 aback-0.047
 closer-0.045
fired-0.043
 away-0.041
 home-0.041
Token and
Token ID290
Feature activation-1.03e+00

Pos logit contributions
kin+0.019
pron+0.018
uren+0.017
omo+0.016
ae+0.016
Neg logit contributions
 aback-0.008
 away-0.008
 closer-0.008
 back-0.007
 home-0.007
Token some
Token ID617
Feature activation-1.20e+00

Pos logit contributions
kin+0.028
pron+0.026
uren+0.024
omo+0.022
lf+0.022
Neg logit contributions
 aback-0.018
 closer-0.016
fired-0.016
 away-0.015
 revenge-0.015
Token papers
Token ID9473
Feature activation-2.08e+00

Pos logit contributions
kin+0.026
pron+0.024
uren+0.022
lf+0.020
omo+0.020
Neg logit contributions
 aback-0.027
 closer-0.024
fired-0.024
 away-0.023
 revenge-0.022
Token nightmare
Token ID17123
Feature activation+7.03e-01

Pos logit contributions
kin+0.031
pron+0.029
uren+0.028
Adam+0.024
ae+0.024
Neg logit contributions
 aback-0.023
 closer-0.021
 home-0.020
 away-0.020
fired-0.019
Token couldn
Token ID3521
Feature activation-6.94e-01

Pos logit contributions
 aback+0.014
 closer+0.013
fired+0.012
 away+0.012
 revenge+0.012
Neg logit contributions
kin-0.017
pron-0.016
uren-0.015
omo-0.014
Adam-0.014
Token't
Token ID470
Feature activation-3.15e-01

Pos logit contributions
kin+0.012
pron+0.010
uren+0.009
lf+0.008
omo+0.008
Neg logit contributions
 aback-0.019
fired-0.018
 closer-0.018
 revenge-0.017
 away-0.016
Token hurt
Token ID5938
Feature activation-1.63e+00

Pos logit contributions
kin+0.008
pron+0.008
uren+0.007
omo+0.006
Adam+0.006
Neg logit contributions
 aback-0.006
 closer-0.006
fired-0.005
 away-0.005
 home-0.005
Token her
Token ID607
Feature activation-1.43e+00

Pos logit contributions
kin+0.040
pron+0.035
uren+0.034
lf+0.031
ia+0.030
Neg logit contributions
 aback-0.033
fired-0.028
 closer-0.028
 revenge-0.026
 nearer-0.025
Token,
Token ID11
Feature activation-4.10e+00

Pos logit contributions
kin+0.035
pron+0.033
uren+0.032
omo+0.028
Adam+0.028
Neg logit contributions
 aback-0.028
 closer-0.026
fired-0.025
 away-0.025
 home-0.025
Token so
Token ID523
Feature activation+5.86e-01

Pos logit contributions
kin+0.095
pron+0.087
uren+0.082
omo+0.074
ae+0.073
Neg logit contributions
 aback-0.089
 closer-0.084
fired-0.078
 away-0.078
 home-0.077
Token she
Token ID673
Feature activation-2.20e-01

Pos logit contributions
 aback+0.013
 closer+0.012
fired+0.011
 away+0.011
 home+0.011
Neg logit contributions
kin-0.014
pron-0.013
uren-0.012
omo-0.010
Adam-0.010
Token lay
Token ID3830
Feature activation-1.72e+00

Pos logit contributions
kin+0.005
pron+0.005
uren+0.005
Adam+0.004
omo+0.004
Neg logit contributions
 aback-0.004
 closer-0.004
 away-0.004
fired-0.004
 home-0.004
Token in
Token ID287
Feature activation+8.06e-01

Pos logit contributions
kin+0.058
pron+0.055
uren+0.052
omo+0.049
lf+0.049
Neg logit contributions
 aback-0.019
 closer-0.016
fired-0.015
 away-0.014
 home-0.013
Token bed
Token ID3996
Feature activation-2.86e+00

Pos logit contributions
 aback+0.016
 closer+0.015
fired+0.014
 away+0.014
 home+0.014
Neg logit contributions
kin-0.020
pron-0.018
uren-0.017
omo-0.015
lf-0.015
Token You
Token ID921
Feature activation-1.09e+00

Pos logit contributions
 aback+0.001
 closer+0.001
fired+0.001
 revenge+0.001
 away+0.001
Neg logit contributions
kin-0.001
pron-0.001
uren-0.001
lf-0.001
omo-0.001
Token are
Token ID389
Feature activation-2.00e+00

Pos logit contributions
kin+0.028
pron+0.026
uren+0.024
omo+0.022
lf+0.022
Neg logit contributions
 aback-0.021
 closer-0.019
fired-0.018
 away-0.018
 revenge-0.017
Token a
Token ID257
Feature activation-4.25e-01

Pos logit contributions
kin+0.052
pron+0.049
uren+0.046
omo+0.042
lf+0.041
Neg logit contributions
 aback-0.037
 closer-0.033
fired-0.032
 away-0.030
 revenge-0.030
Token good
Token ID922
Feature activation+1.04e+00

Pos logit contributions
kin+0.010
pron+0.010
uren+0.008
omo+0.008
lf+0.007
Neg logit contributions
 aback-0.009
fired-0.008
 closer-0.008
 revenge-0.007
 nearer-0.007
Token girl
Token ID2576
Feature activation+9.74e-01

Pos logit contributions
 aback+0.019
 closer+0.017
fired+0.017
 away+0.016
 home+0.016
Neg logit contributions
kin-0.027
pron-0.025
uren-0.024
lf-0.021
omo-0.021
Token,
Token ID11
Feature activation-4.08e+00

Pos logit contributions
 aback+0.021
 closer+0.019
fired+0.018
 away+0.018
 home+0.017
Neg logit contributions
kin-0.023
pron-0.021
uren-0.020
omo-0.018
lf-0.017
Token Lily
Token ID20037
Feature activation-1.22e+00

Pos logit contributions
kin+0.100
pron+0.089
uren+0.086
lf+0.077
bridge+0.077
Neg logit contributions
 aback-0.079
 closer-0.077
 home-0.072
 back-0.070
 away-0.069
Token.
Token ID13
Feature activation+6.36e-01

Pos logit contributions
kin+0.033
pron+0.031
uren+0.030
omo+0.027
ae+0.027
Neg logit contributions
 aback-0.021
 away-0.019
 home-0.019
fired-0.019
 closer-0.018
Token You
Token ID921
Feature activation-9.39e-01

Pos logit contributions
 aback+0.013
fired+0.011
 closer+0.011
 revenge+0.010
 home+0.010
Neg logit contributions
kin-0.016
pron-0.015
uren-0.013
lf-0.012
ae-0.012
Token can
Token ID460
Feature activation-5.23e-01

Pos logit contributions
kin+0.024
pron+0.022
uren+0.021
omo+0.019
lf+0.019
Neg logit contributions
 aback-0.019
 closer-0.016
fired-0.016
 away-0.016
 revenge-0.015
Token help
Token ID1037
Feature activation+1.17e+00

Pos logit contributions
kin+0.012
pron+0.011
uren+0.010
lf+0.009
omo+0.009
Neg logit contributions
 aback-0.011
 closer-0.010
fired-0.010
 away-0.010
 revenge-0.010
Token tr
Token ID491
Feature activation+2.24e-02

Pos logit contributions
kin+0.008
pron+0.008
uren+0.007
Adam+0.007
ae+0.007
Neg logit contributions
 aback-0.007
 closer-0.007
fired-0.006
 home-0.006
 away-0.006
Tokenamp
Token ID696
Feature activation-2.97e+00

Pos logit contributions
 aback+0.001
 closer+0.001
fired+0.001
 away+0.000
 revenge+0.000
Neg logit contributions
kin-0.000
pron-0.000
uren-0.000
omo-0.000
lf-0.000
Tokenoline
Token ID14453
Feature activation-1.89e+00

Pos logit contributions
kin+0.054
pron+0.053
uren+0.048
omo+0.042
 majesty+0.042
Neg logit contributions
 aback-0.074
 away-0.069
 closer-0.068
fired-0.067
 home-0.064
Token and
Token ID290
Feature activation-5.52e-01

Pos logit contributions
kin+0.051
pron+0.050
uren+0.047
omo+0.043
Adam+0.042
Neg logit contributions
 aback-0.031
 closer-0.029
fired-0.028
 away-0.027
 home-0.026
Token a
Token ID257
Feature activation-9.01e-01

Pos logit contributions
kin+0.014
pron+0.013
uren+0.012
omo+0.011
Adam+0.011
Neg logit contributions
 aback-0.011
 closer-0.010
fired-0.009
 away-0.009
 home-0.009
Token sandbox
Token ID35204
Feature activation-4.68e+00

Pos logit contributions
kin+0.021
pron+0.019
uren+0.018
Adam+0.017
ae+0.017
Neg logit contributions
 aback-0.018
 closer-0.018
fired-0.016
 home-0.016
 away-0.016
Token.
Token ID13
Feature activation+5.47e-01

Pos logit contributions
pron+0.133
uren+0.133
kin+0.130
Adam+0.116
 Avery+0.113
Neg logit contributions
 aback-0.064
 closer-0.063
 away-0.062
 home-0.061
fired-0.059
Token He
Token ID679
Feature activation-7.95e-01

Pos logit contributions
 aback+0.011
 closer+0.008
 home+0.008
 back+0.008
 down+0.008
Neg logit contributions
kin-0.016
pron-0.014
lf-0.012
uren-0.012
utes-0.012
Token was
Token ID373
Feature activation-1.48e+00

Pos logit contributions
kin+0.020
pron+0.019
uren+0.018
Adam+0.016
 scalp+0.016
Neg logit contributions
 aback-0.014
 closer-0.014
fired-0.013
 away-0.012
 home-0.012
Token having
Token ID1719
Feature activation-3.30e-01

Pos logit contributions
kin+0.046
pron+0.043
uren+0.041
lf+0.038
omo+0.037
Neg logit contributions
 aback-0.021
 closer-0.021
 home-0.019
 away-0.017
 back-0.017
Token so
Token ID523
Feature activation+1.45e+00

Pos logit contributions
kin+0.010
pron+0.009
uren+0.009
lf+0.008
omo+0.008
Neg logit contributions
 aback-0.006
 closer-0.005
 home-0.004
fired-0.004
 away-0.004