TOP ACTIVATIONS
MAX = 5.981

a mighty cat called L ulu . Every day L ulu
says " W oof Wo of Delivery ". M
was a girl called L ulu who wanted to escape .
have fun and laugh a lot . They do not miss
are happy and laugh a lot . But then
is playful and laughs a lot . She likes Sara and
Tim my a warm , freshly baked cookie .
" My name is L ulu , and I love cream
of fun and laugh a lot . They are
, and Leo smiled a lot . He was very grateful
, a bird named L ulu , who would visit her
funny shows and laugh a lot . Sometimes Tom lets Lily
of fun and laughed a lot . " Anna
are happy and laugh a lot . One day
have fun and laugh a lot . One day
and he always kept an eye out for any junk .
a little bird called L izz ie . She was sitting
of fun and laughed a lot . But then
gigg led and smiled a lot . One day she asked
, a bird named L ulu . L ulu liked to

MIN ACTIVATIONS
MIN = -9.398

dog . They left their missile behind and went back to
safe again . The town spe ople thanked the bear many
Uh - oh , our missile is ruined !" Tim cried
to his mom 's needle work box and took out a
rock and falls off his motorcycle . He hurts his knee
The town spe ople had to find a
back to shore and he drowned in the sea .
too strong . They both drowned , and their bodies were
counter fixed her car in no time . Jane thanked the
shine through . The town spe ople were very happy and
They ran back to the je ep . They saw the
Thank you , Mr . Mechan ic !" Tim my said
Ben slides down , his rh ino falls out of his
into the water . Tom drowned in the water and died
when he noticed that the rh in oc eros looked very
, Mom ! There 's no frog in the mailbox ."
your friends . There 's no need to be sorry when
couldn 't swim and he drowned . The people
room to the other in no time . Just
, Mia . There 's no snake in the log .

INTERVAL 2.136 - 5.981
CONTAINS 3.503%

met a little girl named Lily . Lily was playing near
park again . He hopes Sue will go on the slide
, the old anchor showed her how to move her arms
cut the vegetables as fast as he could , but he
girl named Sarah wanted to dress up . She went to

INTERVAL -1.709 - 2.136
CONTAINS 89.684%

my had a toy truck that he loved to play with
making the meal . When they sat down to
One day , the bear was walking through the
They tried to pull it , push it , and roll
bed . She threw the paper in the trash and yelled

INTERVAL -5.553 - -1.709
CONTAINS 6.813%

stick and pushed the mean pirate away . He pushed them
the dragon heard the giant roar , he didn 't get
they were always happy because they were having fun together all
made a sound . The cat smiled and lay down .
back again soon . <|endoftext|> Charlie loved to climb . He

INTERVAL -9.398 - -5.553
CONTAINS 0.001%

shine through . The town spe ople were very happy and
so hungry . There 's no food to chew here and
. The town spe ople were amazed by this
arrived to his destination in no time .
! The town spe ople were sad and scared
Token a
Token ID257
Feature activation+6.10e-03

Pos logit contributions
Bad+0.023
 narrative+0.022
 exploded+0.022
rob+0.021
 bomb+0.021
Neg logit contributions
raid-0.014
 She-0.013
 polish-0.012
 her-0.012
reath-0.012
Token mighty
Token ID18680
Feature activation+2.40e-01

Pos logit contributions
raid+0.000
reath+0.000
ears+0.000
wn+0.000
she+0.000
Neg logit contributions
Bad-0.000
 exploded-0.000
Did-0.000
 narrative-0.000
 bomb-0.000
Token cat
Token ID3797
Feature activation-7.17e-01

Pos logit contributions
raid+0.010
reath+0.008
ears+0.008
wn+0.008
she+0.008
Neg logit contributions
Bad-0.007
 exploded-0.006
 bomb-0.006
 narrative-0.006
rob-0.006
Token called
Token ID1444
Feature activation+3.05e+00

Pos logit contributions
Bad+0.020
 narrative+0.018
 exploded+0.017
 bomb+0.017
Did+0.016
Neg logit contributions
raid-0.030
 She-0.025
reath-0.025
ears-0.025
 polish-0.024
Token L
Token ID406
Feature activation+4.21e+00

Pos logit contributions
raid+0.120
reath+0.104
ears+0.100
 polish+0.096
wn+0.096
Neg logit contributions
Bad-0.089
 exploded-0.079
 narrative-0.078
Did-0.077
 bomb-0.076
Tokenulu
Token ID15712
Feature activation+5.98e+00

Pos logit contributions
raid+0.121
reath+0.098
 polish+0.091
wn+0.088
 attention+0.088
Neg logit contributions
Bad-0.161
 narrative-0.151
 exploded-0.151
Did-0.149
rob-0.147
Token.
Token ID13
Feature activation+6.40e-02

Pos logit contributions
raid+0.182
reath+0.151
ears+0.142
wn+0.135
 polish+0.135
Neg logit contributions
Bad-0.228
 exploded-0.210
 narrative-0.208
Did-0.207
rob-0.203
Token Every
Token ID3887
Feature activation+2.52e+00

Pos logit contributions
raid+0.002
reath+0.002
annah+0.002
erry+0.002
wn+0.002
Neg logit contributions
Bad-0.002
Did-0.002
 narrative-0.002
 no-0.001
 exploded-0.001
Token day
Token ID1110
Feature activation-1.20e-01

Pos logit contributions
raid+0.079
reath+0.066
ears+0.064
annah+0.059
she+0.059
Neg logit contributions
Bad-0.093
 exploded-0.087
 narrative-0.085
 bomb-0.085
Did-0.084
Token L
Token ID406
Feature activation+2.56e+00

Pos logit contributions
Bad+0.003
 exploded+0.003
Did+0.003
 narrative+0.003
 bomb+0.003
Neg logit contributions
raid-0.005
reath-0.004
wn-0.004
ears-0.004
annah-0.004
Tokenulu
Token ID15712
Feature activation+3.98e+00

Pos logit contributions
raid+0.077
reath+0.061
wn+0.059
 polish+0.058
 attention+0.055
Neg logit contributions
Bad-0.095
 narrative-0.089
 exploded-0.087
Did-0.087
rob-0.085
Token says
Token ID1139
Feature activation+7.87e-01

Pos logit contributions
Bad+0.095
 narrative+0.086
Did+0.086
 exploded+0.086
rob+0.085
Neg logit contributions
raid-0.088
reath-0.074
ears-0.071
 polish-0.068
she-0.067
Token "
Token ID366
Feature activation+4.66e-01

Pos logit contributions
raid+0.024
reath+0.020
ears+0.019
 She+0.018
 polish+0.018
Neg logit contributions
Bad-0.029
 narrative-0.028
rob-0.027
 exploded-0.027
Did-0.026
TokenW
Token ID54
Feature activation-1.03e+00

Pos logit contributions
raid+0.019
reath+0.017
ears+0.017
annah+0.016
 polish+0.016
Neg logit contributions
Bad-0.013
Did-0.011
 exploded-0.011
 narrative-0.011
rob-0.011
Tokenoof
Token ID37711
Feature activation+5.54e-01

Pos logit contributions
Bad+0.017
sed+0.014
 exploded+0.014
rob+0.014
boys+0.013
Neg logit contributions
she-0.048
raid-0.047
 polish-0.044
 she-0.044
 She-0.044
Token Wo
Token ID22173
Feature activation+1.21e+00

Pos logit contributions
raid+0.021
reath+0.018
 polish+0.018
she+0.018
wn+0.017
Neg logit contributions
Bad-0.016
 exploded-0.014
 bomb-0.014
Did-0.013
boys-0.013
Tokenof
Token ID1659
Feature activation+5.93e+00

Pos logit contributions
raid+0.032
she+0.029
 polish+0.028
reath+0.028
 comfortable+0.027
Neg logit contributions
Bad-0.045
 unison-0.040
 narrative-0.040
 bomb-0.040
rob-0.039
Token Delivery
Token ID28682
Feature activation+1.37e+00

Pos logit contributions
raid+0.207
reath+0.174
ears+0.167
 polish+0.162
wn+0.161
Neg logit contributions
Bad-0.199
 exploded-0.180
 narrative-0.177
Did-0.174
 bomb-0.174
Token".
Token ID1911
Feature activation+3.07e-01

Pos logit contributions
raid+0.048
reath+0.042
ears+0.040
she+0.039
wn+0.039
Neg logit contributions
Bad-0.045
 exploded-0.040
 bomb-0.039
rob-0.038
Did-0.038
Token
Token ID198
Feature activation+1.34e-01

Pos logit contributions
raid+0.010
reath+0.008
ears+0.008
 polish+0.007
wn+0.007
Neg logit contributions
Bad-0.011
 exploded-0.010
 narrative-0.010
Did-0.010
rob-0.010
Token
Token ID198
Feature activation+2.42e-01

Pos logit contributions
raid+0.005
reath+0.004
ears+0.004
wn+0.004
 polish+0.004
Neg logit contributions
Bad-0.004
 exploded-0.004
Did-0.004
 narrative-0.004
rob-0.004
TokenM
Token ID44
Feature activation+2.10e+00

Pos logit contributions
raid+0.009
reath+0.008
ears+0.007
 She+0.007
she+0.007
Neg logit contributions
Bad-0.008
 exploded-0.007
 narrative-0.007
rob-0.007
 bomb-0.007
Token was
Token ID373
Feature activation-6.65e-01

Pos logit contributions
raid+0.023
 She+0.020
 polish+0.020
ears+0.019
she+0.019
Neg logit contributions
Bad-0.020
 narrative-0.019
 bomb-0.018
rob-0.018
 exploded-0.018
Token a
Token ID257
Feature activation-3.85e-02

Pos logit contributions
Bad+0.028
 narrative+0.027
 exploded+0.027
rob+0.026
illas+0.026
Neg logit contributions
 She-0.014
raid-0.014
 her-0.013
 polish-0.013
 comfortable-0.013
Token girl
Token ID2576
Feature activation+1.70e+00

Pos logit contributions
Bad+0.002
 exploded+0.001
 narrative+0.001
Did+0.001
 bomb+0.001
Neg logit contributions
raid-0.001
reath-0.001
ears-0.001
wn-0.001
 polish-0.001
Token called
Token ID1444
Feature activation+2.89e+00

Pos logit contributions
raid+0.078
 She+0.065
 polish+0.065
ears+0.064
reath+0.063
Neg logit contributions
Bad-0.041
 narrative-0.037
 exploded-0.037
rob-0.037
 bomb-0.034
Token L
Token ID406
Feature activation+3.88e+00

Pos logit contributions
raid+0.098
reath+0.086
ears+0.079
wn+0.078
 polish+0.076
Neg logit contributions
Bad-0.098
 exploded-0.089
Did-0.088
 narrative-0.087
 bomb-0.086
Tokenulu
Token ID15712
Feature activation+5.90e+00

Pos logit contributions
raid+0.116
reath+0.095
 attention+0.086
 polish+0.086
wn+0.085
Neg logit contributions
Bad-0.144
 narrative-0.137
Did-0.135
 exploded-0.134
rob-0.132
Token who
Token ID508
Feature activation-2.85e-01

Pos logit contributions
raid+0.177
reath+0.145
ears+0.138
 polish+0.130
wn+0.128
Neg logit contributions
Bad-0.230
 exploded-0.211
 narrative-0.211
Did-0.208
rob-0.205
Token wanted
Token ID2227
Feature activation+4.50e-01

Pos logit contributions
Bad+0.006
Did+0.005
 exploded+0.005
Our+0.005
 narrative+0.004
Neg logit contributions
raid-0.014
reath-0.013
ears-0.012
andel-0.012
annah-0.012
Token to
Token ID284
Feature activation+1.44e+00

Pos logit contributions
raid+0.013
reath+0.012
ears+0.011
annah+0.010
wn+0.010
Neg logit contributions
Bad-0.017
 exploded-0.016
Did-0.016
 bomb-0.016
Our-0.015
Token escape
Token ID6654
Feature activation-6.78e-01

Pos logit contributions
raid+0.046
ears+0.044
reath+0.042
wn+0.041
annah+0.040
Neg logit contributions
 exploded-0.044
Bad-0.043
 unison-0.040
boys-0.040
Our-0.040
Token.
Token ID13
Feature activation-2.05e-01

Pos logit contributions
Bad+0.021
 narrative+0.020
 exploded+0.019
 bomb+0.019
boys+0.019
Neg logit contributions
raid-0.024
reath-0.021
wn-0.020
ears-0.020
annah-0.019
Token have
Token ID423
Feature activation-7.30e-01

Pos logit contributions
raid+0.005
reath+0.004
ears+0.004
wn+0.004
 polish+0.004
Neg logit contributions
Bad-0.005
 exploded-0.005
 narrative-0.005
Did-0.005
rob-0.004
Token fun
Token ID1257
Feature activation+3.71e-01

Pos logit contributions
Bad+0.037
 narrative+0.036
storm+0.035
 bomb+0.035
Run+0.035
Neg logit contributions
raid-0.010
 comfortable-0.008
 care-0.008
ears-0.008
 polish-0.008
Token and
Token ID290
Feature activation+4.00e-01

Pos logit contributions
raid+0.005
 she+0.003
ears+0.003
 her+0.003
 She+0.003
Neg logit contributions
Bad-0.020
 exploded-0.019
 narrative-0.019
rob-0.019
 bomb-0.019
Token laugh
Token ID6487
Feature activation+2.92e-01

Pos logit contributions
raid+0.010
reath+0.008
 care+0.008
 polish+0.008
 attention+0.007
Neg logit contributions
Bad-0.017
 exploded-0.016
rob-0.016
Did-0.016
 bomb-0.016
Token a
Token ID257
Feature activation+1.24e+00

Pos logit contributions
raid+0.006
 She+0.005
reath+0.005
 polish+0.004
ears+0.004
Neg logit contributions
Bad-0.013
rob-0.013
 exploded-0.012
 narrative-0.012
 bomb-0.012
Token lot
Token ID1256
Feature activation+5.82e+00

Pos logit contributions
raid+0.020
reath+0.018
 care+0.014
 polish+0.014
ears+0.014
Neg logit contributions
Bad-0.060
 exploded-0.058
Did-0.057
 narrative-0.056
boys-0.056
Token.
Token ID13
Feature activation+4.64e-01

Pos logit contributions
raid+0.166
reath+0.134
ears+0.127
 polish+0.119
wn+0.118
Neg logit contributions
Bad-0.236
 exploded-0.217
 narrative-0.215
Did-0.215
rob-0.211
Token They
Token ID1119
Feature activation+2.58e-01

Pos logit contributions
 She+0.010
raid+0.009
ears+0.007
 name+0.007
 welcome+0.006
Neg logit contributions
Bad-0.021
rob-0.021
 exploded-0.021
 bomb-0.020
storm-0.020
Token do
Token ID466
Feature activation+3.36e-01

Pos logit contributions
raid+0.010
reath+0.009
ears+0.009
wn+0.008
she+0.008
Neg logit contributions
Bad-0.007
 narrative-0.007
 exploded-0.007
Did-0.006
rob-0.006
Token not
Token ID407
Feature activation-1.48e+00

Pos logit contributions
raid+0.013
reath+0.012
ears+0.011
 polish+0.011
she+0.011
Neg logit contributions
Bad-0.009
 exploded-0.008
 narrative-0.008
Did-0.008
rob-0.008
Token miss
Token ID2051
Feature activation-2.02e+00

Pos logit contributions
Bad+0.060
 exploded+0.056
 narrative+0.054
Did+0.053
 bomb+0.053
Neg logit contributions
raid-0.039
reath-0.035
ears-0.034
she-0.031
annah-0.031
Token are
Token ID389
Feature activation-6.02e-01

Pos logit contributions
Bad+0.002
 exploded+0.002
 narrative+0.002
Did+0.002
 bomb+0.002
Neg logit contributions
raid-0.002
reath-0.002
ears-0.002
wn-0.002
annah-0.002
Token happy
Token ID3772
Feature activation+3.41e-01

Pos logit contributions
Bad+0.022
 exploded+0.020
Did+0.020
 narrative+0.019
 bomb+0.019
Neg logit contributions
raid-0.020
reath-0.017
ears-0.016
wn-0.015
 polish-0.015
Token and
Token ID290
Feature activation+1.26e+00

Pos logit contributions
raid+0.008
ears+0.007
 She+0.006
 polish+0.006
 she+0.006
Neg logit contributions
Bad-0.015
 narrative-0.015
rob-0.014
 exploded-0.014
 bomb-0.014
Token laugh
Token ID6487
Feature activation+6.83e-01

Pos logit contributions
raid+0.041
ears+0.033
reath+0.033
erry+0.030
andel+0.030
Neg logit contributions
Bad-0.047
 exploded-0.044
Did-0.042
boys-0.041
Our-0.041
Token a
Token ID257
Feature activation+1.63e+00

Pos logit contributions
raid+0.017
reath+0.013
 She+0.013
 polish+0.012
she+0.012
Neg logit contributions
Bad-0.029
 narrative-0.028
 exploded-0.027
rob-0.027
 bomb-0.027
Token lot
Token ID1256
Feature activation+5.80e+00

Pos logit contributions
raid+0.035
reath+0.029
ears+0.025
 polish+0.024
 She+0.023
Neg logit contributions
Bad-0.074
 narrative-0.070
 exploded-0.070
Did-0.068
rob-0.068
Token.
Token ID13
Feature activation-6.98e-02

Pos logit contributions
raid+0.186
reath+0.157
ears+0.149
wn+0.143
 polish+0.142
Neg logit contributions
Bad-0.206
 exploded-0.191
 narrative-0.190
 bomb-0.187
Did-0.184
Token
Token ID198
Feature activation-5.14e-01

Pos logit contributions
Bad+0.003
 exploded+0.003
 narrative+0.003
rob+0.003
 bomb+0.003
Neg logit contributions
raid-0.002
 She-0.002
ears-0.001
reath-0.001
she-0.001
Token
Token ID198
Feature activation-1.21e-01

Pos logit contributions
Bad+0.017
 exploded+0.016
Did+0.016
 narrative+0.016
rob+0.015
Neg logit contributions
raid-0.018
reath-0.015
ears-0.015
wn-0.014
 polish-0.014
TokenBut
Token ID1537
Feature activation+6.22e-01

Pos logit contributions
Bad+0.005
 exploded+0.004
 narrative+0.004
rob+0.004
 bomb+0.004
Neg logit contributions
raid-0.004
reath-0.003
ears-0.003
 polish-0.003
she-0.003
Token then
Token ID788
Feature activation+3.15e-01

Pos logit contributions
 she+0.020
 her+0.019
raid+0.018
 She+0.017
 polish+0.017
Neg logit contributions
rob-0.021
 narrative-0.020
storm-0.018
Bad-0.018
 exploded-0.017
Token is
Token ID318
Feature activation-3.68e-01

Pos logit contributions
raid+0.044
reath+0.039
ears+0.036
wn+0.036
erry+0.035
Neg logit contributions
Bad-0.033
 exploded-0.031
 narrative-0.030
rob-0.029
boys-0.029
Token playful
Token ID34264
Feature activation-1.47e-01

Pos logit contributions
Bad+0.016
 narrative+0.015
 exploded+0.015
Did+0.014
rob+0.014
Neg logit contributions
raid-0.009
reath-0.008
ears-0.007
 polish-0.007
wn-0.007
Token and
Token ID290
Feature activation+1.53e+00

Pos logit contributions
Bad+0.005
 exploded+0.005
 narrative+0.005
Did+0.005
rob+0.005
Neg logit contributions
raid-0.005
reath-0.004
ears-0.004
 polish-0.004
 She-0.004
Token laughs
Token ID22051
Feature activation+5.77e-01

Pos logit contributions
raid+0.054
andel+0.048
reath+0.047
ears+0.046
erry+0.044
Neg logit contributions
Bad-0.054
boys-0.047
sed-0.045
Our-0.045
girls-0.044
Token a
Token ID257
Feature activation+1.67e+00

Pos logit contributions
raid+0.019
reath+0.016
ears+0.015
wn+0.014
 polish+0.014
Neg logit contributions
Bad-0.021
 exploded-0.019
 narrative-0.019
Did-0.019
 bomb-0.019
Token lot
Token ID1256
Feature activation+5.76e+00

Pos logit contributions
raid+0.051
reath+0.040
ears+0.040
wn+0.036
annah+0.036
Neg logit contributions
Bad-0.066
 narrative-0.060
 exploded-0.060
 bomb-0.060
Did-0.060
Token.
Token ID13
Feature activation+9.62e-01

Pos logit contributions
raid+0.181
reath+0.151
ears+0.144
 polish+0.136
wn+0.136
Neg logit contributions
Bad-0.213
 exploded-0.196
 narrative-0.196
 bomb-0.191
Did-0.190
Token She
Token ID1375
Feature activation+2.75e+00

Pos logit contributions
raid+0.026
reath+0.023
wn+0.021
 polish+0.019
ears+0.018
Neg logit contributions
Bad-0.040
Did-0.039
 narrative-0.038
Our-0.036
sed-0.035
Token likes
Token ID7832
Feature activation+7.03e-01

Pos logit contributions
raid+0.102
reath+0.086
ears+0.083
wn+0.080
erry+0.078
Neg logit contributions
Bad-0.089
 exploded-0.081
 narrative-0.080
Did-0.078
rob-0.077
Token Sara
Token ID24799
Feature activation+3.26e+00

Pos logit contributions
raid+0.024
reath+0.021
ears+0.019
wn+0.019
annah+0.019
Neg logit contributions
Bad-0.024
 exploded-0.022
Did-0.022
boys-0.022
 bomb-0.022
Token and
Token ID290
Feature activation+2.09e+00

Pos logit contributions
raid+0.131
reath+0.117
ears+0.111
wn+0.108
 polish+0.106
Neg logit contributions
Bad-0.092
 exploded-0.081
 narrative-0.080
Did-0.079
boys-0.078
Token Tim
Token ID5045
Feature activation+1.69e+00

Pos logit contributions
raid+0.028
reath+0.024
ears+0.022
wn+0.021
umble+0.020
Neg logit contributions
Bad-0.034
 exploded-0.030
rob-0.030
Did-0.030
 narrative-0.030
Tokenmy
Token ID1820
Feature activation+2.46e+00

Pos logit contributions
raid+0.060
reath+0.060
annah+0.049
andel+0.048
wn+0.048
Neg logit contributions
Bad-0.051
Did-0.044
boys-0.043
Our-0.043
rob-0.043
Token a
Token ID257
Feature activation+9.73e-01

Pos logit contributions
raid+0.114
reath+0.108
ears+0.094
wn+0.094
annah+0.094
Neg logit contributions
Bad-0.050
Our-0.044
boys-0.040
 exploded-0.040
Did-0.039
Token warm
Token ID5814
Feature activation+3.68e+00

Pos logit contributions
raid+0.037
reath+0.032
annah+0.031
ears+0.029
wn+0.029
Neg logit contributions
Bad-0.027
 exploded-0.027
 bomb-0.026
tr-0.024
Our-0.023
Token,
Token ID11
Feature activation+1.02e+00

Pos logit contributions
raid+0.122
she+0.109
reath+0.108
ears+0.104
wn+0.099
Neg logit contributions
Bad-0.116
 bomb-0.108
storm-0.107
 exploded-0.106
 unison-0.102
Token freshly
Token ID29026
Feature activation+5.76e+00

Pos logit contributions
raid+0.025
reath+0.020
ears+0.019
wn+0.017
she+0.016
Neg logit contributions
Bad-0.045
Did-0.042
 exploded-0.042
 narrative-0.041
 bomb-0.040
Token baked
Token ID22979
Feature activation+1.37e+00

Pos logit contributions
raid+0.225
reath+0.191
ears+0.187
annah+0.177
she+0.177
Neg logit contributions
Bad-0.174
 exploded-0.157
Did-0.155
rob-0.150
 narrative-0.150
Token cookie
Token ID19751
Feature activation-6.03e-01

Pos logit contributions
raid+0.058
reath+0.048
wn+0.045
ears+0.045
inters+0.044
Neg logit contributions
Bad-0.035
rob-0.033
 exploded-0.033
Did-0.031
 bomb-0.031
Token.
Token ID13
Feature activation+4.18e-01

Pos logit contributions
Bad+0.019
 exploded+0.018
rob+0.017
boys+0.017
 bomb+0.017
Neg logit contributions
raid-0.022
reath-0.019
wn-0.017
ears-0.017
 polish-0.016
Token
Token ID198
Feature activation-2.37e-01

Pos logit contributions
raid+0.015
reath+0.013
ears+0.012
wn+0.012
 polish+0.012
Neg logit contributions
Bad-0.014
Did-0.012
 exploded-0.012
 narrative-0.012
rob-0.012
Token
Token ID198
Feature activation+6.50e-02

Pos logit contributions
Bad+0.008
 exploded+0.007
Did+0.007
 narrative+0.007
rob+0.007
Neg logit contributions
raid-0.008
reath-0.007
ears-0.007
 polish-0.006
wn-0.006
Token "
Token ID366
Feature activation+1.51e-01

Pos logit contributions
raid+0.022
reath+0.018
ears+0.017
wn+0.016
 polish+0.016
Neg logit contributions
Bad-0.028
 exploded-0.025
Did-0.025
 narrative-0.025
 bomb-0.024
TokenMy
Token ID3666
Feature activation-9.74e-01

Pos logit contributions
raid+0.005
reath+0.004
ears+0.004
 polish+0.004
she+0.004
Neg logit contributions
Bad-0.005
 exploded-0.005
 narrative-0.005
 bomb-0.004
rob-0.004
Token name
Token ID1438
Feature activation+3.52e+00

Pos logit contributions
Bad+0.047
 exploded+0.044
 bomb+0.043
sed+0.042
 narrative+0.042
Neg logit contributions
raid-0.020
reath-0.015
ears-0.014
she-0.013
wn-0.013
Token is
Token ID318
Feature activation+1.69e-01

Pos logit contributions
raid+0.142
reath+0.123
ears+0.119
wn+0.115
 polish+0.112
Neg logit contributions
Bad-0.102
 exploded-0.092
Did-0.088
 narrative-0.088
rob-0.086
Token L
Token ID406
Feature activation+3.78e+00

Pos logit contributions
raid+0.006
reath+0.005
ears+0.005
 She+0.005
 polish+0.004
Neg logit contributions
Bad-0.006
 narrative-0.006
Did-0.005
 exploded-0.005
rob-0.005
Tokenulu
Token ID15712
Feature activation+5.71e+00

Pos logit contributions
raid+0.115
reath+0.096
ears+0.089
 polish+0.088
wn+0.086
Neg logit contributions
Bad-0.141
 exploded-0.130
 narrative-0.129
rob-0.128
Did-0.127
Token,
Token ID11
Feature activation+2.54e-01

Pos logit contributions
raid+0.198
reath+0.168
ears+0.160
wn+0.155
 polish+0.152
Neg logit contributions
Bad-0.193
 exploded-0.176
Did-0.170
 narrative-0.170
 bomb-0.168
Token and
Token ID290
Feature activation+1.06e+00

Pos logit contributions
raid+0.009
reath+0.007
ears+0.007
wn+0.007
 polish+0.007
Neg logit contributions
Bad-0.009
 exploded-0.008
Did-0.008
 narrative-0.008
 bomb-0.008
Token I
Token ID314
Feature activation+1.06e+00

Pos logit contributions
raid+0.033
reath+0.028
ears+0.026
wn+0.025
 polish+0.024
Neg logit contributions
Bad-0.041
Did-0.037
 exploded-0.037
 narrative-0.036
 bomb-0.035
Token love
Token ID1842
Feature activation+4.04e-01

Pos logit contributions
raid+0.034
reath+0.029
ears+0.028
annah+0.026
wn+0.026
Neg logit contributions
Bad-0.038
 exploded-0.035
Did-0.034
 narrative-0.034
 bomb-0.033
Token cream
Token ID8566
Feature activation+8.48e-01

Pos logit contributions
raid+0.013
reath+0.011
ears+0.010
wn+0.010
annah+0.010
Neg logit contributions
Bad-0.015
 exploded-0.014
Did-0.013
rob-0.013
 bomb-0.013
Token of
Token ID286
Feature activation+1.53e+00

Pos logit contributions
raid+0.122
reath+0.102
ears+0.093
she+0.090
annah+0.089
Neg logit contributions
Bad-0.180
 exploded-0.173
 bomb-0.167
 narrative-0.167
Did-0.167
Token fun
Token ID1257
Feature activation+1.13e+00

Pos logit contributions
raid+0.045
reath+0.036
ears+0.035
she+0.033
annah+0.032
Neg logit contributions
Bad-0.061
 exploded-0.057
 narrative-0.056
 bomb-0.055
Did-0.055
Token and
Token ID290
Feature activation+8.24e-01

Pos logit contributions
raid+0.021
reath+0.015
 work+0.015
 polish+0.015
 care+0.013
Neg logit contributions
Bad-0.057
 narrative-0.052
Did-0.051
 exploded-0.051
ishly-0.051
Token laugh
Token ID6487
Feature activation+6.32e-01

Pos logit contributions
raid+0.023
 care+0.020
 attention+0.019
 polish+0.018
 comfortable+0.018
Neg logit contributions
Bad-0.033
rob-0.032
Did-0.030
storm-0.029
 narrative-0.029
Token a
Token ID257
Feature activation+1.58e+00

Pos logit contributions
raid+0.014
reath+0.011
 She+0.011
 polish+0.010
she+0.010
Neg logit contributions
Bad-0.029
rob-0.027
 narrative-0.027
 exploded-0.026
Did-0.026
Token lot
Token ID1256
Feature activation+5.70e+00

Pos logit contributions
raid+0.029
reath+0.025
 polish+0.020
ears+0.019
 care+0.019
Neg logit contributions
Bad-0.075
 exploded-0.071
 narrative-0.071
Did-0.070
rob-0.070
Token.
Token ID13
Feature activation+2.90e-01

Pos logit contributions
raid+0.179
reath+0.150
ears+0.143
 polish+0.135
wn+0.135
Neg logit contributions
Bad-0.210
 exploded-0.194
 narrative-0.193
 bomb-0.189
Did-0.188
Token
Token ID198
Feature activation-4.99e-02

Pos logit contributions
raid+0.008
 She+0.007
reath+0.006
ears+0.006
she+0.006
Neg logit contributions
Bad-0.012
rob-0.011
 exploded-0.011
 narrative-0.011
 bomb-0.011
Token
Token ID198
Feature activation+2.73e-01

Pos logit contributions
Bad+0.002
 exploded+0.002
 narrative+0.002
Did+0.002
rob+0.001
Neg logit contributions
raid-0.002
reath-0.001
ears-0.001
 polish-0.001
wn-0.001
TokenThey
Token ID2990
Feature activation-4.04e-01

Pos logit contributions
raid+0.008
reath+0.007
she+0.007
ears+0.007
 She+0.007
Neg logit contributions
rob-0.009
Bad-0.009
sed-0.009
 exploded-0.009
 narrative-0.009
Token are
Token ID389
Feature activation-8.04e-01

Pos logit contributions
Bad+0.015
 exploded+0.014
 narrative+0.014
Did+0.014
rob+0.014
Neg logit contributions
raid-0.012
reath-0.010
ears-0.010
 polish-0.009
wn-0.009
Token,
Token ID11
Feature activation-7.60e-01

Pos logit contributions
Bad+0.044
rob+0.041
 narrative+0.040
 exploded+0.040
Did+0.039
Neg logit contributions
raid-0.028
reath-0.021
ears-0.020
 polish-0.020
 She-0.019
Token and
Token ID290
Feature activation-2.54e-01

Pos logit contributions
Bad+0.029
 narrative+0.028
rob+0.027
 exploded+0.027
 bomb+0.026
Neg logit contributions
raid-0.022
 polish-0.017
ears-0.017
 She-0.017
 she-0.017
Token Leo
Token ID19632
Feature activation-1.27e+00

Pos logit contributions
Bad+0.008
rob+0.008
 bomb+0.008
 narrative+0.008
 exploded+0.008
Neg logit contributions
raid-0.009
 she-0.008
 care-0.007
 She-0.007
 her-0.007
Token smiled
Token ID13541
Feature activation+8.00e-02

Pos logit contributions
Bad+0.035
 exploded+0.031
 narrative+0.031
Did+0.031
rob+0.030
Neg logit contributions
raid-0.052
reath-0.045
ears-0.043
 polish-0.042
wn-0.042
Token a
Token ID257
Feature activation+1.23e+00

Pos logit contributions
raid+0.002
 She+0.002
reath+0.002
 polish+0.002
ears+0.002
Neg logit contributions
Bad-0.003
rob-0.003
 exploded-0.003
 narrative-0.003
Did-0.003
Token lot
Token ID1256
Feature activation+5.69e+00

Pos logit contributions
raid+0.027
reath+0.022
 polish+0.019
ears+0.019
wn+0.018
Neg logit contributions
Bad-0.055
 exploded-0.052
 narrative-0.052
rob-0.051
Did-0.051
Token.
Token ID13
Feature activation+4.98e-01

Pos logit contributions
raid+0.178
reath+0.148
ears+0.141
 polish+0.133
wn+0.133
Neg logit contributions
Bad-0.212
 exploded-0.195
 narrative-0.195
Did-0.190
 bomb-0.190
Token He
Token ID679
Feature activation-1.18e-01

Pos logit contributions
raid+0.014
 She+0.012
reath+0.012
ears+0.011
she+0.011
Neg logit contributions
Bad-0.019
 exploded-0.018
rob-0.018
 narrative-0.018
 bomb-0.017
Token was
Token ID373
Feature activation-5.64e-01

Pos logit contributions
Bad+0.004
 bomb+0.004
 narrative+0.004
Did+0.003
rob+0.003
Neg logit contributions
raid-0.004
reath-0.003
ears-0.003
 polish-0.003
 She-0.003
Token very
Token ID845
Feature activation+1.21e+00

Pos logit contributions
Bad+0.021
 exploded+0.019
Did+0.019
 narrative+0.018
Our+0.018
Neg logit contributions
raid-0.019
reath-0.015
ears-0.015
wn-0.014
erry-0.014
Token grateful
Token ID14066
Feature activation+9.56e-01

Pos logit contributions
raid+0.046
reath+0.038
ears+0.037
wn+0.036
andel+0.035
Neg logit contributions
Bad-0.041
 exploded-0.034
Our-0.033
Did-0.032
 no-0.032
Token,
Token ID11
Feature activation+1.67e-01

Pos logit contributions
raid+0.010
ears+0.008
reath+0.008
 She+0.008
 polish+0.008
Neg logit contributions
Bad-0.010
 narrative-0.010
 exploded-0.010
rob-0.010
 bomb-0.010
Token a
Token ID257
Feature activation+3.94e-01

Pos logit contributions
raid+0.006
reath+0.005
ears+0.005
 polish+0.005
 She+0.005
Neg logit contributions
Bad-0.005
 narrative-0.005
 exploded-0.005
Did-0.005
rob-0.005
Token bird
Token ID6512
Feature activation+4.00e-02

Pos logit contributions
raid+0.013
reath+0.010
ears+0.010
wn+0.010
she+0.009
Neg logit contributions
Bad-0.015
 exploded-0.013
Did-0.013
 bomb-0.013
 narrative-0.013
Token named
Token ID3706
Feature activation+1.88e+00

Pos logit contributions
raid+0.002
 She+0.001
ears+0.001
 polish+0.001
erry+0.001
Neg logit contributions
Bad-0.001
 narrative-0.001
 exploded-0.001
 bomb-0.001
rob-0.001
Token L
Token ID406
Feature activation+3.85e+00

Pos logit contributions
raid+0.065
reath+0.054
ears+0.053
 She+0.053
 polish+0.051
Neg logit contributions
Bad-0.063
 narrative-0.060
 exploded-0.058
 bomb-0.056
Did-0.056
Tokenulu
Token ID15712
Feature activation+5.69e+00

Pos logit contributions
raid+0.104
reath+0.081
wn+0.077
 polish+0.076
 attention+0.075
Neg logit contributions
Bad-0.152
 narrative-0.143
rob-0.142
 exploded-0.142
Did-0.141
Token,
Token ID11
Feature activation+4.28e-01

Pos logit contributions
raid+0.160
reath+0.128
ears+0.124
 polish+0.117
 She+0.114
Neg logit contributions
Bad-0.232
 narrative-0.215
 exploded-0.214
Did-0.209
rob-0.209
Token who
Token ID508
Feature activation-5.69e-01

Pos logit contributions
raid+0.016
reath+0.014
ears+0.013
 polish+0.012
wn+0.012
Neg logit contributions
Bad-0.014
 exploded-0.012
 narrative-0.012
Did-0.012
rob-0.012
Token would
Token ID561
Feature activation-4.86e-01

Pos logit contributions
Bad+0.012
 exploded+0.010
Did+0.010
rob+0.010
boys+0.009
Neg logit contributions
raid-0.028
reath-0.025
ears-0.024
wn-0.024
annah-0.023
Token visit
Token ID3187
Feature activation+1.03e+00

Pos logit contributions
Bad+0.017
 exploded+0.015
Did+0.015
 narrative+0.015
boys+0.014
Neg logit contributions
raid-0.017
ears-0.014
reath-0.014
wn-0.013
annah-0.013
Token her
Token ID607
Feature activation+1.41e+00

Pos logit contributions
raid+0.024
reath+0.019
ears+0.018
wn+0.017
 polish+0.016
Neg logit contributions
Bad-0.046
 exploded-0.042
Did-0.042
 narrative-0.042
rob-0.042
Token funny
Token ID8258
Feature activation-7.62e-01

Pos logit contributions
raid+0.023
reath+0.020
 polish+0.019
ears+0.018
she+0.018
Neg logit contributions
Bad-0.023
 narrative-0.021
 exploded-0.020
Did-0.020
rob-0.020
Token shows
Token ID2523
Feature activation-4.34e-02

Pos logit contributions
Bad+0.023
 exploded+0.020
 narrative+0.020
Did+0.020
rob+0.019
Neg logit contributions
raid-0.030
reath-0.026
ears-0.025
wn-0.024
 polish-0.024
Token and
Token ID290
Feature activation+6.05e-02

Pos logit contributions
Bad+0.002
 narrative+0.002
 exploded+0.002
Did+0.001
rob+0.001
Neg logit contributions
raid-0.001
reath-0.001
ears-0.001
 polish-0.001
she-0.001
Token laugh
Token ID6487
Feature activation+3.67e-01

Pos logit contributions
raid+0.002
reath+0.001
ears+0.001
 polish+0.001
wn+0.001
Neg logit contributions
Bad-0.002
 exploded-0.002
 narrative-0.002
Did-0.002
rob-0.002
Token a
Token ID257
Feature activation+1.16e+00

Pos logit contributions
raid+0.010
reath+0.008
ears+0.007
 She+0.007
 polish+0.007
Neg logit contributions
Bad-0.015
 narrative-0.014
 exploded-0.014
rob-0.014
Did-0.014
Token lot
Token ID1256
Feature activation+5.68e+00

Pos logit contributions
raid+0.040
ears+0.031
reath+0.031
annah+0.030
wn+0.029
Neg logit contributions
Bad-0.043
Did-0.039
 exploded-0.039
 narrative-0.038
 bomb-0.038
Token.
Token ID13
Feature activation-8.08e-02

Pos logit contributions
raid+0.198
reath+0.169
ears+0.164
wn+0.158
 polish+0.154
Neg logit contributions
Bad-0.183
 narrative-0.170
 exploded-0.169
 bomb-0.167
Did-0.161
Token Sometimes
Token ID8975
Feature activation+1.33e-02

Pos logit contributions
Bad+0.003
 exploded+0.003
 narrative+0.003
 bomb+0.003
rob+0.003
Neg logit contributions
raid-0.002
ears-0.002
reath-0.002
 She-0.002
 polish-0.002
Token Tom
Token ID4186
Feature activation-1.15e+00

Pos logit contributions
raid+0.000
 polish+0.000
 She+0.000
ears+0.000
 she+0.000
Neg logit contributions
Bad-0.000
 narrative-0.000
Did-0.000
 exploded-0.000
rob-0.000
Token lets
Token ID8781
Feature activation+2.25e+00

Pos logit contributions
Bad+0.037
 exploded+0.034
 narrative+0.033
Did+0.033
rob+0.032
Neg logit contributions
raid-0.042
reath-0.036
ears-0.034
wn-0.033
erry-0.032
Token Lily
Token ID20037
Feature activation+1.17e+00

Pos logit contributions
raid+0.076
reath+0.065
ears+0.063
wn+0.059
annah+0.057
Neg logit contributions
Bad-0.078
 exploded-0.072
 narrative-0.069
 bomb-0.069
boys-0.068
Token of
Token ID286
Feature activation+1.07e+00

Pos logit contributions
raid+0.124
reath+0.107
annah+0.095
 polish+0.093
wn+0.092
Neg logit contributions
Bad-0.158
 exploded-0.153
 narrative-0.148
 bomb-0.146
rob-0.146
Token fun
Token ID1257
Feature activation+9.59e-01

Pos logit contributions
raid+0.033
reath+0.026
ears+0.025
she+0.024
umble+0.024
Neg logit contributions
Bad-0.042
 narrative-0.039
 exploded-0.038
rob-0.038
Did-0.037
Token and
Token ID290
Feature activation+4.38e-01

Pos logit contributions
raid+0.024
ears+0.019
reath+0.018
 she+0.017
 polish+0.017
Neg logit contributions
Bad-0.043
 exploded-0.039
Did-0.039
 narrative-0.039
 bomb-0.037
Token laughed
Token ID13818
Feature activation+7.27e-02

Pos logit contributions
raid+0.015
 care+0.012
 attention+0.012
 comfortable+0.012
 polish+0.012
Neg logit contributions
Bad-0.015
rob-0.014
 narrative-0.014
Did-0.014
 bomb-0.014
Token a
Token ID257
Feature activation+1.20e+00

Pos logit contributions
raid+0.002
reath+0.002
 She+0.002
ears+0.001
 polish+0.001
Neg logit contributions
Bad-0.003
rob-0.003
 narrative-0.003
 exploded-0.003
Did-0.003
Token lot
Token ID1256
Feature activation+5.63e+00

Pos logit contributions
raid+0.027
reath+0.021
ears+0.019
 polish+0.019
wn+0.018
Neg logit contributions
Bad-0.054
 exploded-0.051
 narrative-0.051
Did-0.050
rob-0.050
Token.
Token ID13
Feature activation+8.08e-02

Pos logit contributions
raid+0.186
reath+0.159
ears+0.150
wn+0.145
 polish+0.144
Neg logit contributions
Bad-0.194
 exploded-0.180
 narrative-0.179
 bomb-0.176
rob-0.172
Token
Token ID198
Feature activation-2.37e-01

Pos logit contributions
raid+0.002
 She+0.002
ears+0.002
reath+0.002
she+0.002
Neg logit contributions
Bad-0.003
rob-0.003
 exploded-0.003
 narrative-0.003
 bomb-0.003
Token
Token ID198
Feature activation+6.31e-02

Pos logit contributions
Bad+0.009
 narrative+0.008
 exploded+0.008
Did+0.008
rob+0.008
Neg logit contributions
raid-0.008
reath-0.006
ears-0.006
 polish-0.006
she-0.006
Token"
Token ID1
Feature activation+4.14e-01

Pos logit contributions
raid+0.002
reath+0.002
she+0.002
ears+0.002
 She+0.002
Neg logit contributions
Bad-0.002
rob-0.002
 exploded-0.002
 narrative-0.002
sed-0.002
TokenAnna
Token ID31160
Feature activation+4.49e-01

Pos logit contributions
raid+0.011
she+0.010
 She+0.010
reath+0.010
wn+0.010
Neg logit contributions
sed-0.014
 bomb-0.014
ishly-0.014
 attacking-0.014
 exploded-0.014
Token are
Token ID389
Feature activation-9.44e-01

Pos logit contributions
Bad+0.010
 exploded+0.009
 narrative+0.009
Did+0.009
rob+0.009
Neg logit contributions
raid-0.008
reath-0.007
ears-0.007
wn-0.006
 polish-0.006
Token happy
Token ID3772
Feature activation+1.15e-01

Pos logit contributions
Bad+0.037
 exploded+0.034
Did+0.033
 narrative+0.033
 bomb+0.032
Neg logit contributions
raid-0.029
reath-0.024
ears-0.023
wn-0.021
annah-0.021
Token and
Token ID290
Feature activation+1.04e+00

Pos logit contributions
raid+0.003
ears+0.002
 She+0.002
 she+0.002
 polish+0.002
Neg logit contributions
Bad-0.005
rob-0.005
 narrative-0.005
 exploded-0.005
 bomb-0.005
Token laugh
Token ID6487
Feature activation+5.47e-01

Pos logit contributions
raid+0.030
reath+0.024
ears+0.024
wn+0.021
erry+0.021
Neg logit contributions
Bad-0.043
 exploded-0.040
 narrative-0.038
Did-0.038
boys-0.037
Token a
Token ID257
Feature activation+1.27e+00

Pos logit contributions
raid+0.011
 She+0.010
reath+0.009
 polish+0.008
she+0.008
Neg logit contributions
Bad-0.025
rob-0.024
 narrative-0.023
 exploded-0.023
 bomb-0.023
Token lot
Token ID1256
Feature activation+5.63e+00

Pos logit contributions
raid+0.026
reath+0.022
ears+0.018
 polish+0.018
 care+0.017
Neg logit contributions
Bad-0.058
 narrative-0.055
 exploded-0.055
Did-0.055
rob-0.054
Token.
Token ID13
Feature activation+2.02e-01

Pos logit contributions
raid+0.159
reath+0.128
ears+0.121
 polish+0.114
wn+0.112
Neg logit contributions
Bad-0.230
 exploded-0.211
Did-0.210
 narrative-0.210
rob-0.206
Token
Token ID198
Feature activation-1.52e-01

Pos logit contributions
raid+0.005
 She+0.004
reath+0.004
she+0.004
ears+0.004
Neg logit contributions
Bad-0.008
 exploded-0.008
rob-0.008
 bomb-0.008
 narrative-0.008
Token
Token ID198
Feature activation+2.00e-01

Pos logit contributions
Bad+0.005
 exploded+0.005
 narrative+0.005
rob+0.005
Did+0.005
Neg logit contributions
raid-0.005
reath-0.004
ears-0.004
 polish-0.004
she-0.004
TokenOne
Token ID3198
Feature activation+4.93e-01

Pos logit contributions
raid+0.007
reath+0.006
ears+0.005
she+0.005
 She+0.005
Neg logit contributions
Bad-0.006
 exploded-0.006
rob-0.006
sed-0.006
 narrative-0.006
Token day
Token ID1110
Feature activation-4.91e-01

Pos logit contributions
raid+0.016
reath+0.013
ears+0.013
she+0.012
wn+0.012
Neg logit contributions
Bad-0.018
 exploded-0.017
 narrative-0.017
 bomb-0.016
Did-0.016
Token have
Token ID423
Feature activation-8.91e-01

Pos logit contributions
Bad+0.018
 exploded+0.016
 narrative+0.016
Did+0.015
boys+0.015
Neg logit contributions
raid-0.017
reath-0.015
ears-0.014
erry-0.013
wn-0.013
Token fun
Token ID1257
Feature activation+4.44e-01

Pos logit contributions
Bad+0.034
 narrative+0.031
 exploded+0.031
Did+0.030
rob+0.030
Neg logit contributions
raid-0.027
reath-0.023
ears-0.022
 polish-0.021
wn-0.021
Token and
Token ID290
Feature activation+3.06e-01

Pos logit contributions
raid+0.012
reath+0.009
ears+0.009
 polish+0.009
 She+0.008
Neg logit contributions
Bad-0.018
 exploded-0.017
 narrative-0.017
storm-0.016
 bomb-0.016
Token laugh
Token ID6487
Feature activation+2.10e-01

Pos logit contributions
raid+0.009
reath+0.007
ears+0.007
 polish+0.007
wn+0.007
Neg logit contributions
Bad-0.012
 exploded-0.011
 narrative-0.011
Did-0.011
rob-0.011
Token a
Token ID257
Feature activation+1.21e+00

Pos logit contributions
raid+0.004
 She+0.004
reath+0.003
 comfortable+0.003
 her+0.003
Neg logit contributions
Bad-0.010
rob-0.009
 narrative-0.009
 exploded-0.009
 bomb-0.009
Token lot
Token ID1256
Feature activation+5.62e+00

Pos logit contributions
raid+0.030
reath+0.024
ears+0.022
 polish+0.021
wn+0.020
Neg logit contributions
Bad-0.053
 exploded-0.049
 narrative-0.049
Did-0.048
rob-0.048
Token.
Token ID13
Feature activation-3.46e-01

Pos logit contributions
raid+0.174
reath+0.145
ears+0.138
 polish+0.131
wn+0.130
Neg logit contributions
Bad-0.210
 exploded-0.193
 narrative-0.192
Did-0.188
 bomb-0.188
Token
Token ID198
Feature activation-6.41e-01

Pos logit contributions
Bad+0.016
rob+0.016
 exploded+0.016
 bomb+0.015
 narrative+0.015
Neg logit contributions
raid-0.007
 She-0.006
ears-0.005
reath-0.005
 try-0.005
Token
Token ID198
Feature activation-2.54e-01

Pos logit contributions
Bad+0.026
 narrative+0.024
 exploded+0.023
 bomb+0.023
rob+0.023
Neg logit contributions
raid-0.018
reath-0.015
ears-0.014
 She-0.014
she-0.014
TokenOne
Token ID3198
Feature activation+4.25e-01

Pos logit contributions
sed+0.010
 exploded+0.010
rob+0.010
 narrative+0.010
Bad+0.010
Neg logit contributions
raid-0.006
reath-0.005
ears-0.005
 She-0.005
 polish-0.005
Token day
Token ID1110
Feature activation-3.97e-01

Pos logit contributions
raid+0.015
reath+0.013
ears+0.012
she+0.012
wn+0.012
Neg logit contributions
Bad-0.014
 narrative-0.013
 exploded-0.013
 bomb-0.013
Did-0.012
Token and
Token ID290
Feature activation+7.47e-01

Pos logit contributions
raid+0.005
reath+0.004
ears+0.004
 polish+0.004
 She+0.004
Neg logit contributions
Bad-0.005
 narrative-0.005
 exploded-0.005
rob-0.005
Did-0.005
Token he
Token ID339
Feature activation-1.46e+00

Pos logit contributions
raid+0.024
 polish+0.020
reath+0.019
ears+0.019
 She+0.019
Neg logit contributions
Bad-0.026
 narrative-0.025
rob-0.024
 exploded-0.024
Did-0.023
Token always
Token ID1464
Feature activation+2.15e-01

Pos logit contributions
Bad+0.046
 narrative+0.043
rob+0.041
Did+0.041
 bomb+0.041
Neg logit contributions
raid-0.053
reath-0.044
 polish-0.044
ears-0.043
 She-0.042
Token kept
Token ID4030
Feature activation+1.14e+00

Pos logit contributions
raid+0.009
reath+0.008
ears+0.007
wn+0.007
 polish+0.007
Neg logit contributions
Bad-0.006
 exploded-0.005
Did-0.005
 narrative-0.005
rob-0.005
Token an
Token ID281
Feature activation-3.44e-01

Pos logit contributions
raid+0.044
reath+0.038
ears+0.037
erry+0.034
annah+0.034
Neg logit contributions
Bad-0.035
 exploded-0.031
Did-0.031
 narrative-0.030
 bomb-0.030
Token eye
Token ID4151
Feature activation+5.61e+00

Pos logit contributions
Bad+0.013
 exploded+0.012
 narrative+0.012
 bomb+0.012
Did+0.011
Neg logit contributions
raid-0.010
reath-0.008
ears-0.008
she-0.008
wn-0.008
Token out
Token ID503
Feature activation+2.33e+00

Pos logit contributions
raid+0.201
reath+0.172
ears+0.167
wn+0.155
 polish+0.154
Neg logit contributions
Bad-0.182
 exploded-0.166
 narrative-0.163
Did-0.162
 bomb-0.161
Token for
Token ID329
Feature activation-7.56e-01

Pos logit contributions
raid+0.072
reath+0.060
ears+0.058
wn+0.053
 polish+0.053
Neg logit contributions
Bad-0.089
 exploded-0.081
 narrative-0.080
Did-0.080
 bomb-0.079
Token any
Token ID597
Feature activation-3.58e-01

Pos logit contributions
Bad+0.028
 narrative+0.026
 exploded+0.026
Did+0.025
rob+0.025
Neg logit contributions
raid-0.023
reath-0.019
 polish-0.018
ears-0.018
wn-0.018
Token junk
Token ID18556
Feature activation+7.89e-02

Pos logit contributions
Bad+0.012
 exploded+0.011
 bomb+0.011
 narrative+0.011
Did+0.011
Neg logit contributions
raid-0.012
reath-0.010
ears-0.010
she-0.010
annah-0.010
Token.
Token ID13
Feature activation-3.51e-01

Pos logit contributions
raid+0.002
reath+0.002
ears+0.002
 polish+0.002
wn+0.002
Neg logit contributions
Bad-0.003
 narrative-0.003
 exploded-0.003
Did-0.003
rob-0.003
Token a
Token ID257
Feature activation+1.38e-01

Pos logit contributions
Bad+0.021
 narrative+0.020
 exploded+0.020
rob+0.019
 bomb+0.019
Neg logit contributions
raid-0.016
 She-0.014
reath-0.014
 polish-0.013
ears-0.013
Token little
Token ID1310
Feature activation+1.34e+00

Pos logit contributions
raid+0.004
reath+0.003
ears+0.003
wn+0.003
she+0.003
Neg logit contributions
Bad-0.005
 exploded-0.005
Did-0.005
 narrative-0.005
 bomb-0.005
Token bird
Token ID6512
Feature activation-1.52e-01

Pos logit contributions
raid+0.045
reath+0.040
wn+0.038
ears+0.036
she+0.036
Neg logit contributions
Bad-0.047
 bomb-0.042
 exploded-0.041
 narrative-0.040
rob-0.040
Token called
Token ID1444
Feature activation+3.21e+00

Pos logit contributions
Bad+0.005
 narrative+0.004
 exploded+0.004
 bomb+0.004
rob+0.004
Neg logit contributions
raid-0.006
reath-0.005
ears-0.005
 polish-0.005
 She-0.005
Token L
Token ID406
Feature activation+4.25e+00

Pos logit contributions
raid+0.122
reath+0.104
ears+0.101
 polish+0.097
 She+0.095
Neg logit contributions
Bad-0.098
 narrative-0.090
 exploded-0.088
Did-0.087
rob-0.085
Tokenizz
Token ID6457
Feature activation+5.61e+00

Pos logit contributions
raid+0.123
reath+0.099
 polish+0.091
ears+0.089
 attention+0.089
Neg logit contributions
Bad-0.165
 exploded-0.155
 narrative-0.154
Did-0.153
rob-0.151
Tokenie
Token ID494
Feature activation+3.88e+00

Pos logit contributions
raid+0.100
reath+0.069
ears+0.063
 polish+0.055
erry+0.051
Neg logit contributions
Bad-0.289
 narrative-0.271
 exploded-0.270
Did-0.268
 bomb-0.266
Token.
Token ID13
Feature activation+1.67e-01

Pos logit contributions
raid+0.117
reath+0.097
ears+0.092
 polish+0.087
wn+0.086
Neg logit contributions
Bad-0.149
 exploded-0.137
 narrative-0.137
Did-0.135
rob-0.133
Token She
Token ID1375
Feature activation+2.52e+00

Pos logit contributions
reath+0.006
raid+0.006
annah+0.005
old+0.005
 attention+0.005
Neg logit contributions
Did-0.004
Bad-0.004
 no-0.004
 sw-0.004
 narrative-0.004
Token was
Token ID373
Feature activation-3.69e-01

Pos logit contributions
raid+0.101
reath+0.089
ears+0.085
 polish+0.084
 She+0.081
Neg logit contributions
Bad-0.070
 narrative-0.064
 exploded-0.061
Did-0.060
 bomb-0.060
Token sitting
Token ID5586
Feature activation-1.93e+00

Pos logit contributions
Bad+0.012
 exploded+0.011
Did+0.010
boys+0.010
Our+0.010
Neg logit contributions
raid-0.014
reath-0.011
ears-0.011
annah-0.011
wn-0.010
Token of
Token ID286
Feature activation+8.36e-01

Pos logit contributions
raid+0.117
reath+0.100
annah+0.090
 polish+0.087
wn+0.087
Neg logit contributions
Bad-0.164
 exploded-0.157
 narrative-0.153
 bomb-0.151
Did-0.151
Token fun
Token ID1257
Feature activation+8.19e-01

Pos logit contributions
raid+0.024
reath+0.020
ears+0.018
wn+0.017
she+0.017
Neg logit contributions
Bad-0.034
 narrative-0.031
 exploded-0.031
rob-0.030
Did-0.030
Token and
Token ID290
Feature activation+3.96e-01

Pos logit contributions
raid+0.019
ears+0.014
reath+0.013
 she+0.013
 polish+0.012
Neg logit contributions
Bad-0.039
 exploded-0.036
Did-0.035
 narrative-0.035
 bomb-0.034
Token laughed
Token ID13818
Feature activation+1.33e-01

Pos logit contributions
raid+0.012
 care+0.010
 attention+0.010
 comfortable+0.010
ears+0.010
Neg logit contributions
Bad-0.015
rob-0.014
 narrative-0.013
Did-0.013
 bomb-0.013
Token a
Token ID257
Feature activation+1.18e+00

Pos logit contributions
raid+0.003
reath+0.003
 She+0.003
ears+0.003
 polish+0.003
Neg logit contributions
Bad-0.006
rob-0.005
 narrative-0.005
 exploded-0.005
Did-0.005
Token lot
Token ID1256
Feature activation+5.61e+00

Pos logit contributions
raid+0.024
reath+0.020
ears+0.017
 polish+0.017
 care+0.015
Neg logit contributions
Bad-0.054
 narrative-0.052
 exploded-0.052
Did-0.051
rob-0.051
Token.
Token ID13
Feature activation+1.77e-02

Pos logit contributions
raid+0.176
reath+0.148
ears+0.140
wn+0.133
 polish+0.133
Neg logit contributions
Bad-0.207
 exploded-0.191
 narrative-0.190
 bomb-0.186
Did-0.185
Token
Token ID198
Feature activation-3.35e-01

Pos logit contributions
raid+0.000
 She+0.000
ears+0.000
reath+0.000
she+0.000
Neg logit contributions
Bad-0.001
 exploded-0.001
rob-0.001
 bomb-0.001
 narrative-0.001
Token
Token ID198
Feature activation-3.12e-02

Pos logit contributions
Bad+0.012
 narrative+0.011
 exploded+0.011
rob+0.011
 bomb+0.011
Neg logit contributions
raid-0.010
reath-0.009
ears-0.009
she-0.008
 polish-0.008
TokenBut
Token ID1537
Feature activation+5.66e-01

Pos logit contributions
Bad+0.001
 exploded+0.001
rob+0.001
 narrative+0.001
 bomb+0.001
Neg logit contributions
raid-0.001
reath-0.001
ears-0.001
she-0.001
 She-0.001
Token then
Token ID788
Feature activation+8.00e-02

Pos logit contributions
 she+0.018
 her+0.017
raid+0.014
 She+0.013
 as+0.013
Neg logit contributions
rob-0.022
 narrative-0.021
 unison-0.019
Did-0.018
Bad-0.018
Token gigg
Token ID30442
Feature activation-6.42e-01

Pos logit contributions
Bad+0.068
 exploded+0.060
 narrative+0.060
Did+0.059
 bomb+0.057
Neg logit contributions
raid-0.104
reath-0.090
ears-0.088
 polish-0.085
wn-0.084
Tokenled
Token ID992
Feature activation+1.47e+00

Pos logit contributions
Bad+0.017
 narrative+0.014
 exploded+0.014
rob+0.014
Did+0.013
Neg logit contributions
raid-0.027
reath-0.024
wn-0.022
ears-0.022
 attention-0.022
Token and
Token ID290
Feature activation+1.29e+00

Pos logit contributions
raid+0.055
reath+0.048
ears+0.045
wn+0.043
 polish+0.042
Neg logit contributions
Bad-0.047
 exploded-0.042
Did-0.042
 narrative-0.041
 bomb-0.040
Token smiled
Token ID13541
Feature activation+4.29e-01

Pos logit contributions
raid+0.052
reath+0.045
ears+0.044
wn+0.042
she+0.041
Neg logit contributions
Bad-0.037
 exploded-0.034
Did-0.033
rob-0.032
 narrative-0.032
Token a
Token ID257
Feature activation+1.68e+00

Pos logit contributions
raid+0.015
reath+0.013
ears+0.012
wn+0.012
annah+0.011
Neg logit contributions
Bad-0.015
 exploded-0.013
Did-0.013
 narrative-0.013
 bomb-0.013
Token lot
Token ID1256
Feature activation+5.61e+00

Pos logit contributions
raid+0.053
reath+0.042
ears+0.042
wn+0.039
she+0.039
Neg logit contributions
Bad-0.065
 exploded-0.059
Did-0.059
 bomb-0.058
 unison-0.057
Token.
Token ID13
Feature activation+3.20e-01

Pos logit contributions
raid+0.207
reath+0.181
ears+0.176
wn+0.169
she+0.165
Neg logit contributions
Bad-0.164
 exploded-0.156
 bomb-0.155
 narrative-0.153
 unison-0.143
Token One
Token ID1881
Feature activation+8.47e-01

Pos logit contributions
raid+0.013
reath+0.012
wn+0.012
up+0.011
ingle+0.011
Neg logit contributions
Did-0.008
Bad-0.008
Our-0.007
rob-0.007
 lions-0.007
Token day
Token ID1110
Feature activation-7.66e-01

Pos logit contributions
raid+0.028
reath+0.024
ears+0.023
she+0.022
wn+0.021
Neg logit contributions
Bad-0.030
 exploded-0.028
 narrative-0.027
 bomb-0.027
Did-0.027
Token she
Token ID673
Feature activation+6.18e-01

Pos logit contributions
Bad+0.027
 exploded+0.025
 narrative+0.025
Did+0.024
rob+0.024
Neg logit contributions
raid-0.026
reath-0.022
ears-0.021
 polish-0.020
wn-0.020
Token asked
Token ID1965
Feature activation+1.26e+00

Pos logit contributions
raid+0.019
 polish+0.017
ears+0.016
up+0.015
 She+0.015
Neg logit contributions
Bad-0.022
 narrative-0.021
 bomb-0.020
rob-0.020
 unison-0.020
Token,
Token ID11
Feature activation+2.60e-02

Pos logit contributions
raid+0.002
reath+0.002
ears+0.002
 polish+0.002
 She+0.002
Neg logit contributions
Bad-0.002
 narrative-0.002
 exploded-0.002
 bomb-0.002
rob-0.002
Token a
Token ID257
Feature activation+2.13e-01

Pos logit contributions
raid+0.001
reath+0.001
ears+0.001
 polish+0.001
wn+0.001
Neg logit contributions
Bad-0.001
 narrative-0.001
 exploded-0.001
Did-0.001
rob-0.001
Token bird
Token ID6512
Feature activation-2.42e-01

Pos logit contributions
raid+0.008
reath+0.006
ears+0.006
wn+0.006
she+0.006
Neg logit contributions
Bad-0.007
 bomb-0.007
 exploded-0.007
Did-0.007
 narrative-0.006
Token named
Token ID3706
Feature activation+1.70e+00

Pos logit contributions
Bad+0.006
 narrative+0.005
 exploded+0.005
 bomb+0.005
Did+0.005
Neg logit contributions
raid-0.011
reath-0.009
ears-0.009
 polish-0.009
 She-0.009
Token L
Token ID406
Feature activation+3.59e+00

Pos logit contributions
raid+0.062
reath+0.053
ears+0.051
 polish+0.049
wn+0.048
Neg logit contributions
Bad-0.054
 exploded-0.049
 narrative-0.049
Did-0.048
 bomb-0.047
Tokenulu
Token ID15712
Feature activation+5.60e+00

Pos logit contributions
raid+0.117
reath+0.093
wn+0.092
 polish+0.088
 attention+0.087
Neg logit contributions
Bad-0.125
rob-0.120
 narrative-0.117
 exploded-0.113
Did-0.112
Token.
Token ID13
Feature activation-1.22e-02

Pos logit contributions
raid+0.178
reath+0.149
ears+0.141
wn+0.136
 polish+0.134
Neg logit contributions
Bad-0.206
 exploded-0.188
 narrative-0.186
Did-0.186
rob-0.182
Token L
Token ID406
Feature activation+2.29e+00

Pos logit contributions
Bad+0.000
Did+0.000
girls+0.000
rob+0.000
 narrative+0.000
Neg logit contributions
raid-0.001
reath-0.000
wn-0.000
annah-0.000
 polish-0.000
Tokenulu
Token ID15712
Feature activation+3.91e+00

Pos logit contributions
raid+0.070
reath+0.054
wn+0.053
 polish+0.051
ears+0.049
Neg logit contributions
Bad-0.086
 narrative-0.080
rob-0.080
 exploded-0.079
Did-0.078
Token liked
Token ID8288
Feature activation+3.90e-01

Pos logit contributions
raid+0.151
reath+0.131
ears+0.126
 polish+0.122
wn+0.119
Neg logit contributions
Bad-0.116
 narrative-0.104
 exploded-0.103
Did-0.102
 bomb-0.100
Token to
Token ID284
Feature activation+1.68e+00

Pos logit contributions
raid+0.013
reath+0.011
wn+0.011
annah+0.011
ingle+0.010
Neg logit contributions
Bad-0.013
 lions-0.012
Did-0.012
 guns-0.012
 attacking-0.012
Token dog
Token ID3290
Feature activation-3.03e+00

Pos logit contributions
rob+0.006
Bad+0.006
Did+0.005
girls+0.005
 unison+0.005
Neg logit contributions
 old-0.005
raid-0.005
 polish-0.005
reath-0.004
 attention-0.004
Token.
Token ID13
Feature activation-2.23e-01

Pos logit contributions
 narrative+0.117
rob+0.114
Bad+0.113
 bomb+0.103
Did+0.101
Neg logit contributions
raid-0.089
 She-0.071
ears-0.070
 care-0.067
 try-0.066
Token They
Token ID1119
Feature activation-6.29e-01

Pos logit contributions
rob+0.010
 narrative+0.010
Bad+0.009
 exploded+0.009
boys+0.009
Neg logit contributions
 She-0.005
raid-0.005
 old-0.003
she-0.003
 welcome-0.003
Token left
Token ID1364
Feature activation-1.09e+00

Pos logit contributions
rob+0.022
 narrative+0.021
 bomb+0.020
Bad+0.020
storm+0.020
Neg logit contributions
raid-0.019
 care-0.018
 polish-0.017
 try-0.017
 She-0.017
Token their
Token ID511
Feature activation-3.19e+00

Pos logit contributions
rob+0.042
 narrative+0.042
Bad+0.042
 exploded+0.040
Did+0.040
Neg logit contributions
raid-0.028
 She-0.024
 attention-0.023
 old-0.023
 polish-0.023
Token missile
Token ID10105
Feature activation-6.87e+00

Pos logit contributions
rob+0.135
Bad+0.130
Did+0.129
Run+0.120
storm+0.118
Neg logit contributions
raid-0.083
 old-0.071
ears-0.069
 polish-0.068
 attention-0.066
Token behind
Token ID2157
Feature activation-2.80e+00

Pos logit contributions
Bad+0.281
rob+0.271
 narrative+0.266
Did+0.259
 unison+0.246
Neg logit contributions
raid-0.194
ears-0.154
 polish-0.148
wn-0.139
 old-0.137
Token and
Token ID290
Feature activation-1.46e+00

Pos logit contributions
 narrative+0.134
rob+0.130
Bad+0.129
Did+0.120
storm+0.118
Neg logit contributions
raid-0.048
 She-0.046
 her-0.044
 care-0.040
 old-0.039
Token went
Token ID1816
Feature activation-1.24e-01

Pos logit contributions
rob+0.060
 narrative+0.057
Bad+0.055
 unison+0.052
Did+0.052
Neg logit contributions
raid-0.036
 care-0.035
 try-0.035
 polish-0.034
 comfortable-0.033
Token back
Token ID736
Feature activation-1.21e+00

Pos logit contributions
Bad+0.005
 exploded+0.005
 narrative+0.005
Did+0.005
 bomb+0.005
Neg logit contributions
raid-0.003
reath-0.003
ears-0.003
 polish-0.002
wn-0.002
Token to
Token ID284
Feature activation-1.45e+00

Pos logit contributions
Bad+0.058
 narrative+0.056
 exploded+0.054
Did+0.054
rob+0.053
Neg logit contributions
raid-0.026
ears-0.018
reath-0.017
 polish-0.017
 She-0.016
Token safe
Token ID3338
Feature activation+3.45e-01

Pos logit contributions
Bad+0.041
 exploded+0.039
 narrative+0.037
 bomb+0.037
Did+0.037
Neg logit contributions
raid-0.031
reath-0.026
ears-0.024
annah-0.023
wn-0.023
Token again
Token ID757
Feature activation-3.17e+00

Pos logit contributions
raid+0.009
 attention+0.007
 She+0.007
 polish+0.007
 care+0.007
Neg logit contributions
Bad-0.015
Did-0.013
rob-0.013
 narrative-0.013
 exploded-0.013
Token.
Token ID13
Feature activation-5.00e-01

Pos logit contributions
Bad+0.153
rob+0.142
 narrative+0.140
Did+0.140
 exploded+0.139
Neg logit contributions
raid-0.068
 care-0.046
reath-0.046
 polish-0.045
 She-0.043
Token The
Token ID383
Feature activation-8.84e-01

Pos logit contributions
Bad+0.018
 exploded+0.016
 narrative+0.016
Did+0.016
 bomb+0.016
Neg logit contributions
raid-0.016
reath-0.014
ears-0.013
 polish-0.012
wn-0.012
Token town
Token ID3240
Feature activation-1.54e+00

Pos logit contributions
rob+0.033
Bad+0.033
Did+0.032
 exploded+0.031
Our+0.031
Neg logit contributions
raid-0.022
 polish-0.020
reath-0.020
 old-0.019
 care-0.019
Tokenspe
Token ID4125
Feature activation-6.11e+00

Pos logit contributions
Bad+0.048
rob+0.045
 narrative+0.043
Did+0.043
 bomb+0.039
Neg logit contributions
raid-0.057
 polish-0.047
up-0.045
 care-0.045
 old-0.045
Tokenople
Token ID643
Feature activation-1.88e+00

Pos logit contributions
Did+0.189
storm+0.186
 bomb+0.183
Bad+0.179
girls+0.174
Neg logit contributions
raid-0.224
up-0.164
 care-0.159
annah-0.157
wn-0.157
Token thanked
Token ID26280
Feature activation+7.04e-01

Pos logit contributions
Bad+0.057
 narrative+0.052
rob+0.051
 bomb+0.049
Did+0.047
Neg logit contributions
raid-0.072
 polish-0.062
 care-0.059
reath-0.059
ears-0.057
Token the
Token ID262
Feature activation+2.04e+00

Pos logit contributions
raid+0.019
reath+0.016
 polish+0.015
 She+0.015
she+0.014
Neg logit contributions
Bad-0.028
 exploded-0.026
 narrative-0.026
Did-0.026
rob-0.026
Token bear
Token ID6842
Feature activation+3.30e-01

Pos logit contributions
raid+0.069
reath+0.059
ears+0.055
 polish+0.054
wn+0.053
Neg logit contributions
Bad-0.070
 exploded-0.065
 narrative-0.064
Did-0.063
rob-0.063
Token many
Token ID867
Feature activation-3.22e-02

Pos logit contributions
raid+0.011
reath+0.009
ears+0.009
 polish+0.009
wn+0.009
Neg logit contributions
Bad-0.011
 exploded-0.010
 narrative-0.010
Did-0.010
 bomb-0.010
TokenUh
Token ID34653
Feature activation-4.12e+00

Pos logit contributions
rob+0.016
girls+0.016
sed+0.016
boys+0.016
ishly+0.015
Neg logit contributions
raid-0.015
she-0.014
 polish-0.014
 She-0.012
 she-0.012
Token-
Token ID12
Feature activation+1.64e+00

Pos logit contributions
Bad+0.183
 narrative+0.179
rob+0.175
Did+0.173
 exploded+0.173
Neg logit contributions
raid-0.096
reath-0.070
ears-0.065
 polish-0.064
 care-0.063
Tokenoh
Token ID1219
Feature activation+3.72e-01

Pos logit contributions
raid+0.060
ears+0.049
she+0.048
reath+0.046
 polish+0.046
Neg logit contributions
Bad-0.051
 narrative-0.049
 exploded-0.048
rob-0.048
 unison-0.047
Token,
Token ID11
Feature activation-5.87e-01

Pos logit contributions
raid+0.012
reath+0.009
ears+0.009
 polish+0.009
she+0.009
Neg logit contributions
Bad-0.014
 narrative-0.013
Did-0.013
rob-0.013
 exploded-0.012
Token our
Token ID674
Feature activation-2.37e+00

Pos logit contributions
Bad+0.021
rob+0.021
 narrative+0.021
Did+0.020
 exploded+0.019
Neg logit contributions
raid-0.018
 polish-0.014
reath-0.014
ears-0.014
she-0.014
Token missile
Token ID10105
Feature activation-6.07e+00

Pos logit contributions
Bad+0.083
rob+0.078
Did+0.077
 narrative+0.076
 exploded+0.074
Neg logit contributions
raid-0.080
ears-0.065
reath-0.065
 polish-0.062
erry-0.058
Token is
Token ID318
Feature activation-1.07e+00

Pos logit contributions
Bad+0.209
Did+0.196
 narrative+0.196
rob+0.190
 unison+0.184
Neg logit contributions
raid-0.202
reath-0.164
ears-0.163
 polish-0.160
she-0.151
Token ruined
Token ID20484
Feature activation-3.93e+00

Pos logit contributions
Bad+0.034
rob+0.034
 narrative+0.033
Did+0.033
 unison+0.031
Neg logit contributions
raid-0.036
 polish-0.031
reath-0.030
wn-0.030
ears-0.030
Token!"
Token ID2474
Feature activation-8.23e-01

Pos logit contributions
Bad+0.158
Did+0.155
 narrative+0.154
rob+0.152
Our+0.144
Neg logit contributions
raid-0.100
 polish-0.082
ears-0.080
she-0.077
 She-0.077
Token Tim
Token ID5045
Feature activation+3.25e-01

Pos logit contributions
Bad+0.031
 narrative+0.030
rob+0.029
 exploded+0.028
Did+0.028
Neg logit contributions
raid-0.024
 She-0.020
she-0.020
reath-0.019
ears-0.019
Token cried
Token ID16896
Feature activation-7.62e-02

Pos logit contributions
raid+0.012
reath+0.010
ears+0.010
 polish+0.009
wn+0.009
Neg logit contributions
Bad-0.011
 exploded-0.010
 narrative-0.009
Did-0.009
rob-0.009
Token to
Token ID284
Feature activation-9.08e-01

Pos logit contributions
Bad+0.004
 attacking+0.004
 exploded+0.003
 bomb+0.003
 dodging+0.003
Neg logit contributions
raid-0.004
reath-0.003
ears-0.003
umble-0.003
erry-0.003
Token his
Token ID465
Feature activation-2.05e+00

Pos logit contributions
Bad+0.032
 exploded+0.029
 bomb+0.028
 narrative+0.028
Did+0.028
Neg logit contributions
raid-0.031
reath-0.026
ears-0.026
wn-0.024
erry-0.023
Token mom
Token ID1995
Feature activation-2.10e+00

Pos logit contributions
Bad+0.078
 exploded+0.072
 narrative+0.071
Did+0.071
rob+0.071
Neg logit contributions
raid-0.063
reath-0.052
ears-0.050
 polish-0.048
wn-0.046
Token's
Token ID338
Feature activation-3.55e+00

Pos logit contributions
Did+0.047
Bad+0.047
boys+0.046
 exploded+0.043
glass+0.043
Neg logit contributions
raid-0.085
reath-0.083
ears-0.075
wn-0.072
umble-0.072
Token needle
Token ID17598
Feature activation-1.17e+00

Pos logit contributions
Bad+0.101
 narrative+0.095
boys+0.093
 bomb+0.093
 unison+0.091
Neg logit contributions
raid-0.132
reath-0.120
wn-0.111
ears-0.109
umble-0.107
Tokenwork
Token ID1818
Feature activation-5.98e+00

Pos logit contributions
Bad+0.044
 narrative+0.040
 exploded+0.040
Did+0.039
rob+0.038
Neg logit contributions
raid-0.037
reath-0.030
ears-0.029
 polish-0.029
annah-0.028
Token box
Token ID3091
Feature activation-7.75e-01

Pos logit contributions
Bad+0.208
 exploded+0.192
 narrative+0.189
Did+0.186
 bomb+0.185
Neg logit contributions
raid-0.201
reath-0.171
ears-0.163
wn-0.153
 polish-0.152
Token and
Token ID290
Feature activation-9.72e-01

Pos logit contributions
Bad+0.029
 narrative+0.026
 exploded+0.026
Did+0.026
rob+0.025
Neg logit contributions
raid-0.025
reath-0.020
ears-0.020
 polish-0.019
wn-0.019
Token took
Token ID1718
Feature activation-5.42e-01

Pos logit contributions
Bad+0.037
 exploded+0.034
 narrative+0.033
Did+0.033
 bomb+0.033
Neg logit contributions
raid-0.030
reath-0.025
ears-0.024
wn-0.022
 polish-0.022
Token out
Token ID503
Feature activation+5.15e-01

Pos logit contributions
Bad+0.014
 exploded+0.013
 bomb+0.013
 no+0.013
glass+0.012
Neg logit contributions
raid-0.022
ears-0.022
reath-0.021
umble-0.019
erry-0.019
Token a
Token ID257
Feature activation-9.13e-01

Pos logit contributions
raid+0.021
reath+0.019
ears+0.018
umble+0.017
annah+0.017
Neg logit contributions
Bad-0.014
 bomb-0.012
 exploded-0.012
 narrative-0.012
Did-0.012
Token rock
Token ID3881
Feature activation+3.63e-01

Pos logit contributions
raid+0.003
reath+0.003
 polish+0.003
ears+0.003
 She+0.002
Neg logit contributions
Bad-0.005
 narrative-0.005
rob-0.005
Did-0.005
 exploded-0.005
Token and
Token ID290
Feature activation-4.10e-01

Pos logit contributions
raid+0.013
reath+0.011
ears+0.011
wn+0.010
 polish+0.010
Neg logit contributions
Bad-0.012
 exploded-0.011
 narrative-0.011
Did-0.010
 bomb-0.010
Token falls
Token ID8953
Feature activation-2.27e+00

Pos logit contributions
Bad+0.015
 narrative+0.013
 exploded+0.013
Did+0.013
rob+0.013
Neg logit contributions
raid-0.013
reath-0.011
ears-0.011
 polish-0.010
she-0.010
Token off
Token ID572
Feature activation+1.40e-01

Pos logit contributions
Bad+0.083
 exploded+0.078
 bomb+0.074
Did+0.074
 narrative+0.071
Neg logit contributions
raid-0.074
reath-0.066
ears-0.059
annah-0.058
wn-0.056
Token his
Token ID465
Feature activation-2.23e+00

Pos logit contributions
raid+0.004
reath+0.004
ears+0.004
wn+0.003
 polish+0.003
Neg logit contributions
Bad-0.005
 exploded-0.005
 narrative-0.005
Did-0.005
 bomb-0.005
Token motorcycle
Token ID18757
Feature activation-5.94e+00

Pos logit contributions
Bad+0.090
Did+0.087
 narrative+0.085
rob+0.082
Our+0.080
Neg logit contributions
raid-0.062
 polish-0.052
reath-0.050
 attention-0.048
ears-0.047
Token.
Token ID13
Feature activation-8.22e-02

Pos logit contributions
Bad+0.248
 narrative+0.232
Did+0.228
rob+0.224
 exploded+0.224
Neg logit contributions
raid-0.163
reath-0.125
ears-0.121
 polish-0.117
wn-0.112
Token He
Token ID679
Feature activation-7.88e-01

Pos logit contributions
Bad+0.003
Did+0.003
 exploded+0.003
 bomb+0.002
 narrative+0.002
Neg logit contributions
raid-0.003
reath-0.003
ears-0.002
wn-0.002
erry-0.002
Token hurts
Token ID20406
Feature activation-2.73e+00

Pos logit contributions
Bad+0.028
Did+0.027
 narrative+0.027
rob+0.026
 unison+0.026
Neg logit contributions
raid-0.024
 polish-0.020
ears-0.019
reath-0.019
she-0.019
Token his
Token ID465
Feature activation-4.66e-01

Pos logit contributions
 narrative+0.118
Bad+0.116
rob+0.114
 exploded+0.114
storm+0.110
Neg logit contributions
raid-0.065
 She-0.053
 polish-0.051
 her-0.048
 care-0.047
Token knee
Token ID10329
Feature activation-2.07e+00

Pos logit contributions
Did+0.020
Bad+0.019
 narrative+0.019
rob+0.019
Our+0.018
Neg logit contributions
raid-0.013
 polish-0.010
reath-0.010
 attention-0.010
 old-0.009
Token
Token ID220
Feature activation+1.06e+00

Pos logit contributions
raid+0.008
reath+0.007
ears+0.006
wn+0.006
 polish+0.006
Neg logit contributions
Bad-0.006
 exploded-0.005
 narrative-0.005
Did-0.005
 bomb-0.005
Token
Token ID198
Feature activation-1.61e+00

Pos logit contributions
raid+0.042
reath+0.037
wn+0.034
 polish+0.034
ears+0.033
Neg logit contributions
Bad-0.030
 narrative-0.028
Did-0.028
 exploded-0.027
 unison-0.026
Token
Token ID198
Feature activation-1.30e+00

Pos logit contributions
Bad+0.053
Did+0.048
 narrative+0.047
 exploded+0.047
rob+0.045
Neg logit contributions
raid-0.059
reath-0.050
ears-0.047
 polish-0.046
wn-0.045
TokenThe
Token ID464
Feature activation-1.43e+00

Pos logit contributions
Bad+0.039
 exploded+0.035
 narrative+0.035
Did+0.035
rob+0.033
Neg logit contributions
raid-0.050
reath-0.043
ears-0.042
 polish-0.040
wn-0.040
Token town
Token ID3240
Feature activation-1.53e+00

Pos logit contributions
Bad+0.053
rob+0.049
 exploded+0.049
Did+0.049
 narrative+0.048
Neg logit contributions
raid-0.044
reath-0.037
ears-0.034
 polish-0.034
erry-0.032
Tokenspe
Token ID4125
Feature activation-5.89e+00

Pos logit contributions
Bad+0.046
rob+0.042
Did+0.040
 narrative+0.039
girls+0.038
Neg logit contributions
raid-0.059
ears-0.048
 polish-0.048
 She-0.048
she-0.047
Tokenople
Token ID643
Feature activation-2.25e+00

Pos logit contributions
 bomb+0.181
Bad+0.175
Did+0.173
 attacking+0.171
storm+0.171
Neg logit contributions
raid-0.219
ears-0.162
annah-0.162
up-0.159
ingle-0.157
Token had
Token ID550
Feature activation-2.68e+00

Pos logit contributions
Bad+0.072
 bomb+0.065
rob+0.064
 narrative+0.064
Did+0.062
Neg logit contributions
raid-0.082
 polish-0.070
 care-0.067
 She-0.065
reath-0.065
Token to
Token ID284
Feature activation+8.13e-02

Pos logit contributions
Bad+0.092
 narrative+0.084
rob+0.083
Did+0.082
 exploded+0.082
Neg logit contributions
raid-0.091
reath-0.075
ears-0.073
 polish-0.072
wn-0.071
Token find
Token ID1064
Feature activation+1.14e+00

Pos logit contributions
raid+0.002
reath+0.002
 polish+0.002
 care+0.001
wn+0.001
Neg logit contributions
Bad-0.004
Did-0.003
rob-0.003
 exploded-0.003
 narrative-0.003
Token a
Token ID257
Feature activation-1.30e+00

Pos logit contributions
raid+0.037
reath+0.031
 polish+0.030
ears+0.029
wn+0.029
Neg logit contributions
Bad-0.040
 narrative-0.037
Did-0.037
 exploded-0.036
rob-0.036
Token back
Token ID736
Feature activation-4.87e-01

Pos logit contributions
Bad+0.031
 narrative+0.029
Did+0.028
rob+0.028
 exploded+0.028
Neg logit contributions
raid-0.032
ears-0.027
reath-0.027
 polish-0.026
wn-0.026
Token to
Token ID284
Feature activation-8.38e-01

Pos logit contributions
Bad+0.020
 exploded+0.018
 narrative+0.018
Did+0.018
rob+0.018
Neg logit contributions
raid-0.014
reath-0.011
ears-0.010
 polish-0.010
wn-0.010
Token shore
Token ID15191
Feature activation-1.17e+00

Pos logit contributions
Bad+0.035
 narrative+0.035
Did+0.033
rob+0.033
 exploded+0.033
Neg logit contributions
raid-0.021
 polish-0.018
reath-0.017
 care-0.017
 She-0.016
Token and
Token ID290
Feature activation-1.13e+00

Pos logit contributions
Bad+0.047
 narrative+0.045
 exploded+0.043
Did+0.043
rob+0.043
Neg logit contributions
raid-0.033
ears-0.027
reath-0.025
 polish-0.025
 She-0.025
Token he
Token ID339
Feature activation-2.46e+00

Pos logit contributions
Bad+0.044
 narrative+0.043
rob+0.043
 unison+0.041
Did+0.040
Neg logit contributions
raid-0.032
 polish-0.028
 care-0.026
 she-0.026
 try-0.025
Token drowned
Token ID30859
Feature activation-5.86e+00

Pos logit contributions
 narrative+0.095
rob+0.094
Bad+0.090
 bomb+0.085
Did+0.084
Neg logit contributions
raid-0.067
 polish-0.059
 try-0.057
 care-0.057
 comfortable-0.054
Token in
Token ID287
Feature activation-5.49e-01

Pos logit contributions
Bad+0.263
 narrative+0.259
rob+0.250
Did+0.245
 unison+0.242
Neg logit contributions
raid-0.135
ears-0.098
 polish-0.098
 attention-0.098
reath-0.093
Token the
Token ID262
Feature activation-6.56e-01

Pos logit contributions
 narrative+0.023
Bad+0.022
rob+0.022
Did+0.022
boys+0.021
Neg logit contributions
raid-0.013
 polish-0.011
 care-0.010
 old-0.010
 her-0.010
Token sea
Token ID5417
Feature activation-8.56e-01

Pos logit contributions
Bad+0.023
girls+0.022
rob+0.022
Did+0.022
 narrative+0.021
Neg logit contributions
raid-0.018
 polish-0.018
 old-0.017
 comfortable-0.016
reath-0.016
Token.
Token ID13
Feature activation-7.64e-01

Pos logit contributions
Bad+0.038
 narrative+0.036
rob+0.036
Did+0.035
 exploded+0.034
Neg logit contributions
raid-0.020
ears-0.015
 polish-0.014
reath-0.014
annah-0.013
Token
Token ID198
Feature activation-1.09e+00

Pos logit contributions
Bad+0.027
 narrative+0.025
 exploded+0.024
rob+0.024
Did+0.024
Neg logit contributions
raid-0.025
reath-0.021
ears-0.021
 She-0.020
 polish-0.020
Token too
Token ID1165
Feature activation+9.95e-01

Pos logit contributions
Bad+0.046
 narrative+0.042
 exploded+0.042
Did+0.041
rob+0.041
Neg logit contributions
raid-0.045
reath-0.038
ears-0.036
 polish-0.035
wn-0.035
Token strong
Token ID1913
Feature activation+7.91e-01

Pos logit contributions
raid+0.026
reath+0.021
ears+0.019
wn+0.018
she+0.018
Neg logit contributions
Bad-0.043
 exploded-0.040
 bomb-0.039
 narrative-0.039
Did-0.039
Token.
Token ID13
Feature activation-2.73e-01

Pos logit contributions
raid+0.022
reath+0.018
ears+0.017
 polish+0.016
wn+0.016
Neg logit contributions
Bad-0.032
 narrative-0.029
 exploded-0.029
Did-0.029
rob-0.028
Token They
Token ID1119
Feature activation-1.15e+00

Pos logit contributions
Bad+0.008
 exploded+0.008
Did+0.007
 bomb+0.007
sed+0.007
Neg logit contributions
raid-0.010
reath-0.009
ears-0.008
wn-0.008
erry-0.008
Token both
Token ID1111
Feature activation-7.13e-01

Pos logit contributions
rob+0.043
Bad+0.042
 narrative+0.041
Did+0.038
 Year+0.037
Neg logit contributions
raid-0.034
 care-0.031
 polish-0.031
 try-0.028
 comfortable-0.026
Token drowned
Token ID30859
Feature activation-5.86e+00

Pos logit contributions
 narrative+0.025
rob+0.025
Bad+0.025
Did+0.023
 bomb+0.022
Neg logit contributions
raid-0.023
 care-0.020
 polish-0.019
 try-0.017
 comfortable-0.017
Token,
Token ID11
Feature activation-1.35e+00

Pos logit contributions
 narrative+0.253
Bad+0.252
rob+0.242
Did+0.234
 unison+0.230
Neg logit contributions
raid-0.138
 attention-0.108
 polish-0.104
 care-0.103
ears-0.100
Token and
Token ID290
Feature activation-1.04e+00

Pos logit contributions
rob+0.055
 narrative+0.054
Bad+0.054
 unison+0.052
girls+0.051
Neg logit contributions
raid-0.030
 she-0.028
 She-0.027
 comfortable-0.026
 polish-0.026
Token their
Token ID511
Feature activation-2.51e+00

Pos logit contributions
rob+0.045
Bad+0.043
 narrative+0.042
 unison+0.042
Did+0.041
Neg logit contributions
raid-0.023
 she-0.022
 her-0.021
 She-0.020
 care-0.020
Token bodies
Token ID5920
Feature activation-1.27e+00

Pos logit contributions
rob+0.098
Bad+0.094
Did+0.092
 narrative+0.084
Our+0.082
Neg logit contributions
raid-0.070
 old-0.066
 polish-0.064
 comfortable-0.063
 attention-0.062
Token were
Token ID547
Feature activation-2.32e+00

Pos logit contributions
Bad+0.034
 narrative+0.032
rob+0.030
Did+0.029
 bomb+0.028
Neg logit contributions
raid-0.053
reath-0.045
 polish-0.044
ears-0.044
wn-0.043
Token counter
Token ID3753
Feature activation+4.62e-01

Pos logit contributions
Bad+0.003
 exploded+0.003
 narrative+0.003
Did+0.003
 bomb+0.003
Neg logit contributions
raid-0.003
reath-0.002
ears-0.002
wn-0.002
 polish-0.002
Token fixed
Token ID5969
Feature activation-1.96e+00

Pos logit contributions
raid+0.016
ears+0.013
 She+0.013
 polish+0.013
reath+0.013
Neg logit contributions
Bad-0.016
 narrative-0.014
rob-0.014
Did-0.013
 bomb-0.013
Token her
Token ID607
Feature activation+9.81e-01

Pos logit contributions
Bad+0.060
 bomb+0.055
 exploded+0.054
rob+0.054
boys+0.053
Neg logit contributions
raid-0.074
reath-0.064
ears-0.062
umble-0.060
wn-0.057
Token car
Token ID1097
Feature activation-3.15e+00

Pos logit contributions
raid+0.027
reath+0.022
 polish+0.022
ears+0.021
 old+0.020
Neg logit contributions
Bad-0.040
Did-0.038
 narrative-0.038
rob-0.037
 exploded-0.037
Token in
Token ID287
Feature activation-1.03e+00

Pos logit contributions
Bad+0.096
 exploded+0.090
 bomb+0.086
 narrative+0.086
Did+0.085
Neg logit contributions
raid-0.116
reath-0.103
ears-0.096
wn-0.092
 polish-0.090
Token no
Token ID645
Feature activation-5.85e+00

Pos logit contributions
Bad+0.038
 narrative+0.035
 exploded+0.035
Did+0.034
rob+0.034
Neg logit contributions
raid-0.033
reath-0.027
ears-0.026
 polish-0.026
wn-0.025
Token time
Token ID640
Feature activation+6.45e-01

Pos logit contributions
Bad+0.191
 exploded+0.176
 narrative+0.173
 bomb+0.172
 unison+0.170
Neg logit contributions
raid-0.205
reath-0.184
ears-0.181
she-0.170
umble-0.165
Token.
Token ID13
Feature activation-3.86e-01

Pos logit contributions
raid+0.020
reath+0.017
ears+0.016
 polish+0.015
wn+0.015
Neg logit contributions
Bad-0.024
 narrative-0.022
 exploded-0.022
Did-0.022
rob-0.021
Token Jane
Token ID12091
Feature activation+7.56e-01

Pos logit contributions
Bad+0.012
Did+0.011
 narrative+0.011
 exploded+0.010
 unison+0.010
Neg logit contributions
raid-0.015
reath-0.013
 polish-0.011
wn-0.011
ears-0.011
Token thanked
Token ID26280
Feature activation+6.19e-01

Pos logit contributions
raid+0.030
reath+0.025
ears+0.025
 polish+0.024
annah+0.024
Neg logit contributions
Bad-0.022
 narrative-0.020
Did-0.019
 exploded-0.019
 bomb-0.019
Token the
Token ID262
Feature activation+2.02e+00

Pos logit contributions
raid+0.022
reath+0.019
ears+0.018
wn+0.017
 polish+0.016
Neg logit contributions
Bad-0.021
 exploded-0.019
 narrative-0.019
Did-0.019
 bomb-0.018
Token shine
Token ID18340
Feature activation+8.26e-01

Pos logit contributions
Bad+0.051
 exploded+0.047
 narrative+0.046
Did+0.046
 bomb+0.045
Neg logit contributions
raid-0.047
reath-0.041
ears-0.038
wn-0.036
 polish-0.036
Token through
Token ID832
Feature activation+1.45e-01

Pos logit contributions
raid+0.030
reath+0.025
ears+0.024
wn+0.023
 polish+0.023
Neg logit contributions
Bad-0.027
 exploded-0.025
 narrative-0.024
Did-0.024
 bomb-0.024
Token.
Token ID13
Feature activation-3.44e-01

Pos logit contributions
raid+0.003
 polish+0.003
 She+0.003
 her+0.002
 care+0.002
Neg logit contributions
rob-0.006
Bad-0.006
 narrative-0.006
sed-0.006
storm-0.006
Token The
Token ID383
Feature activation-6.82e-01

Pos logit contributions
Bad+0.012
 exploded+0.011
Did+0.010
 narrative+0.010
 bomb+0.010
Neg logit contributions
raid-0.012
reath-0.011
ears-0.010
wn-0.009
 polish-0.009
Token town
Token ID3240
Feature activation-1.19e+00

Pos logit contributions
Bad+0.024
 exploded+0.022
 narrative+0.021
 bomb+0.021
Did+0.021
Neg logit contributions
raid-0.024
ears-0.020
reath-0.020
wn-0.019
annah-0.018
Tokenspe
Token ID4125
Feature activation-5.84e+00

Pos logit contributions
Bad+0.034
 narrative+0.030
rob+0.030
Did+0.030
 exploded+0.029
Neg logit contributions
raid-0.048
reath-0.040
ears-0.040
 polish-0.039
she-0.038
Tokenople
Token ID643
Feature activation-1.53e+00

Pos logit contributions
Bad+0.162
 bomb+0.158
storm+0.158
Did+0.156
 narrative+0.154
Neg logit contributions
raid-0.235
ears-0.177
 polish-0.175
up-0.175
wn-0.173
Token were
Token ID547
Feature activation-1.37e+00

Pos logit contributions
Bad+0.047
 narrative+0.042
rob+0.042
 bomb+0.041
girls+0.039
Neg logit contributions
raid-0.058
 polish-0.051
reath-0.047
 care-0.047
she-0.046
Token very
Token ID845
Feature activation+5.68e-01

Pos logit contributions
Bad+0.054
 narrative+0.050
rob+0.050
Did+0.049
 exploded+0.049
Neg logit contributions
raid-0.039
reath-0.032
ears-0.030
 polish-0.030
wn-0.029
Token happy
Token ID3772
Feature activation+2.45e-01

Pos logit contributions
raid+0.018
reath+0.015
ears+0.014
wn+0.014
annah+0.013
Neg logit contributions
Bad-0.022
 exploded-0.020
Did-0.019
 narrative-0.019
 bomb-0.019
Token and
Token ID290
Feature activation+8.93e-01

Pos logit contributions
raid+0.007
 She+0.005
ears+0.005
 polish+0.005
 she+0.005
Neg logit contributions
Bad-0.010
 narrative-0.010
rob-0.010
 exploded-0.009
Did-0.009
Token They
Token ID1119
Feature activation-5.74e-01

Pos logit contributions
raid+0.003
 She+0.003
reath+0.003
ears+0.003
 polish+0.003
Neg logit contributions
Bad-0.004
rob-0.004
 narrative-0.004
 exploded-0.004
Did-0.004
Token ran
Token ID4966
Feature activation-8.63e-01

Pos logit contributions
Bad+0.019
 narrative+0.018
rob+0.018
 bomb+0.018
storm+0.018
Neg logit contributions
raid-0.018
 polish-0.016
 She-0.016
reath-0.015
ears-0.015
Token back
Token ID736
Feature activation-1.68e+00

Pos logit contributions
Bad+0.035
 exploded+0.032
Did+0.031
 bomb+0.031
 narrative+0.031
Neg logit contributions
raid-0.025
reath-0.021
ears-0.019
umble-0.018
annah-0.018
Token to
Token ID284
Feature activation-1.77e+00

Pos logit contributions
Bad+0.062
 exploded+0.057
 bomb+0.057
Did+0.056
 attacking+0.056
Neg logit contributions
raid-0.050
reath-0.046
wn-0.039
ears-0.039
annah-0.037
Token the
Token ID262
Feature activation-1.34e+00

Pos logit contributions
Bad+0.061
 narrative+0.058
 exploded+0.057
rob+0.057
Did+0.055
Neg logit contributions
raid-0.058
reath-0.049
 polish-0.047
ears-0.046
 She-0.045
Token je
Token ID11223
Feature activation-5.83e+00

Pos logit contributions
Bad+0.049
 narrative+0.045
 exploded+0.044
Did+0.044
rob+0.044
Neg logit contributions
raid-0.043
reath-0.036
ears-0.035
 polish-0.034
wn-0.032
Tokenep
Token ID538
Feature activation-2.22e+00

Pos logit contributions
Bad+0.116
 narrative+0.102
 exploded+0.101
 unison+0.095
 bomb+0.093
Neg logit contributions
raid-0.276
reath-0.250
ears-0.246
wn-0.235
 polish-0.234
Token.
Token ID13
Feature activation-4.56e-01

Pos logit contributions
Bad+0.099
 narrative+0.094
Did+0.090
rob+0.089
 exploded+0.088
Neg logit contributions
raid-0.055
reath-0.040
 polish-0.039
 She-0.039
ears-0.038
Token They
Token ID1119
Feature activation-7.81e-01

Pos logit contributions
Bad+0.017
rob+0.015
 narrative+0.015
 exploded+0.015
Did+0.015
Neg logit contributions
raid-0.014
 She-0.012
reath-0.012
ears-0.011
 polish-0.011
Token saw
Token ID2497
Feature activation-1.32e+00

Pos logit contributions
Bad+0.029
 narrative+0.028
storm+0.027
rob+0.027
 bomb+0.026
Neg logit contributions
raid-0.022
 polish-0.020
ears-0.018
 She-0.018
she-0.018
Token the
Token ID262
Feature activation-4.92e-01

Pos logit contributions
Bad+0.051
 narrative+0.049
rob+0.047
 exploded+0.047
Did+0.046
Neg logit contributions
raid-0.038
ears-0.031
reath-0.030
 polish-0.030
she-0.029
TokenThank
Token ID10449
Feature activation-5.12e-03

Pos logit contributions
Bad+0.028
 exploded+0.026
 bomb+0.025
 narrative+0.025
rob+0.024
Neg logit contributions
raid-0.037
reath-0.032
ears-0.030
 polish-0.030
she-0.030
Token you
Token ID345
Feature activation+1.53e+00

Pos logit contributions
Bad+0.000
 exploded+0.000
 narrative+0.000
Did+0.000
 bomb+0.000
Neg logit contributions
raid-0.000
reath-0.000
ears-0.000
she-0.000
 polish-0.000
Token,
Token ID11
Feature activation-1.74e-01

Pos logit contributions
raid+0.040
reath+0.032
ears+0.032
 She+0.030
erry+0.030
Neg logit contributions
Bad-0.064
 narrative-0.060
Did-0.060
 exploded-0.059
rob-0.058
Token Mr
Token ID1770
Feature activation+3.94e-01

Pos logit contributions
Bad+0.005
 exploded+0.005
 narrative+0.005
Did+0.005
rob+0.005
Neg logit contributions
raid-0.007
reath-0.006
ears-0.005
 polish-0.005
she-0.005
Token.
Token ID13
Feature activation+4.94e-01

Pos logit contributions
raid+0.013
reath+0.011
ears+0.010
wn+0.010
 polish+0.010
Neg logit contributions
Bad-0.014
 exploded-0.013
 narrative-0.013
Did-0.013
 bomb-0.013
Token Mechan
Token ID13438
Feature activation-5.82e+00

Pos logit contributions
raid+0.020
 polish+0.018
 She+0.018
ears+0.017
she+0.017
Neg logit contributions
Bad-0.011
 narrative-0.011
 exploded-0.011
 unison-0.010
rob-0.010
Tokenic
Token ID291
Feature activation+1.36e+00

Pos logit contributions
Bad+0.210
rob+0.201
 narrative+0.193
 exploded+0.191
Did+0.183
Neg logit contributions
raid-0.184
reath-0.155
ears-0.146
 She-0.146
 polish-0.144
Token!"
Token ID2474
Feature activation-2.10e-01

Pos logit contributions
raid+0.050
reath+0.043
ears+0.042
wn+0.040
 polish+0.039
Neg logit contributions
Bad-0.043
 exploded-0.039
 narrative-0.039
rob-0.038
 bomb-0.038
Token Tim
Token ID5045
Feature activation+7.45e-01

Pos logit contributions
Bad+0.006
 exploded+0.006
 narrative+0.005
Did+0.005
rob+0.005
Neg logit contributions
raid-0.008
reath-0.007
ears-0.007
wn-0.007
 polish-0.007
Tokenmy
Token ID1820
Feature activation+1.58e+00

Pos logit contributions
raid+0.021
reath+0.018
ears+0.016
wn+0.016
 polish+0.015
Neg logit contributions
Bad-0.029
 exploded-0.028
Did-0.027
 narrative-0.026
rob-0.026
Token said
Token ID531
Feature activation+8.24e-01

Pos logit contributions
raid+0.060
reath+0.052
ears+0.049
 polish+0.047
wn+0.047
Neg logit contributions
Bad-0.049
 exploded-0.044
 narrative-0.043
Did-0.043
rob-0.042
Token Ben
Token ID3932
Feature activation-2.48e-02

Pos logit contributions
raid+0.070
reath+0.056
ears+0.055
 polish+0.055
she+0.053
Neg logit contributions
Bad-0.090
 narrative-0.084
rob-0.082
Did-0.081
 exploded-0.081
Token slides
Token ID19392
Feature activation+7.26e-01

Pos logit contributions
Bad+0.001
 exploded+0.001
 narrative+0.001
Did+0.001
 bomb+0.001
Neg logit contributions
raid-0.001
reath-0.001
ears-0.001
 polish-0.001
wn-0.001
Token down
Token ID866
Feature activation+1.49e+00

Pos logit contributions
raid+0.025
reath+0.023
wn+0.021
annah+0.020
ears+0.019
Neg logit contributions
Bad-0.026
 exploded-0.024
 attacking-0.022
 guns-0.021
 drowned-0.021
Token,
Token ID11
Feature activation-4.73e-01

Pos logit contributions
raid+0.059
reath+0.054
wn+0.049
ears+0.048
annah+0.046
Neg logit contributions
Bad-0.045
 exploded-0.041
 bomb-0.040
 narrative-0.039
Did-0.038
Token his
Token ID465
Feature activation-1.33e+00

Pos logit contributions
Bad+0.018
 exploded+0.017
 narrative+0.017
Did+0.017
rob+0.016
Neg logit contributions
raid-0.014
reath-0.011
ears-0.011
 polish-0.010
she-0.010
Token rh
Token ID9529
Feature activation-5.79e+00

Pos logit contributions
Bad+0.049
Did+0.048
 narrative+0.047
rob+0.047
Our+0.044
Neg logit contributions
raid-0.042
reath-0.033
 polish-0.033
 old-0.032
ears-0.032
Tokenino
Token ID2879
Feature activation-3.55e+00

Pos logit contributions
Bad+0.169
 exploded+0.156
 narrative+0.155
Did+0.153
 unison+0.147
Neg logit contributions
raid-0.221
reath-0.191
ears-0.185
 polish-0.174
wn-0.171
Token falls
Token ID8953
Feature activation-2.21e+00

Pos logit contributions
Bad+0.124
 narrative+0.114
Did+0.112
rob+0.112
 exploded+0.109
Neg logit contributions
raid-0.117
reath-0.095
ears-0.095
 polish-0.091
she-0.088
Token out
Token ID503
Feature activation+5.82e-01

Pos logit contributions
Bad+0.082
 exploded+0.078
Did+0.073
 bomb+0.073
rob+0.071
Neg logit contributions
raid-0.071
reath-0.063
ears-0.056
annah-0.055
wn-0.052
Token of
Token ID286
Feature activation-5.76e-01

Pos logit contributions
raid+0.016
reath+0.013
ears+0.012
 polish+0.011
wn+0.011
Neg logit contributions
Bad-0.024
 exploded-0.023
 narrative-0.023
Did-0.022
rob-0.022
Token his
Token ID465
Feature activation-1.83e+00

Pos logit contributions
Bad+0.022
 narrative+0.021
Did+0.020
 exploded+0.020
boys+0.020
Neg logit contributions
raid-0.017
reath-0.014
 polish-0.013
ears-0.013
 She-0.012
Token into
Token ID656
Feature activation-1.24e+00

Pos logit contributions
raid+0.002
reath+0.002
ears+0.002
annah+0.002
umble+0.002
Neg logit contributions
Bad-0.002
 exploded-0.002
 bomb-0.002
 narrative-0.002
Did-0.002
Token the
Token ID262
Feature activation-6.65e-01

Pos logit contributions
Bad+0.047
 narrative+0.046
rob+0.044
 exploded+0.044
storm+0.043
Neg logit contributions
raid-0.035
reath-0.028
 polish-0.028
ears-0.027
 She-0.027
Token water
Token ID1660
Feature activation+7.29e-01

Pos logit contributions
rob+0.026
Bad+0.025
girls+0.024
Did+0.024
storm+0.024
Neg logit contributions
raid-0.016
reath-0.014
 polish-0.014
 old-0.014
wn-0.013
Token.
Token ID13
Feature activation-3.53e-01

Pos logit contributions
raid+0.018
ears+0.014
reath+0.013
 polish+0.013
 She+0.013
Neg logit contributions
Bad-0.032
 narrative-0.030
rob-0.030
Did-0.029
 exploded-0.029
Token Tom
Token ID4186
Feature activation-1.64e+00

Pos logit contributions
Bad+0.012
 exploded+0.011
 narrative+0.011
Did+0.011
rob+0.011
Neg logit contributions
raid-0.012
reath-0.010
ears-0.010
 polish-0.009
wn-0.009
Token drowned
Token ID30859
Feature activation-5.78e+00

Pos logit contributions
 narrative+0.069
rob+0.063
Bad+0.059
storm+0.058
 bomb+0.056
Neg logit contributions
raid-0.042
 polish-0.036
up-0.035
 try-0.034
ears-0.034
Token in
Token ID287
Feature activation-7.36e-01

Pos logit contributions
Bad+0.229
 narrative+0.228
rob+0.223
 unison+0.211
 exploded+0.208
Neg logit contributions
raid-0.156
 She-0.123
 polish-0.122
ears-0.122
reath-0.119
Token the
Token ID262
Feature activation-8.23e-01

Pos logit contributions
 narrative+0.030
Bad+0.030
rob+0.029
Did+0.028
 exploded+0.028
Neg logit contributions
raid-0.018
 polish-0.015
 She-0.014
 old-0.014
reath-0.014
Token water
Token ID1660
Feature activation+1.58e-01

Pos logit contributions
rob+0.033
girls+0.032
Bad+0.031
Did+0.030
boys+0.030
Neg logit contributions
 old-0.018
raid-0.018
 polish-0.017
reath-0.017
 comfortable-0.016
Token and
Token ID290
Feature activation-1.07e+00

Pos logit contributions
raid+0.004
ears+0.003
 She+0.003
 polish+0.003
reath+0.003
Neg logit contributions
Bad-0.007
 narrative-0.006
rob-0.006
Did-0.006
 exploded-0.006
Token died
Token ID3724
Feature activation-3.94e+00

Pos logit contributions
 unison+0.042
 narrative+0.042
rob+0.041
Bad+0.040
Did+0.037
Neg logit contributions
raid-0.028
 her-0.024
 she-0.024
 She-0.023
 polish-0.022
Token when
Token ID618
Feature activation+1.78e+00

Pos logit contributions
raid+0.006
reath+0.005
ears+0.005
 polish+0.004
wn+0.004
Neg logit contributions
Bad-0.006
 narrative-0.005
 exploded-0.005
rob-0.005
Did-0.005
Token he
Token ID339
Feature activation-1.80e+00

Pos logit contributions
raid+0.047
 polish+0.037
 She+0.036
reath+0.036
she+0.035
Neg logit contributions
Bad-0.071
 narrative-0.067
 exploded-0.067
rob-0.067
Did-0.065
Token noticed
Token ID6810
Feature activation-1.18e+00

Pos logit contributions
Bad+0.058
 narrative+0.056
 bomb+0.053
rob+0.052
 exploded+0.050
Neg logit contributions
raid-0.064
ears-0.052
 polish-0.052
reath-0.051
she-0.050
Token that
Token ID326
Feature activation-1.33e+00

Pos logit contributions
Bad+0.043
 narrative+0.042
 exploded+0.040
Did+0.039
rob+0.038
Neg logit contributions
raid-0.036
 polish-0.030
ears-0.028
reath-0.028
she-0.028
Token the
Token ID262
Feature activation-2.43e-01

Pos logit contributions
Bad+0.052
 exploded+0.049
 narrative+0.049
Did+0.048
 unison+0.047
Neg logit contributions
raid-0.037
 polish-0.029
ears-0.028
reath-0.028
she-0.027
Token rh
Token ID9529
Feature activation-5.78e+00

Pos logit contributions
 narrative+0.006
Bad+0.006
Did+0.005
rob+0.005
 exploded+0.005
Neg logit contributions
raid-0.010
 old-0.009
reath-0.009
 polish-0.009
ears-0.008
Tokenin
Token ID259
Feature activation-2.69e+00

Pos logit contributions
Bad+0.229
 exploded+0.213
 narrative+0.213
Did+0.209
 bomb+0.205
Neg logit contributions
raid-0.166
reath-0.135
ears-0.129
 polish-0.120
she-0.117
Tokenoc
Token ID420
Feature activation-2.40e+00

Pos logit contributions
 narrative+0.064
Bad+0.060
Did+0.053
 unison+0.052
 exploded+0.050
Neg logit contributions
raid-0.116
reath-0.098
 polish-0.098
ears-0.097
erry-0.097
Tokeneros
Token ID27498
Feature activation-3.28e+00

Pos logit contributions
Bad+0.051
Did+0.044
 narrative+0.044
 exploded+0.044
 bomb+0.040
Neg logit contributions
raid-0.115
reath-0.101
ears-0.098
 polish-0.095
erry-0.092
Token looked
Token ID3114
Feature activation-3.35e-01

Pos logit contributions
Bad+0.092
 narrative+0.087
rob+0.084
Did+0.081
 bomb+0.079
Neg logit contributions
raid-0.129
 polish-0.108
reath-0.108
ears-0.107
she-0.103
Token very
Token ID845
Feature activation+1.02e-01

Pos logit contributions
Bad+0.013
 exploded+0.012
Did+0.011
 narrative+0.011
 bomb+0.011
Neg logit contributions
raid-0.011
reath-0.009
ears-0.008
wn-0.008
annah-0.008
Token,
Token ID11
Feature activation-5.01e-01

Pos logit contributions
Bad+0.038
 narrative+0.036
rob+0.035
Did+0.035
 exploded+0.035
Neg logit contributions
raid-0.028
reath-0.023
ears-0.022
 She-0.022
she-0.022
Token Mom
Token ID11254
Feature activation+4.02e-01

Pos logit contributions
Bad+0.019
rob+0.019
 exploded+0.018
 narrative+0.018
Did+0.017
Neg logit contributions
raid-0.014
 polish-0.012
reath-0.012
 She-0.012
ears-0.011
Token!
Token ID0
Feature activation-5.22e-02

Pos logit contributions
raid+0.015
reath+0.014
wn+0.012
ears+0.012
she+0.012
Neg logit contributions
Bad-0.012
 exploded-0.011
boys-0.011
Did-0.011
rob-0.010
Token There
Token ID1318
Feature activation+6.55e-02

Pos logit contributions
Bad+0.002
 narrative+0.002
rob+0.002
 exploded+0.002
 bomb+0.002
Neg logit contributions
raid-0.001
 She-0.001
reath-0.001
ears-0.001
she-0.001
Token's
Token ID338
Feature activation-3.75e+00

Pos logit contributions
raid+0.003
reath+0.002
ears+0.002
wn+0.002
 polish+0.002
Neg logit contributions
Bad-0.002
 exploded-0.002
 narrative-0.002
Did-0.002
 bomb-0.002
Token no
Token ID645
Feature activation-5.78e+00

Pos logit contributions
Bad+0.131
rob+0.128
Did+0.125
 narrative+0.124
storm+0.118
Neg logit contributions
raid-0.111
 polish-0.094
reath-0.094
 She-0.091
 old-0.091
Token frog
Token ID21264
Feature activation-2.13e+00

Pos logit contributions
Bad+0.220
 narrative+0.201
 exploded+0.201
Did+0.200
rob+0.197
Neg logit contributions
raid-0.178
reath-0.147
ears-0.138
 polish-0.134
wn-0.132
Token in
Token ID287
Feature activation-4.25e-01

Pos logit contributions
Bad+0.073
 narrative+0.073
rob+0.069
Did+0.068
 unison+0.066
Neg logit contributions
raid-0.070
ears-0.059
reath-0.056
 polish-0.055
wn-0.053
Token the
Token ID262
Feature activation-8.57e-01

Pos logit contributions
Bad+0.016
 narrative+0.016
Did+0.016
rob+0.016
 exploded+0.016
Neg logit contributions
raid-0.012
 polish-0.009
reath-0.009
ears-0.009
wn-0.008
Token mailbox
Token ID37282
Feature activation-2.16e+00

Pos logit contributions
Bad+0.031
rob+0.030
 exploded+0.029
Did+0.028
 narrative+0.028
Neg logit contributions
raid-0.026
reath-0.022
 She-0.021
 polish-0.021
wn-0.020
Token."
Token ID526
Feature activation-1.03e-01

Pos logit contributions
Bad+0.082
 narrative+0.077
Did+0.074
rob+0.074
 exploded+0.073
Neg logit contributions
raid-0.066
reath-0.052
ears-0.052
 polish-0.050
 She-0.048
Token your
Token ID534
Feature activation-7.63e-01

Pos logit contributions
raid+0.030
reath+0.026
ears+0.025
wn+0.023
 polish+0.023
Neg logit contributions
Bad-0.031
 exploded-0.028
 narrative-0.027
Did-0.027
 bomb-0.027
Token friends
Token ID2460
Feature activation-1.32e+00

Pos logit contributions
Bad+0.025
 narrative+0.023
 exploded+0.022
 bomb+0.022
 unison+0.022
Neg logit contributions
raid-0.026
reath-0.024
she-0.023
ears-0.022
wn-0.022
Token.
Token ID13
Feature activation-4.65e-01

Pos logit contributions
Bad+0.044
 exploded+0.040
 narrative+0.040
Did+0.040
 bomb+0.039
Neg logit contributions
raid-0.046
reath-0.040
ears-0.038
wn-0.036
 polish-0.035
Token There
Token ID1318
Feature activation+1.72e-01

Pos logit contributions
Bad+0.016
 narrative+0.014
Did+0.014
 exploded+0.014
 bomb+0.014
Neg logit contributions
raid-0.016
reath-0.014
ears-0.013
 polish-0.013
wn-0.013
Token's
Token ID338
Feature activation-3.51e+00

Pos logit contributions
raid+0.007
reath+0.006
ears+0.006
wn+0.005
 polish+0.005
Neg logit contributions
Bad-0.005
 narrative-0.004
 exploded-0.004
Did-0.004
 bomb-0.004
Token no
Token ID645
Feature activation-5.77e+00

Pos logit contributions
Bad+0.102
 exploded+0.091
 narrative+0.090
Did+0.089
rob+0.088
Neg logit contributions
raid-0.138
reath-0.120
ears-0.115
 polish-0.112
wn-0.111
Token need
Token ID761
Feature activation-8.10e-01

Pos logit contributions
Bad+0.215
 exploded+0.197
 narrative+0.196
 bomb+0.193
Did+0.188
Neg logit contributions
raid-0.177
reath-0.153
ears-0.147
she-0.140
annah-0.135
Token to
Token ID284
Feature activation+7.97e-01

Pos logit contributions
Bad+0.034
 exploded+0.032
 narrative+0.032
Did+0.031
rob+0.031
Neg logit contributions
raid-0.021
reath-0.017
ears-0.016
 polish-0.015
wn-0.015
Token be
Token ID307
Feature activation-1.04e+00

Pos logit contributions
raid+0.024
reath+0.019
ears+0.018
 polish+0.017
wn+0.017
Neg logit contributions
Bad-0.031
 exploded-0.029
 narrative-0.029
Did-0.028
 bomb-0.028
Token sorry
Token ID7926
Feature activation-3.33e+00

Pos logit contributions
Bad+0.038
 exploded+0.035
 narrative+0.035
Did+0.034
rob+0.033
Neg logit contributions
raid-0.034
reath-0.028
ears-0.027
 polish-0.025
wn-0.025
Token when
Token ID618
Feature activation+1.16e+00

Pos logit contributions
Bad+0.107
 exploded+0.097
 narrative+0.097
Did+0.095
 bomb+0.095
Neg logit contributions
raid-0.119
reath-0.104
ears-0.098
wn-0.094
annah-0.091
Token couldn
Token ID3521
Feature activation-6.07e-01

Pos logit contributions
 narrative+0.013
Bad+0.012
rob+0.012
 unison+0.011
 bomb+0.011
Neg logit contributions
raid-0.011
 polish-0.009
 She-0.008
ears-0.008
erry-0.008
Token't
Token ID470
Feature activation-2.43e+00

Pos logit contributions
Bad+0.021
 narrative+0.019
Did+0.019
 exploded+0.019
 bomb+0.018
Neg logit contributions
raid-0.020
reath-0.017
she-0.017
ears-0.017
 She-0.017
Token swim
Token ID9422
Feature activation-1.08e+00

Pos logit contributions
Bad+0.090
 exploded+0.084
Did+0.080
boys+0.080
 bomb+0.079
Neg logit contributions
raid-0.075
ears-0.063
reath-0.061
wn-0.057
annah-0.056
Token and
Token ID290
Feature activation-3.66e-01

Pos logit contributions
Bad+0.036
 narrative+0.032
 exploded+0.032
Did+0.032
rob+0.031
Neg logit contributions
raid-0.038
reath-0.032
ears-0.031
 polish-0.030
wn-0.030
Token he
Token ID339
Feature activation-2.10e+00

Pos logit contributions
Bad+0.012
 narrative+0.012
rob+0.011
Did+0.011
 unison+0.011
Neg logit contributions
raid-0.013
 polish-0.011
ears-0.010
 She-0.010
reath-0.010
Token drowned
Token ID30859
Feature activation-5.76e+00

Pos logit contributions
Bad+0.062
 narrative+0.059
rob+0.056
Did+0.055
 bomb+0.055
Neg logit contributions
raid-0.082
reath-0.068
ears-0.067
 polish-0.066
wn-0.064
Token.
Token ID13
Feature activation-7.25e-01

Pos logit contributions
Bad+0.247
 narrative+0.243
rob+0.231
 exploded+0.227
Did+0.227
Neg logit contributions
raid-0.145
ears-0.108
 polish-0.107
reath-0.106
 attention-0.105
Token
Token ID198
Feature activation-1.11e+00

Pos logit contributions
Bad+0.024
 exploded+0.022
Did+0.022
 narrative+0.021
 bomb+0.021
Neg logit contributions
raid-0.026
reath-0.023
ears-0.021
wn-0.021
 polish-0.020
Token
Token ID198
Feature activation-7.72e-01

Pos logit contributions
Bad+0.039
 exploded+0.036
 narrative+0.036
Did+0.035
rob+0.035
Neg logit contributions
raid-0.037
reath-0.031
ears-0.030
 polish-0.028
wn-0.028
TokenThe
Token ID464
Feature activation-1.07e+00

Pos logit contributions
Bad+0.023
rob+0.022
 narrative+0.022
 exploded+0.021
 bomb+0.020
Neg logit contributions
raid-0.028
reath-0.025
ears-0.024
she-0.023
 polish-0.023
Token people
Token ID661
Feature activation-1.98e+00

Pos logit contributions
rob+0.042
und+0.041
ishly+0.040
girls+0.040
illas+0.040
Neg logit contributions
 old-0.030
 special-0.024
 comfortable-0.023
 work-0.023
 new-0.023
Token room
Token ID2119
Feature activation+1.08e+00

Pos logit contributions
Bad+0.012
 narrative+0.011
 exploded+0.011
 bomb+0.011
Did+0.010
Neg logit contributions
raid-0.011
reath-0.010
ears-0.009
wn-0.009
she-0.009
Token to
Token ID284
Feature activation+2.01e-04

Pos logit contributions
raid+0.033
reath+0.027
ears+0.026
 polish+0.025
wn+0.025
Neg logit contributions
Bad-0.041
 narrative-0.037
 exploded-0.037
Did-0.037
rob-0.036
Token the
Token ID262
Feature activation-5.46e-01

Pos logit contributions
raid+0.000
reath+0.000
 polish+0.000
wn+0.000
ears+0.000
Neg logit contributions
Bad-0.000
 narrative-0.000
Did-0.000
 exploded-0.000
 bomb-0.000
Token other
Token ID584
Feature activation-2.09e+00

Pos logit contributions
Bad+0.020
 exploded+0.018
 narrative+0.018
Did+0.018
rob+0.018
Neg logit contributions
raid-0.018
reath-0.015
ears-0.014
 polish-0.014
wn-0.013
Token in
Token ID287
Feature activation-1.12e+00

Pos logit contributions
Bad+0.058
 narrative+0.051
 exploded+0.051
Did+0.049
 unison+0.049
Neg logit contributions
raid-0.084
reath-0.074
ears-0.070
wn-0.070
she-0.069
Token no
Token ID645
Feature activation-5.76e+00

Pos logit contributions
Bad+0.039
 exploded+0.035
 narrative+0.034
Did+0.034
 bomb+0.034
Neg logit contributions
raid-0.039
reath-0.034
ears-0.032
wn-0.030
she-0.030
Token time
Token ID640
Feature activation+6.76e-01

Pos logit contributions
Bad+0.158
 unison+0.148
 exploded+0.145
 narrative+0.139
 bomb+0.137
Neg logit contributions
raid-0.216
reath-0.209
ears-0.208
she-0.198
annah-0.185
Token.
Token ID13
Feature activation-4.84e-01

Pos logit contributions
raid+0.022
reath+0.018
ears+0.017
 polish+0.016
wn+0.016
Neg logit contributions
Bad-0.025
 exploded-0.023
 narrative-0.022
Did-0.022
 bomb-0.022
Token
Token ID198
Feature activation-8.60e-01

Pos logit contributions
Bad+0.015
Did+0.014
 narrative+0.014
 exploded+0.013
rob+0.013
Neg logit contributions
raid-0.018
reath-0.016
ears-0.015
 polish-0.014
wn-0.014
Token
Token ID198
Feature activation-5.11e-01

Pos logit contributions
Bad+0.028
 exploded+0.026
 narrative+0.026
Did+0.025
rob+0.025
Neg logit contributions
raid-0.031
reath-0.026
ears-0.025
 polish-0.024
wn-0.024
TokenJust
Token ID5703
Feature activation+3.37e-01

Pos logit contributions
Bad+0.016
 exploded+0.015
 narrative+0.015
sed+0.015
rob+0.015
Neg logit contributions
raid-0.017
reath-0.015
she-0.015
wn-0.014
ears-0.014
Token,
Token ID11
Feature activation-1.56e-01

Pos logit contributions
Bad+0.040
 exploded+0.036
 narrative+0.036
Did+0.036
 bomb+0.035
Neg logit contributions
raid-0.038
reath-0.032
ears-0.031
 polish-0.029
wn-0.029
Token Mia
Token ID32189
Feature activation+1.79e+00

Pos logit contributions
Bad+0.006
rob+0.006
 narrative+0.006
 exploded+0.006
Did+0.006
Neg logit contributions
raid-0.004
reath-0.004
ears-0.003
 polish-0.003
she-0.003
Token.
Token ID13
Feature activation+2.51e-02

Pos logit contributions
raid+0.058
reath+0.049
ears+0.046
wn+0.044
 polish+0.043
Neg logit contributions
Bad-0.065
 exploded-0.060
 narrative-0.059
Did-0.058
 bomb-0.058
Token There
Token ID1318
Feature activation+1.05e-01

Pos logit contributions
raid+0.001
reath+0.001
ears+0.001
wn+0.001
 polish+0.001
Neg logit contributions
Bad-0.001
 exploded-0.001
 narrative-0.001
Did-0.001
 bomb-0.001
Token's
Token ID338
Feature activation-3.86e+00

Pos logit contributions
raid+0.004
reath+0.004
ears+0.004
wn+0.003
annah+0.003
Neg logit contributions
Bad-0.003
 exploded-0.003
 narrative-0.003
Did-0.002
 bomb-0.002
Token no
Token ID645
Feature activation-5.75e+00

Pos logit contributions
Bad+0.122
rob+0.117
 narrative+0.115
Did+0.114
 exploded+0.108
Neg logit contributions
raid-0.136
reath-0.115
 polish-0.114
ears-0.111
 attention-0.109
Token snake
Token ID17522
Feature activation-3.04e+00

Pos logit contributions
Bad+0.199
 exploded+0.183
 narrative+0.177
 bomb+0.176
Did+0.176
Neg logit contributions
raid-0.195
reath-0.166
ears-0.159
she-0.150
annah-0.150
Token in
Token ID287
Feature activation-4.19e-01

Pos logit contributions
Bad+0.108
 narrative+0.106
rob+0.103
 unison+0.098
Did+0.098
Neg logit contributions
raid-0.098
ears-0.080
reath-0.077
 polish-0.076
erry-0.071
Token the
Token ID262
Feature activation-1.00e+00

Pos logit contributions
Bad+0.016
 narrative+0.015
rob+0.015
Did+0.015
 exploded+0.015
Neg logit contributions
raid-0.012
 polish-0.010
reath-0.010
ears-0.009
 She-0.009
Token log
Token ID2604
Feature activation-8.63e-01

Pos logit contributions
Bad+0.030
 narrative+0.026
 exploded+0.026
 bomb+0.026
Did+0.025
Neg logit contributions
raid-0.041
reath-0.035
ears-0.034
she-0.033
annah-0.032
Token.
Token ID13
Feature activation-3.77e-01

Pos logit contributions
Bad+0.036
 narrative+0.034
rob+0.033
Did+0.033
 unison+0.032
Neg logit contributions
raid-0.023
ears-0.018
reath-0.017
 polish-0.017
 She-0.017
Token met
Token ID1138
Feature activation-3.44e-01

Pos logit contributions
raid+0.045
 polish+0.040
ears+0.037
up+0.036
erry+0.036
Neg logit contributions
Bad-0.060
rob-0.056
 narrative-0.055
 unison-0.054
 bomb-0.052
Token a
Token ID257
Feature activation-7.33e-03

Pos logit contributions
Bad+0.013
 narrative+0.013
storm+0.012
 exploded+0.012
rob+0.012
Neg logit contributions
raid-0.010
 She-0.008
 polish-0.008
reath-0.008
ears-0.008
Token little
Token ID1310
Feature activation+1.46e+00

Pos logit contributions
Bad+0.000
 bomb+0.000
 exploded+0.000
Did+0.000
 narrative+0.000
Neg logit contributions
raid-0.000
ears-0.000
reath-0.000
wn-0.000
annah-0.000
Token girl
Token ID2576
Feature activation+1.88e+00

Pos logit contributions
raid+0.059
reath+0.052
ears+0.050
wn+0.049
she+0.048
Neg logit contributions
Bad-0.042
 exploded-0.036
 bomb-0.036
Did-0.036
 narrative-0.035
Token named
Token ID3706
Feature activation+1.43e+00

Pos logit contributions
raid+0.093
reath+0.080
ears+0.078
 polish+0.078
 She+0.077
Neg logit contributions
Bad-0.038
 narrative-0.033
 exploded-0.033
rob-0.032
 bomb-0.031
Token Lily
Token ID20037
Feature activation+2.92e+00

Pos logit contributions
raid+0.055
reath+0.048
ears+0.045
wn+0.044
ingle+0.041
Neg logit contributions
Bad-0.045
boys-0.039
Did-0.038
 exploded-0.038
 narrative-0.037
Token.
Token ID13
Feature activation+2.55e-01

Pos logit contributions
raid+0.095
reath+0.081
ears+0.076
wn+0.073
 polish+0.071
Neg logit contributions
Bad-0.105
Did-0.096
 exploded-0.096
 narrative-0.095
rob-0.092
Token Lily
Token ID20037
Feature activation+1.41e+00

Pos logit contributions
raid+0.011
reath+0.010
wn+0.009
ears+0.009
umble+0.009
Neg logit contributions
Did-0.006
Bad-0.006
girls-0.005
Our-0.005
boys-0.005
Token was
Token ID373
Feature activation-4.36e-01

Pos logit contributions
raid+0.046
 She+0.041
 polish+0.040
ears+0.039
reath+0.038
Neg logit contributions
Bad-0.047
 narrative-0.045
 bomb-0.043
rob-0.043
Did-0.041
Token playing
Token ID2712
Feature activation+3.39e-01

Pos logit contributions
Bad+0.017
 narrative+0.016
 exploded+0.016
Did+0.016
rob+0.016
Neg logit contributions
raid-0.012
reath-0.010
ears-0.009
 polish-0.009
 She-0.009
Token near
Token ID1474
Feature activation-2.63e-01

Pos logit contributions
raid+0.007
 polish+0.007
reath+0.006
 She+0.006
 her+0.006
Neg logit contributions
 narrative-0.014
 exploded-0.014
Bad-0.014
 unison-0.014
 bomb-0.013
Token park
Token ID3952
Feature activation+1.25e+00

Pos logit contributions
Bad+0.018
 narrative+0.017
 exploded+0.017
rob+0.017
Did+0.017
Neg logit contributions
raid-0.015
reath-0.013
 polish-0.012
ears-0.012
 She-0.012
Token again
Token ID757
Feature activation-2.94e+00

Pos logit contributions
raid+0.032
 She+0.024
ears+0.023
reath+0.023
 she+0.022
Neg logit contributions
Bad-0.054
rob-0.050
 narrative-0.049
 exploded-0.049
 bomb-0.048
Token.
Token ID13
Feature activation+2.44e-01

Pos logit contributions
Bad+0.137
rob+0.131
 exploded+0.130
 narrative+0.129
sed+0.129
Neg logit contributions
raid-0.062
 polish-0.043
 She-0.043
 she-0.041
 comfortable-0.041
Token He
Token ID679
Feature activation-5.51e-01

Pos logit contributions
raid+0.006
 She+0.005
reath+0.005
ears+0.005
she+0.005
Neg logit contributions
Bad-0.010
 exploded-0.010
 narrative-0.009
rob-0.009
 bomb-0.009
Token hopes
Token ID7176
Feature activation+8.13e-01

Pos logit contributions
Bad+0.017
 exploded+0.016
 narrative+0.016
Did+0.015
rob+0.015
Neg logit contributions
raid-0.021
reath-0.018
wn-0.017
ears-0.017
annah-0.016
Token Sue
Token ID26089
Feature activation+2.35e+00

Pos logit contributions
raid+0.020
 attention+0.016
 she+0.016
 polish+0.016
 She+0.015
Neg logit contributions
Bad-0.035
rob-0.034
 narrative-0.033
Did-0.032
 unison-0.032
Token will
Token ID481
Feature activation+2.38e-01

Pos logit contributions
raid+0.098
reath+0.088
andel+0.086
wn+0.083
annah+0.082
Neg logit contributions
Bad-0.062
 exploded-0.056
boys-0.055
Did-0.054
girls-0.053
Token go
Token ID467
Feature activation+5.24e-01

Pos logit contributions
raid+0.007
reath+0.006
 polish+0.005
ears+0.005
wn+0.005
Neg logit contributions
Bad-0.009
 narrative-0.009
rob-0.009
 exploded-0.009
Did-0.009
Token on
Token ID319
Feature activation-1.85e+00

Pos logit contributions
raid+0.019
reath+0.016
ears+0.015
 polish+0.015
wn+0.015
Neg logit contributions
Bad-0.017
 exploded-0.016
 narrative-0.016
Did-0.015
 bomb-0.015
Token the
Token ID262
Feature activation-6.50e-01

Pos logit contributions
Bad+0.080
 narrative+0.079
 exploded+0.076
Did+0.075
sed+0.075
Neg logit contributions
raid-0.039
 her-0.036
 polish-0.034
 comfortable-0.033
 old-0.033
Token slide
Token ID10649
Feature activation-9.69e-01

Pos logit contributions
Bad+0.024
 narrative+0.024
Did+0.024
 unison+0.023
 exploded+0.023
Neg logit contributions
raid-0.017
 polish-0.015
reath-0.015
 old-0.015
 attention-0.014
Token,
Token ID11
Feature activation-2.77e-02

Pos logit contributions
raid+0.035
reath+0.033
wn+0.030
ears+0.030
umble+0.026
Neg logit contributions
Bad-0.038
 narrative-0.035
 exploded-0.034
Did-0.034
 no-0.033
Token the
Token ID262
Feature activation+7.75e-01

Pos logit contributions
Bad+0.001
Did+0.001
 narrative+0.001
Run+0.001
Our+0.001
Neg logit contributions
raid-0.001
reath-0.001
wn-0.001
ears-0.001
umble-0.000
Token old
Token ID1468
Feature activation+2.50e-01

Pos logit contributions
raid+0.025
reath+0.021
ears+0.020
wn+0.018
she+0.018
Neg logit contributions
Bad-0.029
 exploded-0.027
 narrative-0.027
Did-0.026
 bomb-0.026
Token anchor
Token ID18021
Feature activation-9.97e-01

Pos logit contributions
raid+0.008
reath+0.007
ears+0.007
wn+0.006
she+0.006
Neg logit contributions
Bad-0.009
 exploded-0.008
 narrative-0.008
 bomb-0.008
Did-0.008
Token showed
Token ID3751
Feature activation-2.17e-01

Pos logit contributions
Bad+0.033
 narrative+0.031
rob+0.029
Did+0.029
 unison+0.028
Neg logit contributions
raid-0.035
 polish-0.030
reath-0.028
ears-0.028
up-0.027
Token her
Token ID607
Feature activation+2.22e+00

Pos logit contributions
Bad+0.008
 exploded+0.007
 narrative+0.007
Our+0.007
 unison+0.007
Neg logit contributions
raid-0.006
reath-0.005
ears-0.005
wn-0.005
inters-0.004
Token how
Token ID703
Feature activation+1.44e+00

Pos logit contributions
raid+0.076
reath+0.066
ears+0.062
wn+0.060
annah+0.058
Neg logit contributions
Bad-0.076
 exploded-0.070
 narrative-0.068
 bomb-0.067
Did-0.067
Token to
Token ID284
Feature activation+9.03e-01

Pos logit contributions
reath+0.060
raid+0.058
andel+0.051
wn+0.050
annah+0.049
Neg logit contributions
Bad-0.037
Our-0.034
 no-0.034
Did-0.032
 sw-0.031
Token move
Token ID1445
Feature activation-4.84e-01

Pos logit contributions
raid+0.031
reath+0.026
 polish+0.025
ears+0.025
wn+0.024
Neg logit contributions
Bad-0.031
 narrative-0.028
 exploded-0.028
Did-0.028
rob-0.027
Token her
Token ID607
Feature activation+7.89e-01

Pos logit contributions
Bad+0.015
 exploded+0.013
 bomb+0.013
Did+0.013
 narrative+0.013
Neg logit contributions
raid-0.018
reath-0.016
ears-0.016
annah-0.015
wn-0.014
Token arms
Token ID5101
Feature activation+9.08e-01

Pos logit contributions
raid+0.028
reath+0.023
 polish+0.023
ears+0.022
 attention+0.021
Neg logit contributions
Bad-0.027
Did-0.025
 narrative-0.024
rob-0.024
 exploded-0.024
Token cut
Token ID2005
Feature activation-4.26e-01

Pos logit contributions
raid+0.009
reath+0.007
 polish+0.006
ears+0.006
wn+0.006
Neg logit contributions
Bad-0.016
 narrative-0.015
 exploded-0.015
Did-0.014
rob-0.014
Token the
Token ID262
Feature activation+5.49e-01

Pos logit contributions
Bad+0.013
 exploded+0.012
 bomb+0.012
 narrative+0.011
Did+0.011
Neg logit contributions
raid-0.016
reath-0.014
ears-0.014
wn-0.013
annah-0.013
Token vegetables
Token ID13701
Feature activation-4.30e-01

Pos logit contributions
raid+0.019
wn+0.015
old+0.014
ingle+0.014
reath+0.014
Neg logit contributions
Bad-0.018
 guns-0.017
 narrative-0.017
 exploded-0.017
 bomb-0.017
Token as
Token ID355
Feature activation+2.69e+00

Pos logit contributions
Bad+0.012
 exploded+0.011
 bomb+0.011
 narrative+0.010
 attacking+0.010
Neg logit contributions
raid-0.017
reath-0.016
ears-0.014
wn-0.014
annah-0.013
Token fast
Token ID3049
Feature activation+8.37e-02

Pos logit contributions
raid+0.088
reath+0.074
ears+0.070
 polish+0.066
wn+0.066
Neg logit contributions
Bad-0.098
 exploded-0.090
 narrative-0.089
Did-0.088
 bomb-0.087
Token as
Token ID355
Feature activation+3.57e+00

Pos logit contributions
raid+0.003
reath+0.002
ears+0.002
wn+0.002
umble+0.002
Neg logit contributions
Bad-0.003
 exploded-0.003
 bomb-0.003
Did-0.003
 attacking-0.003
Token he
Token ID339
Feature activation-9.26e-01

Pos logit contributions
raid+0.125
reath+0.107
ears+0.100
wn+0.096
 polish+0.094
Neg logit contributions
Bad-0.122
 exploded-0.112
 narrative-0.110
Did-0.110
 bomb-0.109
Token could
Token ID714
Feature activation+1.43e+00

Pos logit contributions
Bad+0.026
 exploded+0.024
Did+0.024
 narrative+0.022
 bomb+0.022
Neg logit contributions
raid-0.037
reath-0.034
ears-0.031
wn-0.030
annah-0.030
Token,
Token ID11
Feature activation-5.59e-01

Pos logit contributions
raid+0.050
reath+0.044
ears+0.041
wn+0.040
she+0.038
Neg logit contributions
Bad-0.046
 exploded-0.044
Did-0.042
 bomb-0.041
 narrative-0.041
Token but
Token ID475
Feature activation-7.30e-01

Pos logit contributions
Bad+0.018
 exploded+0.017
Did+0.016
 narrative+0.016
 bomb+0.016
Neg logit contributions
raid-0.020
reath-0.017
ears-0.016
wn-0.016
 polish-0.015
Token he
Token ID339
Feature activation-1.99e+00

Pos logit contributions
Bad+0.032
rob+0.031
 unison+0.030
 narrative+0.030
Did+0.030
Neg logit contributions
raid-0.017
 polish-0.013
she-0.013
 she-0.013
 She-0.013
Token girl
Token ID2576
Feature activation+1.70e+00

Pos logit contributions
raid+0.047
reath+0.040
ears+0.038
wn+0.037
she+0.036
Neg logit contributions
Bad-0.052
 exploded-0.046
 narrative-0.046
 bomb-0.046
Did-0.046
Token named
Token ID3706
Feature activation+1.44e+00

Pos logit contributions
raid+0.074
 polish+0.064
 She+0.063
 care+0.061
ears+0.060
Neg logit contributions
Bad-0.044
rob-0.040
 narrative-0.039
 exploded-0.037
 bomb-0.036
Token Sarah
Token ID10490
Feature activation+2.42e+00

Pos logit contributions
raid+0.052
reath+0.047
wn+0.042
ears+0.042
 polish+0.041
Neg logit contributions
Bad-0.045
 exploded-0.042
Did-0.040
 narrative-0.040
boys-0.039
Token wanted
Token ID2227
Feature activation+5.30e-01

Pos logit contributions
raid+0.089
reath+0.076
ears+0.073
 polish+0.070
wn+0.069
Neg logit contributions
Bad-0.078
 exploded-0.070
 narrative-0.070
Did-0.069
rob-0.068
Token to
Token ID284
Feature activation+1.32e+00

Pos logit contributions
raid+0.017
reath+0.016
ears+0.014
wn+0.014
ingle+0.014
Neg logit contributions
Bad-0.018
 exploded-0.017
 bomb-0.017
Did-0.017
 guns-0.016
Token dress
Token ID6576
Feature activation+2.31e+00

Pos logit contributions
raid+0.044
ears+0.042
reath+0.040
erry+0.038
wn+0.038
Neg logit contributions
 exploded-0.039
Bad-0.039
boys-0.037
Our-0.037
 bomb-0.037
Token up
Token ID510
Feature activation+5.99e-01

Pos logit contributions
raid+0.075
umble+0.066
reath+0.064
ears+0.062
wn+0.058
Neg logit contributions
Bad-0.071
boys-0.068
 exploded-0.067
 guns-0.066
 bomb-0.064
Token.
Token ID13
Feature activation-4.30e-01

Pos logit contributions
raid+0.023
reath+0.021
ears+0.020
wn+0.019
umble+0.018
Neg logit contributions
Bad-0.017
 narrative-0.015
Did-0.015
 exploded-0.015
 bomb-0.014
Token She
Token ID1375
Feature activation+1.93e+00

Pos logit contributions
Did+0.012
 no+0.011
tr+0.011
 were+0.011
 Mark+0.011
Neg logit contributions
reath-0.015
erry-0.013
raid-0.013
ears-0.012
 pollen-0.012
Token went
Token ID1816
Feature activation-2.78e-01

Pos logit contributions
raid+0.079
reath+0.073
ears+0.068
umble+0.066
 attention+0.065
Neg logit contributions
Bad-0.050
 exploded-0.050
Did-0.047
 bomb-0.043
rob-0.043
Token to
Token ID284
Feature activation-8.86e-01

Pos logit contributions
 attacking+0.007
 guns+0.007
 dodging+0.006
rob+0.006
glass+0.006
Neg logit contributions
raid-0.011
reath-0.010
umble-0.010
ears-0.010
ingle-0.009
Tokenmy
Token ID1820
Feature activation+1.27e-01

Pos logit contributions
Bad+0.016
 exploded+0.014
Did+0.014
rob+0.014
boys+0.014
Neg logit contributions
raid-0.011
reath-0.009
ears-0.008
wn-0.008
she-0.008
Token had
Token ID550
Feature activation-1.89e+00

Pos logit contributions
raid+0.005
reath+0.004
ears+0.004
 polish+0.004
she+0.004
Neg logit contributions
Bad-0.004
 narrative-0.003
 exploded-0.003
Did-0.003
 bomb-0.003
Token a
Token ID257
Feature activation-1.24e-01

Pos logit contributions
 narrative+0.079
Bad+0.075
rob+0.073
 unison+0.072
storm+0.070
Neg logit contributions
raid-0.044
 She-0.042
 comfortable-0.040
 her-0.039
 polish-0.039
Token toy
Token ID13373
Feature activation-1.10e+00

Pos logit contributions
Bad+0.005
 exploded+0.005
 narrative+0.005
 bomb+0.005
Did+0.005
Neg logit contributions
raid-0.003
reath-0.003
ears-0.003
she-0.002
wn-0.002
Token truck
Token ID7779
Feature activation-1.26e+00

Pos logit contributions
Bad+0.038
 narrative+0.036
Did+0.035
rob+0.035
 exploded+0.033
Neg logit contributions
raid-0.037
 polish-0.031
 She-0.031
reath-0.029
 she-0.029
Token that
Token ID326
Feature activation-6.36e-01

Pos logit contributions
Bad+0.037
 exploded+0.034
Did+0.033
 narrative+0.033
 bomb+0.032
Neg logit contributions
raid-0.048
reath-0.043
ears-0.040
wn-0.039
 polish-0.038
Token he
Token ID339
Feature activation-2.12e+00

Pos logit contributions
Bad+0.018
 exploded+0.017
Did+0.016
 bomb+0.016
rob+0.016
Neg logit contributions
raid-0.026
reath-0.023
ears-0.021
wn-0.021
andel-0.021
Token loved
Token ID6151
Feature activation+3.72e-01

Pos logit contributions
Bad+0.056
 exploded+0.051
Did+0.049
boys+0.046
Our+0.045
Neg logit contributions
raid-0.091
reath-0.080
ears-0.077
andel-0.074
 attention-0.074
Token to
Token ID284
Feature activation+1.62e+00

Pos logit contributions
raid+0.012
reath+0.010
ears+0.009
wn+0.009
annah+0.009
Neg logit contributions
Bad-0.014
Did-0.013
 exploded-0.013
 bomb-0.013
rob-0.012
Token play
Token ID711
Feature activation+1.84e+00

Pos logit contributions
raid+0.048
ears+0.040
reath+0.040
she+0.038
annah+0.037
Neg logit contributions
Bad-0.060
 exploded-0.056
rob-0.054
Did-0.054
 bomb-0.053
Token with
Token ID351
Feature activation+5.07e-02

Pos logit contributions
raid+0.041
 polish+0.035
reath+0.035
 She+0.034
she+0.033
Neg logit contributions
Bad-0.078
 narrative-0.078
 exploded-0.076
sed-0.074
 unison-0.072
Token making
Token ID1642
Feature activation+3.42e-01

Pos logit contributions
Bad+0.059
 exploded+0.053
 narrative+0.052
Did+0.052
 bomb+0.051
Neg logit contributions
raid-0.072
reath-0.062
ears-0.060
wn-0.057
 polish-0.057
Token the
Token ID262
Feature activation+4.45e-01

Pos logit contributions
raid+0.012
reath+0.011
ears+0.010
wn+0.010
 polish+0.010
Neg logit contributions
Bad-0.011
 exploded-0.010
 narrative-0.010
Did-0.010
 bomb-0.010
Token meal
Token ID9799
Feature activation-1.55e+00

Pos logit contributions
raid+0.013
reath+0.012
ears+0.011
 polish+0.011
 attention+0.010
Neg logit contributions
Bad-0.017
Did-0.015
 exploded-0.015
 narrative-0.015
rob-0.015
Token.
Token ID13
Feature activation-5.89e-01

Pos logit contributions
 exploded+0.048
Bad+0.047
 bomb+0.045
 narrative+0.045
boys+0.043
Neg logit contributions
raid-0.056
reath-0.048
ears-0.045
wn-0.043
annah-0.042
Token
Token ID198
Feature activation-8.19e-01

Pos logit contributions
Bad+0.020
 exploded+0.019
Did+0.019
Our+0.018
 narrative+0.018
Neg logit contributions
raid-0.021
reath-0.018
ears-0.016
wn-0.016
 polish-0.015
Token
Token ID198
Feature activation-4.57e-01

Pos logit contributions
Bad+0.029
 exploded+0.026
 narrative+0.026
Did+0.026
rob+0.025
Neg logit contributions
raid-0.028
reath-0.023
ears-0.022
 polish-0.021
wn-0.021
TokenWhen
Token ID2215
Feature activation+2.90e+00

Pos logit contributions
Bad+0.016
 exploded+0.015
 narrative+0.015
Did+0.015
rob+0.015
Neg logit contributions
raid-0.015
reath-0.013
ears-0.012
 polish-0.012
wn-0.011
Token they
Token ID484
Feature activation-2.12e+00

Pos logit contributions
raid+0.104
reath+0.088
ears+0.085
 polish+0.085
she+0.083
Neg logit contributions
Bad-0.093
 narrative-0.085
Did-0.084
rob-0.084
 exploded-0.083
Token sat
Token ID3332
Feature activation-3.66e-01

Pos logit contributions
Bad+0.069
rob+0.062
 narrative+0.062
 bomb+0.060
Did+0.059
Neg logit contributions
raid-0.075
reath-0.064
 polish-0.063
ears-0.062
she-0.060
Token down
Token ID866
Feature activation+1.69e+00

Pos logit contributions
Bad+0.015
 exploded+0.015
 narrative+0.014
Did+0.014
 unison+0.014
Neg logit contributions
raid-0.009
reath-0.008
ears-0.007
 polish-0.007
 She-0.007
Token to
Token ID284
Feature activation-4.57e-02

Pos logit contributions
raid+0.052
reath+0.043
ears+0.041
 polish+0.039
wn+0.039
Neg logit contributions
Bad-0.064
 exploded-0.059
 narrative-0.058
Did-0.058
rob-0.057
Token
Token ID198
Feature activation-9.10e-01

Pos logit contributions
Bad+0.030
 exploded+0.028
 narrative+0.028
 bomb+0.027
Did+0.027
Neg logit contributions
raid-0.020
reath-0.016
 She-0.015
ears-0.015
 polish-0.014
Token
Token ID198
Feature activation-5.06e-01

Pos logit contributions
Bad+0.038
 exploded+0.035
 narrative+0.035
 bomb+0.034
Did+0.034
Neg logit contributions
raid-0.024
reath-0.019
 She-0.019
ears-0.018
she-0.018
TokenOne
Token ID3198
Feature activation-9.92e-02

Pos logit contributions
Bad+0.020
 exploded+0.020
sed+0.019
 narrative+0.019
rob+0.019
Neg logit contributions
raid-0.012
 She-0.010
reath-0.010
 polish-0.010
she-0.010
Token day
Token ID1110
Feature activation-7.97e-01

Pos logit contributions
Bad+0.004
 exploded+0.003
 narrative+0.003
Did+0.003
 bomb+0.003
Neg logit contributions
raid-0.003
reath-0.003
ears-0.002
she-0.002
wn-0.002
Token,
Token ID11
Feature activation+1.93e-01

Pos logit contributions
 narrative+0.035
Bad+0.035
rob+0.033
Did+0.033
 exploded+0.032
Neg logit contributions
raid-0.019
 polish-0.014
 She-0.014
 care-0.013
ears-0.013
Token the
Token ID262
Feature activation+6.06e-01

Pos logit contributions
raid+0.004
 she+0.004
 She+0.003
 polish+0.003
 her+0.003
Neg logit contributions
 narrative-0.009
rob-0.008
 exploded-0.008
Bad-0.008
girls-0.008
Token bear
Token ID6842
Feature activation-1.33e+00

Pos logit contributions
raid+0.021
reath+0.018
ears+0.017
 polish+0.016
wn+0.016
Neg logit contributions
Bad-0.021
 exploded-0.019
 narrative-0.019
Did-0.019
rob-0.018
Token was
Token ID373
Feature activation-6.58e-01

Pos logit contributions
Bad+0.052
 narrative+0.050
rob+0.049
 unison+0.049
 bomb+0.047
Neg logit contributions
raid-0.037
up-0.031
 polish-0.031
 She-0.031
ears-0.030
Token walking
Token ID6155
Feature activation-2.08e-02

Pos logit contributions
Bad+0.023
 exploded+0.021
 narrative+0.021
Did+0.020
 bomb+0.020
Neg logit contributions
raid-0.022
reath-0.019
ears-0.018
 polish-0.017
wn-0.017
Token through
Token ID832
Feature activation-6.88e-01

Pos logit contributions
Bad+0.001
 exploded+0.001
 narrative+0.001
Did+0.001
rob+0.001
Neg logit contributions
raid-0.001
reath-0.001
ears-0.000
 polish-0.000
 She-0.000
Token the
Token ID262
Feature activation-5.38e-01

Pos logit contributions
 narrative+0.029
Bad+0.029
rob+0.027
 exploded+0.027
storm+0.026
Neg logit contributions
raid-0.016
 polish-0.013
 She-0.013
 old-0.012
 care-0.012
Token They
Token ID1119
Feature activation-4.89e-01

Pos logit contributions
raid+0.000
 She+0.000
reath+0.000
ears+0.000
she+0.000
Neg logit contributions
Bad-0.000
rob-0.000
 narrative-0.000
 exploded-0.000
Did-0.000
Token tried
Token ID3088
Feature activation+7.99e-01

Pos logit contributions
Bad+0.015
rob+0.015
 narrative+0.014
 bomb+0.013
storm+0.013
Neg logit contributions
raid-0.018
 polish-0.015
 She-0.015
ears-0.015
reath-0.015
Token to
Token ID284
Feature activation+3.40e-01

Pos logit contributions
raid+0.018
reath+0.013
ears+0.013
 polish+0.012
wn+0.012
Neg logit contributions
Bad-0.037
 narrative-0.034
 exploded-0.034
Did-0.034
rob-0.034
Token pull
Token ID2834
Feature activation-2.02e-01

Pos logit contributions
raid+0.009
reath+0.007
ears+0.006
 polish+0.006
wn+0.006
Neg logit contributions
Bad-0.015
 exploded-0.014
 narrative-0.014
Did-0.013
 bomb-0.013
Token it
Token ID340
Feature activation+2.04e-01

Pos logit contributions
Bad+0.008
rob+0.008
 narrative+0.008
 exploded+0.008
Did+0.007
Neg logit contributions
raid-0.006
reath-0.004
ears-0.004
 polish-0.004
she-0.004
Token,
Token ID11
Feature activation-9.64e-01

Pos logit contributions
raid+0.008
reath+0.008
ears+0.007
annah+0.007
wn+0.007
Neg logit contributions
 exploded-0.005
Bad-0.005
 bomb-0.005
 attacking-0.005
 no-0.005
Token push
Token ID4574
Feature activation-4.99e-01

Pos logit contributions
Bad+0.035
 narrative+0.033
rob+0.032
 exploded+0.032
Did+0.031
Neg logit contributions
raid-0.031
reath-0.025
ears-0.024
 polish-0.024
she-0.024
Token it
Token ID340
Feature activation-4.71e-02

Pos logit contributions
Bad+0.020
 narrative+0.019
 exploded+0.019
rob+0.019
Did+0.018
Neg logit contributions
raid-0.014
reath-0.011
ears-0.011
 polish-0.010
she-0.010
Token,
Token ID11
Feature activation-7.88e-01

Pos logit contributions
Bad+0.001
 exploded+0.001
 bomb+0.001
 attacking+0.001
 dodging+0.001
Neg logit contributions
raid-0.002
reath-0.002
ears-0.002
annah-0.002
wn-0.001
Token and
Token ID290
Feature activation-4.45e-01

Pos logit contributions
Bad+0.029
 narrative+0.027
rob+0.027
 exploded+0.027
 bomb+0.026
Neg logit contributions
raid-0.024
reath-0.020
 polish-0.019
ears-0.019
she-0.019
Token roll
Token ID4836
Feature activation+8.01e-01

Pos logit contributions
Bad+0.017
 narrative+0.016
rob+0.016
Did+0.015
 exploded+0.015
Neg logit contributions
raid-0.014
 polish-0.011
she-0.010
 She-0.010
wn-0.010
Token bed
Token ID3996
Feature activation-7.91e-01

Pos logit contributions
raid+0.005
reath+0.004
ears+0.003
 polish+0.003
annah+0.003
Neg logit contributions
Bad-0.006
 narrative-0.006
Did-0.006
rob-0.006
 exploded-0.005
Token.
Token ID13
Feature activation-3.59e-02

Pos logit contributions
Bad+0.033
Did+0.030
 narrative+0.030
rob+0.029
 exploded+0.029
Neg logit contributions
raid-0.022
reath-0.017
ears-0.017
 She-0.016
annah-0.016
Token She
Token ID1375
Feature activation+1.64e+00

Pos logit contributions
Bad+0.002
Did+0.002
 narrative+0.001
 exploded+0.001
Our+0.001
Neg logit contributions
raid-0.001
reath-0.001
wn-0.001
ears-0.001
erry-0.001
Token threw
Token ID9617
Feature activation-2.33e+00

Pos logit contributions
raid+0.052
 polish+0.045
 She+0.042
she+0.041
up+0.040
Neg logit contributions
Bad-0.056
rob-0.056
 narrative-0.054
 bomb-0.052
girls-0.052
Token the
Token ID262
Feature activation+2.42e-01

Pos logit contributions
Bad+0.078
 exploded+0.070
Did+0.068
 bomb+0.067
 narrative+0.066
Neg logit contributions
raid-0.085
reath-0.076
ears-0.070
annah-0.066
umble-0.066
Token paper
Token ID3348
Feature activation-8.40e-03

Pos logit contributions
raid+0.007
reath+0.006
ears+0.006
 polish+0.005
wn+0.005
Neg logit contributions
Bad-0.009
 exploded-0.009
 narrative-0.008
Did-0.008
 bomb-0.008
Token in
Token ID287
Feature activation-1.24e+00

Pos logit contributions
Bad+0.000
 exploded+0.000
 bomb+0.000
 narrative+0.000
Did+0.000
Neg logit contributions
raid-0.000
reath-0.000
ears-0.000
wn-0.000
annah-0.000
Token the
Token ID262
Feature activation-8.70e-01

Pos logit contributions
Bad+0.046
 exploded+0.042
 narrative+0.042
Did+0.041
 bomb+0.040
Neg logit contributions
raid-0.040
reath-0.033
ears-0.032
 polish-0.030
wn-0.030
Token trash
Token ID13913
Feature activation-7.10e-01

Pos logit contributions
Bad+0.033
 exploded+0.031
 narrative+0.030
 bomb+0.030
Did+0.030
Neg logit contributions
raid-0.027
reath-0.022
ears-0.022
umble-0.020
she-0.020
Token and
Token ID290
Feature activation-9.52e-01

Pos logit contributions
Bad+0.026
 narrative+0.024
 exploded+0.024
Did+0.024
rob+0.024
Neg logit contributions
raid-0.022
reath-0.018
ears-0.018
 polish-0.017
she-0.016
Token yelled
Token ID22760
Feature activation-1.02e+00

Pos logit contributions
Bad+0.035
 narrative+0.034
rob+0.034
 unison+0.033
storm+0.032
Neg logit contributions
raid-0.028
 polish-0.024
 she-0.022
she-0.022
 her-0.022
Token stick
Token ID4859
Feature activation+1.85e+00

Pos logit contributions
raid+0.070
reath+0.059
 polish+0.055
ears+0.055
wn+0.054
Neg logit contributions
Bad-0.079
 narrative-0.073
Did-0.072
 exploded-0.071
rob-0.070
Token and
Token ID290
Feature activation+2.77e-01

Pos logit contributions
raid+0.068
reath+0.061
ears+0.057
wn+0.054
 polish+0.053
Neg logit contributions
Bad-0.057
 exploded-0.052
 bomb-0.051
 narrative-0.050
Did-0.050
Token pushed
Token ID7121
Feature activation-4.55e-01

Pos logit contributions
raid+0.009
 polish+0.007
reath+0.007
ears+0.007
wn+0.007
Neg logit contributions
Bad-0.010
 narrative-0.009
Did-0.009
rob-0.009
 exploded-0.009
Token the
Token ID262
Feature activation+9.05e-01

Pos logit contributions
Bad+0.015
 exploded+0.013
 bomb+0.013
 narrative+0.013
Did+0.012
Neg logit contributions
raid-0.017
reath-0.015
ears-0.014
wn-0.013
annah-0.012
Token mean
Token ID1612
Feature activation-1.88e+00

Pos logit contributions
raid+0.030
 polish+0.027
reath+0.027
 attention+0.025
 old+0.025
Neg logit contributions
Bad-0.029
 narrative-0.029
Did-0.028
rob-0.027
Our-0.025
Token pirate
Token ID25868
Feature activation-1.80e+00

Pos logit contributions
Bad+0.058
 exploded+0.052
 narrative+0.051
 bomb+0.051
Did+0.050
Neg logit contributions
raid-0.072
reath-0.062
ears-0.060
wn-0.057
she-0.057
Token away
Token ID1497
Feature activation-1.66e-01

Pos logit contributions
Bad+0.063
 exploded+0.058
 bomb+0.056
 narrative+0.056
Did+0.056
Neg logit contributions
raid-0.060
reath-0.051
ears-0.049
wn-0.045
she-0.045
Token.
Token ID13
Feature activation-3.40e-01

Pos logit contributions
Bad+0.007
 narrative+0.006
Did+0.006
rob+0.006
 exploded+0.006
Neg logit contributions
raid-0.005
reath-0.004
ears-0.004
 polish-0.004
wn-0.003
Token He
Token ID679
Feature activation-8.02e-01

Pos logit contributions
Bad+0.011
 unison+0.010
Did+0.010
 exploded+0.009
Run+0.009
Neg logit contributions
raid-0.013
reath-0.011
ears-0.011
wn-0.010
 polish-0.009
Token pushed
Token ID7121
Feature activation-6.93e-01

Pos logit contributions
 narrative+0.029
Bad+0.029
rob+0.027
Did+0.026
storm+0.025
Neg logit contributions
raid-0.024
 polish-0.021
 try-0.019
 care-0.019
 comfortable-0.019
Token them
Token ID606
Feature activation+4.08e-01

Pos logit contributions
Bad+0.024
 exploded+0.022
 narrative+0.022
Did+0.022
 bomb+0.021
Neg logit contributions
raid-0.023
reath-0.020
ears-0.019
 polish-0.018
wn-0.018
Token the
Token ID262
Feature activation+3.15e-01

Pos logit contributions
raid+0.081
reath+0.066
 polish+0.064
 She+0.062
she+0.062
Neg logit contributions
Bad-0.106
 narrative-0.098
Did-0.097
rob-0.097
 exploded-0.096
Token dragon
Token ID10441
Feature activation-4.12e+00

Pos logit contributions
raid+0.010
reath+0.009
 polish+0.009
ears+0.008
 old+0.008
Neg logit contributions
Bad-0.011
rob-0.010
Did-0.010
 narrative-0.010
 exploded-0.009
Token heard
Token ID2982
Feature activation-8.68e-01

Pos logit contributions
 narrative+0.147
Bad+0.147
rob+0.136
Did+0.132
 bomb+0.127
Neg logit contributions
raid-0.129
 polish-0.107
up-0.102
ears-0.100
 She-0.099
Token the
Token ID262
Feature activation+3.14e-01

Pos logit contributions
Bad+0.030
 narrative+0.028
 exploded+0.028
Did+0.027
rob+0.027
Neg logit contributions
raid-0.029
reath-0.025
ears-0.023
 polish-0.022
wn-0.022
Token giant
Token ID6175
Feature activation-2.03e+00

Pos logit contributions
raid+0.009
reath+0.008
 polish+0.008
 old+0.008
 attention+0.007
Neg logit contributions
Bad-0.011
rob-0.011
Did-0.011
 narrative-0.011
Our-0.010
Token roar
Token ID34532
Feature activation-2.42e+00

Pos logit contributions
Bad+0.065
 exploded+0.060
 narrative+0.057
Did+0.057
 bomb+0.056
Neg logit contributions
raid-0.074
reath-0.064
ears-0.061
wn-0.058
 polish-0.058
Token,
Token ID11
Feature activation-7.59e-01

Pos logit contributions
Bad+0.085
 narrative+0.078
Did+0.076
rob+0.076
 exploded+0.076
Neg logit contributions
raid-0.080
reath-0.067
ears-0.063
 polish-0.062
wn-0.061
Token he
Token ID339
Feature activation-1.84e+00

Pos logit contributions
Bad+0.030
 narrative+0.028
 exploded+0.028
Did+0.027
rob+0.027
Neg logit contributions
raid-0.021
reath-0.017
ears-0.016
 polish-0.016
she-0.016
Token didn
Token ID1422
Feature activation+9.92e-01

Pos logit contributions
Bad+0.061
 narrative+0.060
rob+0.057
 bomb+0.054
Did+0.053
Neg logit contributions
raid-0.062
 polish-0.051
reath-0.051
 She-0.050
ears-0.049
Token't
Token ID470
Feature activation-1.45e+00

Pos logit contributions
raid+0.041
reath+0.035
ears+0.034
wn+0.033
 polish+0.032
Neg logit contributions
Bad-0.028
 exploded-0.025
 narrative-0.024
Did-0.024
 bomb-0.024
Token get
Token ID651
Feature activation+2.57e+00

Pos logit contributions
Bad+0.055
 exploded+0.052
Did+0.049
 narrative+0.049
 bomb+0.048
Neg logit contributions
raid-0.042
ears-0.037
reath-0.035
annah-0.034
she-0.031
Token they
Token ID484
Feature activation-2.53e+00

Pos logit contributions
Bad+0.030
rob+0.030
 narrative+0.028
Did+0.027
 exploded+0.027
Neg logit contributions
raid-0.028
 she-0.023
 polish-0.023
 care-0.023
 attention-0.022
Token were
Token ID547
Feature activation-2.06e+00

Pos logit contributions
Bad+0.094
rob+0.083
 narrative+0.082
 bomb+0.082
Did+0.081
Neg logit contributions
raid-0.082
 polish-0.068
reath-0.067
ears-0.064
wn-0.063
Token always
Token ID1464
Feature activation+5.36e-01

Pos logit contributions
Bad+0.072
 exploded+0.066
 narrative+0.064
Did+0.064
 bomb+0.062
Neg logit contributions
raid-0.071
reath-0.060
ears-0.057
 polish-0.053
wn-0.053
Token happy
Token ID3772
Feature activation-3.71e-01

Pos logit contributions
raid+0.016
reath+0.013
ears+0.013
 polish+0.012
wn+0.012
Neg logit contributions
Bad-0.020
 narrative-0.019
 exploded-0.019
rob-0.019
 bomb-0.018
Token because
Token ID780
Feature activation+5.33e-01

Pos logit contributions
Bad+0.016
rob+0.015
 narrative+0.015
 exploded+0.015
Did+0.015
Neg logit contributions
raid-0.010
ears-0.007
 polish-0.007
 She-0.007
reath-0.007
Token they
Token ID484
Feature activation-1.96e+00

Pos logit contributions
raid+0.018
 she+0.016
 polish+0.016
 old+0.015
 She+0.015
Neg logit contributions
Bad-0.017
rob-0.017
 narrative-0.016
Did-0.016
 exploded-0.015
Token were
Token ID547
Feature activation-1.60e+00

Pos logit contributions
Bad+0.058
 narrative+0.052
 bomb+0.050
rob+0.050
Did+0.050
Neg logit contributions
raid-0.074
reath-0.064
 polish-0.064
 care-0.061
wn-0.061
Token having
Token ID1719
Feature activation-6.72e-01

Pos logit contributions
Bad+0.060
 narrative+0.056
 exploded+0.055
Did+0.055
rob+0.054
Neg logit contributions
raid-0.049
reath-0.041
ears-0.038
 polish-0.038
wn-0.038
Token fun
Token ID1257
Feature activation+1.00e-01

Pos logit contributions
Bad+0.026
 narrative+0.024
 exploded+0.024
rob+0.023
Did+0.023
Neg logit contributions
raid-0.019
reath-0.016
 polish-0.015
 care-0.015
 She-0.015
Token together
Token ID1978
Feature activation-1.34e+00

Pos logit contributions
raid+0.002
 polish+0.002
 care+0.002
ears+0.002
 she+0.002
Neg logit contributions
Bad-0.005
 exploded-0.004
 narrative-0.004
Did-0.004
sed-0.004
Token all
Token ID477
Feature activation+1.57e+00

Pos logit contributions
Bad+0.065
rob+0.060
 narrative+0.059
 exploded+0.059
Did+0.058
Neg logit contributions
raid-0.028
 polish-0.019
reath-0.018
ears-0.018
 care-0.018
Token made
Token ID925
Feature activation+2.73e-01

Pos logit contributions
Bad+0.028
 exploded+0.026
Did+0.025
boys+0.024
rob+0.024
Neg logit contributions
raid-0.029
reath-0.026
ears-0.024
wn-0.022
umble-0.022
Token a
Token ID257
Feature activation-6.69e-01

Pos logit contributions
raid+0.011
reath+0.010
ears+0.010
annah+0.009
wn+0.009
Neg logit contributions
Bad-0.007
 exploded-0.007
boys-0.006
 bomb-0.006
Our-0.006
Token sound
Token ID2128
Feature activation+7.44e-01

Pos logit contributions
Bad+0.026
 exploded+0.025
 bomb+0.024
 narrative+0.023
Did+0.023
Neg logit contributions
raid-0.020
reath-0.016
ears-0.016
wn-0.015
she-0.015
Token.
Token ID13
Feature activation-2.60e-01

Pos logit contributions
raid+0.025
reath+0.021
ears+0.021
annah+0.019
wn+0.019
Neg logit contributions
Bad-0.026
 exploded-0.024
Did-0.023
 bomb-0.023
 narrative-0.023
Token The
Token ID383
Feature activation-4.53e-01

Pos logit contributions
Bad+0.008
Did+0.007
 unison+0.007
Our+0.007
 exploded+0.007
Neg logit contributions
raid-0.010
reath-0.009
wn-0.008
ears-0.008
 attention-0.008
Token cat
Token ID3797
Feature activation-2.32e+00

Pos logit contributions
Bad+0.015
rob+0.015
 narrative+0.015
 exploded+0.014
Did+0.014
Neg logit contributions
raid-0.015
reath-0.012
 polish-0.012
ears-0.012
 old-0.012
Token smiled
Token ID13541
Feature activation-3.67e-01

Pos logit contributions
Bad+0.070
 narrative+0.066
rob+0.063
 bomb+0.062
Did+0.061
Neg logit contributions
raid-0.088
reath-0.073
ears-0.073
 polish-0.072
 She-0.070
Token and
Token ID290
Feature activation+1.24e+00

Pos logit contributions
Bad+0.011
 exploded+0.010
Did+0.010
 narrative+0.009
 bomb+0.009
Neg logit contributions
raid-0.014
reath-0.013
ears-0.012
wn-0.011
annah-0.011
Token lay
Token ID3830
Feature activation+1.86e+00

Pos logit contributions
raid+0.045
reath+0.038
ears+0.037
 polish+0.036
she+0.035
Neg logit contributions
Bad-0.040
 narrative-0.036
 exploded-0.036
Did-0.035
rob-0.035
Token down
Token ID866
Feature activation+2.30e+00

Pos logit contributions
raid+0.040
reath+0.030
ears+0.029
 polish+0.027
 She+0.027
Neg logit contributions
Bad-0.086
 narrative-0.082
 exploded-0.081
rob-0.079
 bomb-0.079
Token.
Token ID13
Feature activation-1.13e-01

Pos logit contributions
raid+0.095
reath+0.085
ears+0.080
wn+0.077
umble+0.075
Neg logit contributions
Bad-0.063
 exploded-0.058
Did-0.056
 narrative-0.056
 bomb-0.054
Token back
Token ID736
Feature activation-8.28e-01

Pos logit contributions
raid+0.037
reath+0.031
ears+0.029
wn+0.027
 polish+0.027
Neg logit contributions
Bad-0.044
 exploded-0.041
 narrative-0.040
Did-0.040
 bomb-0.039
Token again
Token ID757
Feature activation-3.37e+00

Pos logit contributions
Bad+0.032
 exploded+0.030
 narrative+0.030
Did+0.029
 bomb+0.029
Neg logit contributions
raid-0.025
reath-0.020
ears-0.019
 polish-0.018
wn-0.018
Token soon
Token ID2582
Feature activation-1.28e+00

Pos logit contributions
Bad+0.130
 exploded+0.120
 narrative+0.119
rob+0.117
 bomb+0.117
Neg logit contributions
raid-0.105
reath-0.082
 polish-0.079
 She-0.079
ears-0.078
Token.
Token ID13
Feature activation-4.11e-01

Pos logit contributions
Bad+0.041
 exploded+0.039
 narrative+0.037
Did+0.037
 bomb+0.036
Neg logit contributions
raid-0.044
reath-0.040
ears-0.037
wn-0.035
 polish-0.035
Token<|endoftext|>
Token ID50256
Feature activation-8.68e-01

Pos logit contributions
Bad+0.009
Our+0.009
Did+0.009
 exploded+0.008
 narrative+0.008
Neg logit contributions
raid-0.018
reath-0.016
wn-0.016
ears-0.015
 polish-0.014
TokenCharlie
Token ID37136
Feature activation-2.72e+00

Pos logit contributions
Bad+0.036
 narrative+0.033
 exploded+0.033
 bomb+0.033
Did+0.031
Neg logit contributions
raid-0.022
 She-0.018
reath-0.018
ears-0.018
 polish-0.017
Token loved
Token ID6151
Feature activation+6.36e-01

Pos logit contributions
Bad+0.066
 exploded+0.061
Did+0.059
boys+0.055
Our+0.053
Neg logit contributions
raid-0.121
reath-0.110
ears-0.104
wn-0.100
 attention-0.098
Token to
Token ID284
Feature activation+1.52e+00

Pos logit contributions
raid+0.021
reath+0.018
wn+0.016
ears+0.016
ingle+0.016
Neg logit contributions
Bad-0.023
Did-0.021
 exploded-0.020
 guns-0.020
boys-0.020
Token climb
Token ID12080
Feature activation+1.67e-01

Pos logit contributions
raid+0.052
ears+0.048
reath+0.045
wn+0.044
erry+0.042
Neg logit contributions
Bad-0.046
 unison-0.045
 exploded-0.043
Our-0.042
boys-0.042
Token.
Token ID13
Feature activation-3.69e-01

Pos logit contributions
raid+0.005
reath+0.004
ears+0.004
wn+0.004
 polish+0.004
Neg logit contributions
Bad-0.006
 exploded-0.006
 narrative-0.006
Did-0.005
rob-0.005
Token He
Token ID679
Feature activation-2.26e-01

Pos logit contributions
Did+0.008
 unison+0.008
Bad+0.008
Our+0.007
 tigers+0.007
Neg logit contributions
raid-0.015
reath-0.015
ears-0.014
up-0.014
erry-0.013
Token shine
Token ID18340
Feature activation+8.26e-01

Pos logit contributions
Bad+0.051
 exploded+0.047
 narrative+0.046
Did+0.046
 bomb+0.045
Neg logit contributions
raid-0.047
reath-0.041
ears-0.038
wn-0.036
 polish-0.036
Token through
Token ID832
Feature activation+1.45e-01

Pos logit contributions
raid+0.030
reath+0.025
ears+0.024
wn+0.023
 polish+0.023
Neg logit contributions
Bad-0.027
 exploded-0.025
 narrative-0.024
Did-0.024
 bomb-0.024
Token.
Token ID13
Feature activation-3.44e-01

Pos logit contributions
raid+0.003
 polish+0.003
 She+0.003
 her+0.002
 care+0.002
Neg logit contributions
rob-0.006
Bad-0.006
 narrative-0.006
sed-0.006
storm-0.006
Token The
Token ID383
Feature activation-6.82e-01

Pos logit contributions
Bad+0.012
 exploded+0.011
Did+0.010
 narrative+0.010
 bomb+0.010
Neg logit contributions
raid-0.012
reath-0.011
ears-0.010
wn-0.009
 polish-0.009
Token town
Token ID3240
Feature activation-1.19e+00

Pos logit contributions
Bad+0.024
 exploded+0.022
 narrative+0.021
 bomb+0.021
Did+0.021
Neg logit contributions
raid-0.024
ears-0.020
reath-0.020
wn-0.019
annah-0.018
Tokenspe
Token ID4125
Feature activation-5.84e+00

Pos logit contributions
Bad+0.034
 narrative+0.030
rob+0.030
Did+0.030
 exploded+0.029
Neg logit contributions
raid-0.048
reath-0.040
ears-0.040
 polish-0.039
she-0.038
Tokenople
Token ID643
Feature activation-1.53e+00

Pos logit contributions
Bad+0.162
 bomb+0.158
storm+0.158
Did+0.156
 narrative+0.154
Neg logit contributions
raid-0.235
ears-0.177
 polish-0.175
up-0.175
wn-0.173
Token were
Token ID547
Feature activation-1.37e+00

Pos logit contributions
Bad+0.047
 narrative+0.042
rob+0.042
 bomb+0.041
girls+0.039
Neg logit contributions
raid-0.058
 polish-0.051
reath-0.047
 care-0.047
she-0.046
Token very
Token ID845
Feature activation+5.68e-01

Pos logit contributions
Bad+0.054
 narrative+0.050
rob+0.050
Did+0.049
 exploded+0.049
Neg logit contributions
raid-0.039
reath-0.032
ears-0.030
 polish-0.030
wn-0.029
Token happy
Token ID3772
Feature activation+2.45e-01

Pos logit contributions
raid+0.018
reath+0.015
ears+0.014
wn+0.014
annah+0.013
Neg logit contributions
Bad-0.022
 exploded-0.020
Did-0.019
 narrative-0.019
 bomb-0.019
Token and
Token ID290
Feature activation+8.93e-01

Pos logit contributions
raid+0.007
 She+0.005
ears+0.005
 polish+0.005
 she+0.005
Neg logit contributions
Bad-0.010
 narrative-0.010
rob-0.010
 exploded-0.009
Did-0.009
Token so
Token ID523
Feature activation+1.78e+00

Pos logit contributions
Bad+0.012
 exploded+0.011
 bomb+0.010
Did+0.010
 attacking+0.010
Neg logit contributions
raid-0.017
reath-0.014
ears-0.014
wn-0.013
ingle-0.013
Token hungry
Token ID14720
Feature activation+5.14e-01

Pos logit contributions
raid+0.065
reath+0.053
wn+0.052
ears+0.048
ingle+0.046
Neg logit contributions
Bad-0.061
 exploded-0.055
Did-0.053
 narrative-0.051
 bomb-0.051
Token.
Token ID13
Feature activation-2.69e-01

Pos logit contributions
raid+0.020
reath+0.018
ears+0.016
wn+0.016
 polish+0.015
Neg logit contributions
Bad-0.015
 exploded-0.014
 bomb-0.013
Did-0.013
 narrative-0.013
Token There
Token ID1318
Feature activation+2.53e-01

Pos logit contributions
Bad+0.010
Did+0.009
 exploded+0.008
 narrative+0.008
 bomb+0.008
Neg logit contributions
raid-0.009
reath-0.008
ears-0.007
wn-0.007
 polish-0.007
Token's
Token ID338
Feature activation-3.57e+00

Pos logit contributions
raid+0.011
reath+0.010
ears+0.009
wn+0.009
annah+0.009
Neg logit contributions
Bad-0.006
 exploded-0.006
 narrative-0.006
boys-0.005
 bomb-0.005
Token no
Token ID645
Feature activation-5.68e+00

Pos logit contributions
Bad+0.110
rob+0.101
 narrative+0.101
Did+0.099
 exploded+0.099
Neg logit contributions
raid-0.129
reath-0.110
 polish-0.108
ears-0.108
 She-0.105
Token food
Token ID2057
Feature activation-1.77e+00

Pos logit contributions
Bad+0.202
 exploded+0.186
 bomb+0.180
 narrative+0.177
Did+0.174
Neg logit contributions
raid-0.179
reath-0.155
ears-0.149
she-0.145
annah-0.142
Token to
Token ID284
Feature activation+3.93e-01

Pos logit contributions
Bad+0.057
 exploded+0.052
 narrative+0.051
Did+0.050
 bomb+0.049
Neg logit contributions
raid-0.064
reath-0.055
ears-0.052
wn-0.050
 polish-0.050
Token chew
Token ID34722
Feature activation-5.23e-01

Pos logit contributions
raid+0.011
reath+0.009
ears+0.008
wn+0.008
 polish+0.008
Neg logit contributions
Bad-0.016
 exploded-0.015
 narrative-0.015
Did-0.015
 bomb-0.014
Token here
Token ID994
Feature activation+2.81e-01

Pos logit contributions
Bad+0.016
 exploded+0.015
 narrative+0.014
Did+0.014
 bomb+0.014
Neg logit contributions
raid-0.020
reath-0.017
ears-0.016
wn-0.015
 polish-0.015
Token and
Token ID290
Feature activation-3.78e-01

Pos logit contributions
raid+0.009
reath+0.008
ears+0.007
 polish+0.007
wn+0.007
Neg logit contributions
Bad-0.010
 exploded-0.009
 narrative-0.009
Did-0.009
rob-0.009
Token.
Token ID13
Feature activation-3.68e-01

Pos logit contributions
raid+0.004
reath+0.003
ears+0.003
wn+0.003
annah+0.003
Neg logit contributions
Bad-0.004
 exploded-0.004
 bomb-0.004
 narrative-0.003
Did-0.003
Token
Token ID198
Feature activation-8.04e-01

Pos logit contributions
Bad+0.013
 exploded+0.012
 narrative+0.012
Did+0.012
rob+0.011
Neg logit contributions
raid-0.012
reath-0.010
ears-0.010
 polish-0.009
wn-0.009
Token
Token ID198
Feature activation-5.25e-01

Pos logit contributions
Bad+0.030
 narrative+0.028
 exploded+0.028
Did+0.027
 bomb+0.027
Neg logit contributions
raid-0.024
reath-0.021
ears-0.020
she-0.019
 She-0.019
TokenThe
Token ID464
Feature activation-9.00e-01

Pos logit contributions
Bad+0.013
 exploded+0.012
 narrative+0.012
 bomb+0.012
rob+0.011
Neg logit contributions
raid-0.022
reath-0.019
ears-0.019
she-0.018
wn-0.018
Token town
Token ID3240
Feature activation-1.17e+00

Pos logit contributions
Bad+0.030
 narrative+0.028
 exploded+0.027
 bomb+0.026
Did+0.026
Neg logit contributions
raid-0.033
reath-0.027
ears-0.027
wn-0.026
she-0.025
Tokenspe
Token ID4125
Feature activation-5.73e+00

Pos logit contributions
Bad+0.037
rob+0.036
Did+0.033
 narrative+0.032
girls+0.031
Neg logit contributions
raid-0.042
up-0.034
 She-0.034
ears-0.034
 polish-0.034
Tokenople
Token ID643
Feature activation-1.45e+00

Pos logit contributions
storm+0.169
 bomb+0.166
Bad+0.166
Did+0.165
girls+0.160
Neg logit contributions
raid-0.219
up-0.167
ears-0.164
annah-0.160
 polish-0.156
Token were
Token ID547
Feature activation-1.49e+00

Pos logit contributions
Bad+0.048
rob+0.047
 bomb+0.043
 narrative+0.043
storm+0.042
Neg logit contributions
raid-0.049
 polish-0.044
 She-0.043
 care-0.042
 she-0.041
Token amazed
Token ID24562
Feature activation-2.00e+00

Pos logit contributions
rob+0.064
Bad+0.064
 narrative+0.061
Did+0.059
 bomb+0.058
Neg logit contributions
raid-0.035
 comfortable-0.027
 She-0.027
 polish-0.027
reath-0.027
Token by
Token ID416
Feature activation+1.26e+00

Pos logit contributions
Bad+0.074
 exploded+0.068
 narrative+0.068
Did+0.067
rob+0.066
Neg logit contributions
raid-0.064
reath-0.052
ears-0.050
 polish-0.048
wn-0.047
Token this
Token ID428
Feature activation+1.59e-01

Pos logit contributions
raid+0.029
 polish+0.025
 She+0.025
reath+0.024
 old+0.023
Neg logit contributions
Bad-0.051
rob-0.050
 narrative-0.049
 exploded-0.049
Did-0.049
Token arrived
Token ID5284
Feature activation-1.80e+00

Pos logit contributions
Bad+0.052
 narrative+0.048
 bomb+0.046
Did+0.046
 exploded+0.045
Neg logit contributions
raid-0.067
reath-0.056
ears-0.055
 polish-0.055
annah-0.053
Token to
Token ID284
Feature activation+1.33e-02

Pos logit contributions
Bad+0.055
 exploded+0.050
 narrative+0.050
Did+0.048
 bomb+0.048
Neg logit contributions
raid-0.068
reath-0.060
ears-0.055
wn-0.053
umble-0.052
Token his
Token ID465
Feature activation-2.05e+00

Pos logit contributions
raid+0.000
reath+0.000
ears+0.000
wn+0.000
 polish+0.000
Neg logit contributions
Bad-0.000
 exploded-0.000
 narrative-0.000
Did-0.000
 bomb-0.000
Token destination
Token ID10965
Feature activation-1.86e+00

Pos logit contributions
Bad+0.081
Did+0.075
 exploded+0.075
rob+0.074
 narrative+0.074
Neg logit contributions
raid-0.060
reath-0.049
 polish-0.046
ears-0.046
wn-0.043
Token in
Token ID287
Feature activation-9.70e-01

Pos logit contributions
Bad+0.061
 exploded+0.056
Did+0.055
 narrative+0.055
 bomb+0.054
Neg logit contributions
raid-0.066
reath-0.057
ears-0.054
wn-0.051
 polish-0.050
Token no
Token ID645
Feature activation-5.64e+00

Pos logit contributions
Bad+0.036
 exploded+0.033
 narrative+0.033
rob+0.032
Did+0.032
Neg logit contributions
raid-0.030
reath-0.024
 polish-0.024
ears-0.023
wn-0.023
Token time
Token ID640
Feature activation+5.97e-01

Pos logit contributions
Bad+0.196
 narrative+0.179
 exploded+0.179
 bomb+0.173
 unison+0.173
Neg logit contributions
raid-0.190
reath-0.165
ears-0.161
she-0.150
annah-0.143
Token.
Token ID13
Feature activation-4.15e-01

Pos logit contributions
raid+0.020
reath+0.016
ears+0.016
 polish+0.015
wn+0.015
Neg logit contributions
Bad-0.021
 exploded-0.020
 narrative-0.019
Did-0.019
rob-0.019
Token
Token ID220
Feature activation+1.26e+00

Pos logit contributions
Bad+0.014
Did+0.013
 narrative+0.012
 exploded+0.012
Our+0.012
Neg logit contributions
raid-0.015
reath-0.013
ears-0.012
wn-0.012
 polish-0.012
Token
Token ID198
Feature activation-8.40e-01

Pos logit contributions
raid+0.054
reath+0.048
ears+0.043
wn+0.043
 polish+0.042
Neg logit contributions
Bad-0.033
 exploded-0.029
Did-0.029
Our-0.029
rob-0.027
Token
Token ID198
Feature activation-5.27e-01

Pos logit contributions
Bad+0.027
 exploded+0.024
 narrative+0.024
Did+0.024
rob+0.023
Neg logit contributions
raid-0.031
reath-0.026
ears-0.025
 polish-0.024
wn-0.024
Token!
Token ID0
Feature activation-5.04e-01

Pos logit contributions
raid+0.020
reath+0.017
ears+0.016
 polish+0.015
wn+0.015
Neg logit contributions
Bad-0.025
 exploded-0.023
 narrative-0.023
Did-0.023
 bomb-0.022
Token
Token ID198
Feature activation-8.82e-01

Pos logit contributions
Bad+0.017
Did+0.016
Our+0.015
 exploded+0.015
 unison+0.014
Neg logit contributions
raid-0.018
reath-0.016
wn-0.014
ears-0.014
 polish-0.014
Token
Token ID198
Feature activation-5.24e-01

Pos logit contributions
Bad+0.027
Did+0.024
 exploded+0.023
 narrative+0.023
Our+0.022
Neg logit contributions
raid-0.035
reath-0.030
ears-0.028
wn-0.028
 polish-0.027
TokenThe
Token ID464
Feature activation-1.13e+00

Pos logit contributions
Bad+0.016
Did+0.014
 narrative+0.014
 exploded+0.014
 bomb+0.013
Neg logit contributions
raid-0.021
reath-0.018
ears-0.017
 polish-0.017
wn-0.017
Token town
Token ID3240
Feature activation-1.46e+00

Pos logit contributions
Bad+0.043
rob+0.040
Did+0.040
 exploded+0.039
 narrative+0.039
Neg logit contributions
raid-0.034
reath-0.028
 polish-0.027
ears-0.026
wn-0.025
Tokenspe
Token ID4125
Feature activation-5.67e+00

Pos logit contributions
Bad+0.047
rob+0.045
 narrative+0.043
Did+0.042
girls+0.040
Neg logit contributions
raid-0.053
ears-0.042
up-0.042
 polish-0.042
she-0.041
Tokenople
Token ID643
Feature activation-1.85e+00

Pos logit contributions
 bomb+0.174
Did+0.171
storm+0.168
Bad+0.165
girls+0.164
Neg logit contributions
raid-0.214
up-0.155
ingle-0.151
annah-0.151
ears-0.150
Token were
Token ID547
Feature activation-1.52e+00

Pos logit contributions
Bad+0.060
 narrative+0.058
rob+0.058
 bomb+0.055
girls+0.051
Neg logit contributions
raid-0.065
 polish-0.056
 care-0.053
 she-0.052
she-0.052
Token sad
Token ID6507
Feature activation-7.51e-01

Pos logit contributions
Bad+0.059
rob+0.057
 narrative+0.056
Did+0.055
 bomb+0.053
Neg logit contributions
raid-0.043
reath-0.035
ears-0.033
 polish-0.033
wn-0.033
Token and
Token ID290
Feature activation+4.99e-01

Pos logit contributions
Bad+0.028
 narrative+0.025
 exploded+0.025
Did+0.025
rob+0.025
Neg logit contributions
raid-0.024
reath-0.020
ears-0.019
 polish-0.018
 She-0.018
Token scared
Token ID12008
Feature activation-1.20e+00

Pos logit contributions
raid+0.015
 polish+0.012
 She+0.012
reath+0.012
she+0.012
Neg logit contributions
Bad-0.018
rob-0.017
 narrative-0.017
Did-0.016
 exploded-0.016