TOP ACTIVATIONS
MAX = 10.210

on his paw . They also gave him a delicious bowl
band - aid . They also praised Lily for being smart
band - aid . They also helped to wash the salt
they loved them . They also said they were proud of
they loved them . They also said they liked the movie
make them angry . They also told her that things are
and a kiss . They also give Sam a hug and
do it again . They also said they were sorry for
taped their books . They also put the par rot in
to bed early . They also said they had to be
clean the mess . They also tell them to ask before
mom and dad . They also say they love them .
away . They also do some chores . They
belong to us . They also told him that it 's
for the surprise . They also said they were sorry for
for his book . They also wanted to record more things
while they cleaned . They also learned to respect their toys
to the man . They also had to work hard to
five their friends . They also hug and high - five
kissed their dolls . They also hugged and kissed each other

MIN ACTIVATIONS
MIN = -14.066

it come out of the seaw eed and walk around the
started to pick up the seaw eed and put it in
he decided to remove the seaw eed from the water so
box and share the ch ocol ates . They are happy
beach was full of messy seaw eed . The girl tried
not like to share his cr ay ons with his sister
. Can we share the cr ay on ?"
He tries to grab the cr ay on from Mia 's
happy to see our big cuc umber ." Lily says .
It was hiding under a seaw eed . Lily said ,
still have to remove the cr ay on marks . White
brother accidentally knocked over the v ase and it broke into
started eating the delicious ch ocol ates . She was so
you want to borrow another cr ay on ?" Lily asks
him if he took her cr ay ons . He said
" Can I take these cr ay ons home ?" Her
you help me get the cr ay ons from the cabinet
'm trying to get the cr ay ons from the cabinet
a big box of ch ocol ates to share with the
He remembers he borrowed the cr ay on .

INTERVAL 4.141 - 10.210
CONTAINS 14.123%

they disagreed on something and they began to scatter in different
little boy and his mom and dad had a big celebration
Sunday was very proud and everyone praised him for being so
to her mom in tears and asked , why would you
Tim my and Sally . They loved to play together every

INTERVAL -1.928 - 4.141
CONTAINS 52.821%

you , too . You are good children . Now ,
to try . Lily took a bite and said , "
that even if he struggled , he could still do great
. One day , they play match in the
L ily 's mom heard her and smiled too . She

INTERVAL -7.997 - -1.928
CONTAINS 32.496%

butter around in the bowl . It became smoother and more
and it started to get long . When
radio to call them ." He took them by
back . One day , Sus ie wanted to
out of the window !" Tom was very scared

INTERVAL -14.066 - -7.997
CONTAINS 0.560%

about her sailing adventure . <|endoftext|> One day , Mrs .
he laughed and laughed . <|endoftext|> Once upon a time ,
when he needed it . <|endoftext|> One day , a boy
blue wings of the bird fl apping around . He had
crown and a swing . <|endoftext|> Once there was a boy
Token on
Token ID319
Feature activation+5.60e-01

Pos logit contributions
arl+0.045
ay+0.043
elly+0.042
ane+0.042
ute+0.041
Neg logit contributions
 put-0.036
 pretended-0.036
 never-0.035
 punished-0.034
 forgot-0.034
Token his
Token ID465
Feature activation-2.01e-01

Pos logit contributions
 put+0.005
 never+0.005
 pretended+0.004
 learned+0.004
 used+0.004
Neg logit contributions
arl-0.017
ay-0.017
elly-0.017
 Today-0.017
ane-0.017
Token paw
Token ID41827
Feature activation-3.62e+00

Pos logit contributions
arl+0.004
ay+0.004
ute+0.004
elly+0.004
 Today+0.004
Neg logit contributions
 pretended-0.003
 put-0.003
 never-0.003
 used-0.003
 made-0.003
Token.
Token ID13
Feature activation-2.72e+00

Pos logit contributions
arl+0.083
ay+0.079
elly+0.079
 Today+0.077
ane+0.076
Neg logit contributions
 put-0.062
 never-0.060
 pretended-0.059
 used-0.058
 learned-0.058
Token They
Token ID1119
Feature activation+8.71e+00

Pos logit contributions
arl+0.059
ane+0.057
ute+0.057
elly+0.056
ay+0.055
Neg logit contributions
 put-0.051
 pretended-0.048
 learned-0.048
 never-0.047
 used-0.046
Token also
Token ID635
Feature activation+1.02e+01

Pos logit contributions
 punished+0.075
 permission+0.074
eling+0.073
 supposed+0.073
 myself+0.071
Neg logit contributions
-0.181
ay-0.177
ane-0.170
ifying-0.170
arl-0.170
Token gave
Token ID2921
Feature activation+1.62e+00

Pos logit contributions
 himself+0.063
 never+0.063
 herself+0.058
ck+0.057
ts+0.057
Neg logit contributions
arl-0.230
-0.223
elly-0.220
ay-0.218
ute-0.209
Token him
Token ID683
Feature activation-3.88e-01

Pos logit contributions
 forgot+0.019
 put+0.019
 pretended+0.019
 never+0.018
 learned+0.018
Neg logit contributions
ay-0.043
arl-0.040
ummy-0.040
elly-0.040
ore-0.039
Token a
Token ID257
Feature activation+5.90e-01

Pos logit contributions
ay+0.009
arl+0.009
elly+0.009
igsaw+0.009
aris+0.009
Neg logit contributions
 pretended-0.005
 forgot-0.005
 never-0.005
 put-0.005
 remembered-0.005
Token delicious
Token ID12625
Feature activation-3.66e+00

Pos logit contributions
 put+0.009
 never+0.009
 pretended+0.009
 used+0.009
 cleaned+0.008
Neg logit contributions
arl-0.014
elly-0.014
ay-0.014
ane-0.014
 Today-0.013
Token bowl
Token ID9396
Feature activation-5.59e+00

Pos logit contributions
arl+0.082
ay+0.080
elly+0.078
 Today+0.076
ute+0.075
Neg logit contributions
 put-0.062
 never-0.062
 pretended-0.061
 learned-0.059
 hoped-0.059
Token band
Token ID4097
Feature activation-3.84e+00

Pos logit contributions
 put+0.007
 cleaned+0.007
 used+0.006
 never+0.006
 made+0.006
Neg logit contributions
arl-0.012
elly-0.012
ane-0.012
ay-0.012
 Today-0.011
Token-
Token ID12
Feature activation-1.33e+00

Pos logit contributions
arl+0.066
ay+0.063
elly+0.062
ane+0.060
 Today+0.059
Neg logit contributions
 put-0.086
 never-0.084
 pretended-0.084
 used-0.082
 learned-0.082
Tokenaid
Token ID1698
Feature activation-4.42e+00

Pos logit contributions
arl+0.034
ay+0.033
elly+0.033
ane+0.032
ute+0.031
Neg logit contributions
 put-0.018
 pretended-0.018
 never-0.018
 forgot-0.017
 used-0.017
Token.
Token ID13
Feature activation-2.77e+00

Pos logit contributions
arl+0.106
elly+0.102
ay+0.102
 Today+0.101
+0.099
Neg logit contributions
 put-0.071
 never-0.068
 made-0.066
 used-0.065
 pretended-0.065
Token They
Token ID1119
Feature activation+9.18e+00

Pos logit contributions
ane+0.057
ute+0.056
arl+0.056
ay+0.056
owers+0.053
Neg logit contributions
 put-0.056
 learned-0.053
 never-0.053
 pretended-0.052
 hoped-0.052
Token also
Token ID635
Feature activation+1.02e+01

Pos logit contributions
 permission+0.087
 himself+0.081
 finding+0.080
wed+0.079
 supposed+0.078
Neg logit contributions
-0.199
ay-0.186
owers-0.184
ane-0.183
arl-0.183
Token praised
Token ID15342
Feature activation-3.85e-01

Pos logit contributions
 himself+0.082
 never+0.078
 pretended+0.075
 herself+0.072
 myself+0.072
Neg logit contributions
arl-0.220
-0.218
elly-0.212
ay-0.206
oms-0.200
Token Lily
Token ID20037
Feature activation-1.53e+00

Pos logit contributions
arl+0.011
ay+0.011
elly+0.010
 Today+0.010
ane+0.010
Neg logit contributions
 put-0.004
 never-0.004
 pretended-0.004
 used-0.004
 learned-0.004
Token for
Token ID329
Feature activation+2.53e+00

Pos logit contributions
arl+0.032
ay+0.032
elly+0.032
 Today+0.031
ane+0.030
Neg logit contributions
 put-0.027
 pretended-0.026
 never-0.026
 punished-0.026
 used-0.025
Token being
Token ID852
Feature activation+2.94e+00

Pos logit contributions
 pretended+0.037
 forgot+0.036
 hoped+0.032
 counted+0.031
 remembered+0.031
Neg logit contributions
arl-0.061
-0.053
apping-0.051
ummy-0.051
ay-0.050
Token smart
Token ID4451
Feature activation-3.75e+00

Pos logit contributions
 pretended+0.048
 forgot+0.045
 put+0.043
wed+0.042
 imagined+0.042
Neg logit contributions
arl-0.061
elly-0.060
apping-0.058
ay-0.058
over-0.056
Token band
Token ID4097
Feature activation-2.52e+00

Pos logit contributions
 put+0.009
 cleaned+0.008
 learned+0.008
 used+0.008
 made+0.008
Neg logit contributions
arl-0.017
elly-0.017
ay-0.017
ane-0.017
 Today-0.017
Token-
Token ID12
Feature activation-1.03e+00

Pos logit contributions
arl+0.048
ay+0.046
elly+0.045
ane+0.044
 Today+0.043
Neg logit contributions
 put-0.052
 never-0.051
 pretended-0.050
 used-0.049
 punished-0.049
Tokenaid
Token ID1698
Feature activation-3.86e+00

Pos logit contributions
arl+0.026
ay+0.025
elly+0.025
ane+0.024
ute+0.023
Neg logit contributions
 put-0.015
 pretended-0.015
 never-0.014
 forgot-0.014
 remembered-0.014
Token.
Token ID13
Feature activation-3.22e+00

Pos logit contributions
arl+0.091
ay+0.088
elly+0.087
 Today+0.086
ane+0.084
Neg logit contributions
 put-0.063
 never-0.060
 pretended-0.059
 made-0.058
 used-0.058
Token They
Token ID1119
Feature activation+8.51e+00

Pos logit contributions
ane+0.064
ay+0.063
ute+0.062
arl+0.062
owers+0.060
Neg logit contributions
 put-0.067
 learned-0.065
 pretended-0.064
 never-0.063
 hoped-0.063
Token also
Token ID635
Feature activation+1.01e+01

Pos logit contributions
eling+0.080
ck+0.080
 permission+0.079
 finding+0.077
 pretending+0.076
Neg logit contributions
-0.187
elly-0.171
owers-0.170
arl-0.169
uddle-0.168
Token helped
Token ID4193
Feature activation-2.97e-01

Pos logit contributions
 himself+0.072
 never+0.072
 myself+0.071
 supposed+0.068
eling+0.068
Neg logit contributions
elly-0.216
arl-0.215
-0.207
owers-0.196
ay-0.196
Token to
Token ID284
Feature activation+4.39e+00

Pos logit contributions
arl+0.008
ay+0.008
elly+0.007
 Today+0.007
ummy+0.007
Neg logit contributions
 never-0.004
 pretended-0.004
 hoped-0.003
 learned-0.003
 remembered-0.003
Token wash
Token ID13502
Feature activation-1.24e+00

Pos logit contributions
 pretended+0.049
 remembered+0.046
 hoped+0.044
 forgot+0.043
 learned+0.043
Neg logit contributions
arl-0.119
-0.110
ay-0.108
ute-0.107
 Today-0.104
Token the
Token ID262
Feature activation-2.20e+00

Pos logit contributions
arl+0.035
ay+0.034
elly+0.034
 Today+0.033
ute+0.033
Neg logit contributions
 put-0.014
 never-0.014
 pretended-0.013
 learned-0.013
 used-0.013
Token salt
Token ID8268
Feature activation-5.17e+00

Pos logit contributions
arl+0.051
elly+0.049
ay+0.048
ute+0.047
 Today+0.046
Neg logit contributions
 never-0.036
 pretended-0.036
 put-0.035
 hoped-0.034
 used-0.034
Token they
Token ID484
Feature activation+5.94e+00

Pos logit contributions
arl+0.024
ay+0.023
elly+0.023
ute+0.022
ane+0.022
Neg logit contributions
 put-0.012
 never-0.012
 learned-0.011
 made-0.011
 cleaned-0.011
Token loved
Token ID6151
Feature activation+7.07e-02

Pos logit contributions
ck+0.108
 forth+0.103
 punished+0.098
eling+0.096
 pretended+0.095
Neg logit contributions
owers-0.093
-0.092
ane-0.092
ay-0.090
elly-0.090
Token them
Token ID606
Feature activation-1.72e+00

Pos logit contributions
 pretended+0.001
 punished+0.001
 forgot+0.001
 put+0.001
 remembered+0.001
Neg logit contributions
arl-0.002
elly-0.002
ay-0.002
ummy-0.002
 Today-0.002
Token.
Token ID13
Feature activation-2.89e+00

Pos logit contributions
arl+0.040
ay+0.038
elly+0.038
 Today+0.037
ane+0.037
Neg logit contributions
 put-0.029
 pretended-0.027
 never-0.027
 used-0.027
 learned-0.026
Token They
Token ID1119
Feature activation+8.72e+00

Pos logit contributions
ane+0.062
anger+0.059
ay+0.059
ute+0.059
andel+0.059
Neg logit contributions
 put-0.056
 learned-0.055
 hoped-0.053
 made-0.052
 pretended-0.052
Token also
Token ID635
Feature activation+1.01e+01

Pos logit contributions
 permission+0.106
eling+0.105
ck+0.101
ts+0.100
 forth+0.095
Neg logit contributions
-0.166
owers-0.161
elly-0.160
ay-0.156
arry-0.155
Token said
Token ID531
Feature activation-2.53e-01

Pos logit contributions
eling+0.085
ts+0.084
 permission+0.081
 forth+0.080
ck+0.079
Neg logit contributions
arl-0.203
elly-0.203
-0.197
owers-0.191
arry-0.187
Token they
Token ID484
Feature activation+6.15e+00

Pos logit contributions
arl+0.007
ay+0.006
elly+0.006
 Today+0.006
ane+0.006
Neg logit contributions
 put-0.004
 never-0.004
 pretended-0.003
 learned-0.003
 made-0.003
Token were
Token ID547
Feature activation+3.35e+00

Pos logit contributions
ck+0.111
 forth+0.105
eling+0.102
 punished+0.097
 asking+0.096
Neg logit contributions
owers-0.099
ane-0.098
-0.095
ay-0.095
elly-0.094
Token proud
Token ID6613
Feature activation-1.46e+00

Pos logit contributions
 pretended+0.064
wed+0.063
 imagined+0.063
 forgot+0.060
 tried+0.060
Neg logit contributions
arl-0.062
ay-0.052
ummy-0.051
ute-0.049
owers-0.049
Token of
Token ID286
Feature activation+1.17e+00

Pos logit contributions
arl+0.021
elly+0.020
ay+0.019
 Today+0.018
ummy+0.018
Neg logit contributions
 put-0.037
 pretended-0.036
 never-0.036
 punished-0.036
 used-0.035
Token they
Token ID484
Feature activation+5.52e+00

Pos logit contributions
arl+0.011
elly+0.011
ay+0.011
 Today+0.010
ane+0.010
Neg logit contributions
 put-0.006
 never-0.006
 pretended-0.006
 learned-0.006
 made-0.006
Token loved
Token ID6151
Feature activation+1.85e-01

Pos logit contributions
ck+0.097
 pretended+0.088
 punished+0.086
 put+0.085
ts+0.080
Neg logit contributions
-0.102
ane-0.101
ay-0.101
 Today-0.099
elly-0.098
Token them
Token ID606
Feature activation-2.13e+00

Pos logit contributions
 pretended+0.002
 forgot+0.002
 punished+0.002
 put+0.002
 remembered+0.002
Neg logit contributions
arl-0.005
elly-0.005
ay-0.005
ummy-0.005
 Today-0.005
Token.
Token ID13
Feature activation-3.10e+00

Pos logit contributions
arl+0.050
ay+0.049
elly+0.048
 Today+0.047
ane+0.047
Neg logit contributions
 put-0.033
 pretended-0.032
 never-0.031
 used-0.031
 punished-0.031
Token They
Token ID1119
Feature activation+8.59e+00

Pos logit contributions
ane+0.067
ay+0.065
anger+0.065
ute+0.064
arl+0.064
Neg logit contributions
 put-0.058
 hoped-0.055
 learned-0.055
 never-0.055
 pretended-0.054
Token also
Token ID635
Feature activation+1.01e+01

Pos logit contributions
ck+0.107
ts+0.105
eling+0.098
 permission+0.097
ps+0.094
Neg logit contributions
-0.172
ay-0.168
elly-0.168
arl-0.165
arry-0.163
Token said
Token ID531
Feature activation-4.47e-01

Pos logit contributions
ck+0.097
ts+0.091
 forth+0.081
 permission+0.080
eling+0.078
Neg logit contributions
elly-0.220
arl-0.213
 Today-0.206
ay-0.198
-0.194
Token they
Token ID484
Feature activation+5.99e+00

Pos logit contributions
arl+0.011
ay+0.011
elly+0.011
 Today+0.011
ane+0.011
Neg logit contributions
 put-0.007
 never-0.006
 pretended-0.006
 learned-0.006
 made-0.006
Token liked
Token ID8288
Feature activation+8.88e-01

Pos logit contributions
ck+0.107
 punished+0.088
 forth+0.088
eling+0.088
ts+0.088
Neg logit contributions
ane-0.110
ay-0.109
elly-0.106
-0.105
owers-0.105
Token the
Token ID262
Feature activation-2.24e+00

Pos logit contributions
 pretended+0.015
 put+0.015
 punished+0.015
 forgot+0.015
 learned+0.015
Neg logit contributions
arl-0.019
elly-0.018
ay-0.018
ummy-0.018
 Today-0.018
Token movie
Token ID3807
Feature activation-5.62e+00

Pos logit contributions
arl+0.048
ay+0.046
elly+0.045
 Today+0.044
ane+0.044
Neg logit contributions
 put-0.042
 never-0.040
 pretended-0.040
 used-0.039
 learned-0.039
Token make
Token ID787
Feature activation-3.35e-01

Pos logit contributions
 pretended+0.063
 hoped+0.060
 learned+0.058
 cleaned+0.057
 put+0.057
Neg logit contributions
arl-0.124
elly-0.118
ay-0.116
 Today-0.114
ute-0.112
Token them
Token ID606
Feature activation-7.94e-02

Pos logit contributions
arl+0.008
ay+0.008
elly+0.008
ute+0.008
ane+0.008
Neg logit contributions
 pretended-0.005
 put-0.005
 never-0.005
 hoped-0.005
 learned-0.005
Token angry
Token ID7954
Feature activation-3.30e+00

Pos logit contributions
arl+0.002
ay+0.002
elly+0.002
ute+0.002
ane+0.002
Neg logit contributions
 pretended-0.001
 put-0.001
 never-0.001
 used-0.001
 hoped-0.001
Token.
Token ID13
Feature activation-3.16e+00

Pos logit contributions
arl+0.071
ay+0.068
elly+0.067
 Today+0.065
ane+0.065
Neg logit contributions
 put-0.061
 never-0.059
 pretended-0.058
 learned-0.057
 used-0.057
Token They
Token ID1119
Feature activation+8.78e+00

Pos logit contributions
arl+0.069
ane+0.068
ute+0.067
ay+0.066
owers+0.065
Neg logit contributions
 put-0.057
 learned-0.057
 never-0.056
 cleaned-0.054
 hoped-0.054
Token also
Token ID635
Feature activation+1.00e+01

Pos logit contributions
ts+0.102
eling+0.095
 pretended+0.093
 pretending+0.093
anut+0.090
Neg logit contributions
ay-0.182
ane-0.173
arry-0.166
arl-0.163
uttered-0.156
Token told
Token ID1297
Feature activation+1.09e+00

Pos logit contributions
ts+0.104
 pretended+0.092
 himself+0.082
 pretending+0.080
ck+0.076
Neg logit contributions
ay-0.218
arl-0.218
arry-0.212
ane-0.205
ute-0.202
Token her
Token ID607
Feature activation+1.27e+00

Pos logit contributions
 pretended+0.012
 used+0.012
 remembered+0.012
 put+0.012
 hoped+0.012
Neg logit contributions
arl-0.030
ay-0.028
elly-0.028
ummy-0.028
 Today-0.027
Token that
Token ID326
Feature activation+2.45e+00

Pos logit contributions
 pretended+0.020
 put+0.020
 used+0.019
 punished+0.019
 hoped+0.018
Neg logit contributions
arl-0.028
ay-0.027
elly-0.027
ane-0.027
ute-0.027
Token things
Token ID1243
Feature activation+1.76e+00

Pos logit contributions
 put+0.033
 pretended+0.032
 punished+0.031
 never+0.031
 learned+0.031
Neg logit contributions
arl-0.060
elly-0.060
ay-0.058
ane-0.058
 Today-0.058
Token are
Token ID389
Feature activation+2.59e+00

Pos logit contributions
 pretended+0.029
 put+0.027
 remembered+0.027
 hoped+0.026
 punished+0.026
Neg logit contributions
arl-0.038
ay-0.038
ane-0.036
elly-0.035
ute-0.035
Token and
Token ID290
Feature activation+7.22e+00

Pos logit contributions
arl+0.109
ay+0.104
elly+0.104
 Today+0.102
ane+0.101
Neg logit contributions
 put-0.075
 never-0.072
 pretended-0.071
 used-0.069
 learned-0.069
Token a
Token ID257
Feature activation+9.34e-01

Pos logit contributions
 never+0.101
 punished+0.099
 pretended+0.094
 forgot+0.094
wed+0.094
Neg logit contributions
arl-0.153
ay-0.153
 Today-0.148
elly-0.146
ute-0.144
Token kiss
Token ID9245
Feature activation-2.68e+00

Pos logit contributions
 put+0.012
 used+0.011
 cleaned+0.011
 pretended+0.011
 never+0.011
Neg logit contributions
arl-0.025
elly-0.025
ay-0.025
ane-0.024
 Today-0.024
Token.
Token ID13
Feature activation-3.05e+00

Pos logit contributions
arl+0.061
ay+0.059
elly+0.058
 Today+0.057
ane+0.057
Neg logit contributions
 put-0.046
 never-0.044
 pretended-0.044
 used-0.043
 learned-0.043
Token They
Token ID1119
Feature activation+8.56e+00

Pos logit contributions
ane+0.069
arl+0.067
ute+0.067
ay+0.065
elly+0.063
Neg logit contributions
 put-0.055
 learned-0.052
 hoped-0.052
 pretended-0.052
 never-0.052
Token also
Token ID635
Feature activation+1.00e+01

Pos logit contributions
 remembered+0.101
 never+0.099
 pretended+0.099
 punished+0.098
 tried+0.095
Neg logit contributions
arl-0.211
ay-0.201
 Today-0.195
-0.194
ane-0.193
Token give
Token ID1577
Feature activation+9.28e-01

Pos logit contributions
 never+0.101
 pretended+0.097
 forgot+0.097
 remembered+0.093
 tried+0.089
Neg logit contributions
arl-0.261
 Today-0.241
ay-0.239
ute-0.236
-0.234
Token Sam
Token ID3409
Feature activation-5.64e-01

Pos logit contributions
 punished+0.010
 pretended+0.010
 put+0.010
 never+0.010
 forgot+0.010
Neg logit contributions
ay-0.025
elly-0.024
arl-0.023
ummy-0.023
ore-0.023
Token a
Token ID257
Feature activation+6.38e-01

Pos logit contributions
elly+0.013
ay+0.013
arl+0.013
ane+0.013
 Today+0.012
Neg logit contributions
 pretended-0.007
 punished-0.007
 put-0.007
 forgot-0.007
 never-0.007
Token hug
Token ID16225
Feature activation-3.14e+00

Pos logit contributions
 put+0.008
 never+0.008
 used+0.008
 cleaned+0.008
 made+0.007
Neg logit contributions
arl-0.017
elly-0.017
ay-0.017
 Today-0.016
ane-0.016
Token and
Token ID290
Feature activation+7.09e+00

Pos logit contributions
arl+0.074
ay+0.070
elly+0.070
 Today+0.068
ane+0.068
Neg logit contributions
 put-0.052
 never-0.050
 pretended-0.049
 learned-0.048
 used-0.048
Token do
Token ID466
Feature activation+5.17e-01

Pos logit contributions
 pretended+0.052
 hoped+0.050
 put+0.049
 learned+0.048
 cleaned+0.047
Neg logit contributions
arl-0.123
ay-0.118
elly-0.117
 Today-0.117
ute-0.114
Token it
Token ID340
Feature activation-8.05e-01

Pos logit contributions
 pretended+0.008
 put+0.007
 cleaned+0.007
 hoped+0.007
 used+0.007
Neg logit contributions
arl-0.012
elly-0.011
ay-0.011
ane-0.011
ute-0.011
Token again
Token ID757
Feature activation-1.09e+00

Pos logit contributions
arl+0.018
ay+0.018
elly+0.017
ane+0.017
 Today+0.017
Neg logit contributions
 put-0.014
 never-0.013
 pretended-0.013
 learned-0.013
 used-0.013
Token.
Token ID13
Feature activation-3.00e+00

Pos logit contributions
arl+0.026
ay+0.025
elly+0.024
ane+0.024
 Today+0.024
Neg logit contributions
 put-0.018
 never-0.018
 pretended-0.017
 used-0.017
 learned-0.017
Token They
Token ID1119
Feature activation+8.51e+00

Pos logit contributions
ane+0.066
ute+0.066
andel+0.065
ay+0.065
owers+0.064
Neg logit contributions
 put-0.055
 never-0.054
 hoped-0.054
 learned-0.053
 pretended-0.051
Token also
Token ID635
Feature activation+1.00e+01

Pos logit contributions
eling+0.091
ts+0.088
 pretending+0.087
 supposed+0.083
ck+0.082
Neg logit contributions
-0.169
ay-0.165
olly-0.164
arl-0.162
ane-0.160
Token said
Token ID531
Feature activation-3.13e-01

Pos logit contributions
ts+0.086
 himself+0.084
eling+0.079
 pretending+0.077
 myself+0.076
Neg logit contributions
arl-0.202
elly-0.202
-0.197
ay-0.193
arry-0.191
Token they
Token ID484
Feature activation+6.08e+00

Pos logit contributions
arl+0.008
ay+0.008
elly+0.008
 Today+0.008
ane+0.008
Neg logit contributions
 put-0.004
 never-0.004
 pretended-0.004
 learned-0.004
 made-0.004
Token were
Token ID547
Feature activation+3.44e+00

Pos logit contributions
ck+0.103
 pretended+0.090
eling+0.090
 punished+0.089
ts+0.088
Neg logit contributions
ane-0.110
ay-0.109
-0.107
elly-0.106
owers-0.106
Token sorry
Token ID7926
Feature activation-1.53e+00

Pos logit contributions
 pretended+0.068
 imagined+0.066
wed+0.064
 forgot+0.063
 put+0.062
Neg logit contributions
arl-0.064
ay-0.052
ummy-0.051
apping-0.051
elly-0.051
Token for
Token ID329
Feature activation+1.40e+00

Pos logit contributions
arl+0.038
ay+0.036
elly+0.036
ane+0.035
 Today+0.035
Neg logit contributions
 put-0.024
 never-0.023
 pretended-0.023
 learned-0.022
 used-0.022
Token taped
Token ID36114
Feature activation-6.50e-01

Pos logit contributions
 yours+0.069
eling+0.067
 permission+0.067
ck+0.066
 myself+0.065
Neg logit contributions
-0.173
ane-0.162
owers-0.161
op-0.159
arl-0.158
Token their
Token ID511
Feature activation-1.33e-02

Pos logit contributions
arl+0.018
ay+0.017
elly+0.017
 Today+0.017
ane+0.017
Neg logit contributions
 put-0.008
 pretended-0.007
 never-0.007
 learned-0.007
 used-0.007
Token books
Token ID3835
Feature activation-4.95e+00

Pos logit contributions
arl+0.000
ay+0.000
elly+0.000
 Today+0.000
ane+0.000
Neg logit contributions
 put-0.000
 never-0.000
 pretended-0.000
 used-0.000
 learned-0.000
Token.
Token ID13
Feature activation-3.23e+00

Pos logit contributions
arl+0.120
elly+0.117
ay+0.113
 Today+0.112
arry+0.111
Neg logit contributions
 put-0.080
 never-0.078
 used-0.074
 made-0.074
 pretended-0.073
Token They
Token ID1119
Feature activation+8.40e+00

Pos logit contributions
ane+0.073
ay+0.070
ute+0.068
arl+0.067
owers+0.066
Neg logit contributions
 put-0.060
 pretended-0.057
 never-0.056
 hoped-0.056
 learned-0.056
Token also
Token ID635
Feature activation+1.00e+01

Pos logit contributions
 permission+0.101
 yours+0.089
 asking+0.088
 finding+0.085
ck+0.083
Neg logit contributions
-0.173
he-0.159
owers-0.157
ane-0.155
ay-0.153
Token put
Token ID1234
Feature activation+2.03e+00

Pos logit contributions
 himself+0.078
 permission+0.067
ck+0.067
 sure+0.066
 myself+0.064
Neg logit contributions
arl-0.214
elly-0.210
-0.203
ay-0.199
oms-0.195
Token the
Token ID262
Feature activation-2.35e+00

Pos logit contributions
 forgot+0.027
 pretended+0.027
 put+0.027
 never+0.027
 remembered+0.026
Neg logit contributions
arl-0.051
ay-0.051
elly-0.047
ane-0.047
-0.047
Token par
Token ID1582
Feature activation-9.19e+00

Pos logit contributions
arl+0.056
ay+0.054
elly+0.053
 Today+0.052
ane+0.052
Neg logit contributions
 put-0.038
 never-0.037
 pretended-0.036
 learned-0.035
 used-0.035
Tokenrot
Token ID10599
Feature activation-2.89e+00

Pos logit contributions
arl+0.097
 Today+0.096
elly+0.094
ummy+0.080
+0.080
Neg logit contributions
 put-0.264
 never-0.262
 used-0.255
 pretended-0.254
 learned-0.254
Token in
Token ID287
Feature activation+1.65e+00

Pos logit contributions
arl+0.065
ay+0.063
elly+0.062
ane+0.062
ute+0.061
Neg logit contributions
 put-0.047
 never-0.046
 punished-0.045
 pretended-0.045
 learned-0.044
Token to
Token ID284
Feature activation+1.82e+00

Pos logit contributions
 pretended+0.006
 put+0.006
 never+0.006
 remembered+0.006
 hoped+0.006
Neg logit contributions
arl-0.007
ay-0.007
elly-0.006
ore-0.006
 Today-0.006
Token bed
Token ID3996
Feature activation-5.59e+00

Pos logit contributions
 pretended+0.022
 never+0.021
 remembered+0.021
 made+0.021
 hoped+0.021
Neg logit contributions
arl-0.049
 Today-0.046
ay-0.045
-0.045
elly-0.045
Token early
Token ID1903
Feature activation-3.44e+00

Pos logit contributions
arl+0.133
ay+0.131
elly+0.128
ane+0.126
 Today+0.126
Neg logit contributions
 put-0.094
 never-0.089
 punished-0.085
 learned-0.085
 pretended-0.085
Token.
Token ID13
Feature activation-2.45e+00

Pos logit contributions
arl+0.082
ay+0.079
elly+0.078
ane+0.076
arry+0.075
Neg logit contributions
 put-0.058
 never-0.055
 pretended-0.054
 used-0.053
 made-0.053
Token They
Token ID1119
Feature activation+9.00e+00

Pos logit contributions
ane+0.054
ay+0.053
ute+0.052
owers+0.052
anger+0.051
Neg logit contributions
 put-0.046
 learned-0.044
 hoped-0.044
 never-0.044
 pretended-0.042
Token also
Token ID635
Feature activation+9.98e+00

Pos logit contributions
ck+0.106
ts+0.105
ps+0.104
eling+0.102
 myself+0.101
Neg logit contributions
arl-0.173
-0.164
ay-0.162
arry-0.156
elly-0.154
Token said
Token ID531
Feature activation-3.71e-01

Pos logit contributions
 himself+0.090
ck+0.086
ts+0.085
 herself+0.081
 myself+0.080
Neg logit contributions
arl-0.220
elly-0.203
ay-0.186
oky-0.185
-0.184
Token they
Token ID484
Feature activation+6.12e+00

Pos logit contributions
arl+0.010
ay+0.010
elly+0.010
ute+0.009
ane+0.009
Neg logit contributions
 put-0.005
 never-0.005
 pretended-0.005
 learned-0.005
 made-0.005
Token had
Token ID550
Feature activation+3.26e+00

Pos logit contributions
ck+0.104
 pretended+0.089
eling+0.088
 forth+0.088
ts+0.086
Neg logit contributions
ay-0.113
ane-0.111
elly-0.109
-0.106
 Today-0.104
Token to
Token ID284
Feature activation+4.36e+00

Pos logit contributions
 pretended+0.063
ck+0.061
 put+0.060
 used+0.057
 hoped+0.057
Neg logit contributions
arl-0.059
elly-0.059
ay-0.057
 Today-0.054
ummy-0.053
Token be
Token ID307
Feature activation+2.81e+00

Pos logit contributions
 pretended+0.056
 hoped+0.052
 remembered+0.050
 used+0.050
 learned+0.049
Neg logit contributions
arl-0.116
ay-0.109
 Today-0.108
ute-0.105
-0.103
Token clean
Token ID3424
Feature activation-2.52e+00

Pos logit contributions
 pretended+0.013
 remembered+0.012
 never+0.012
 forgot+0.012
 hoped+0.012
Neg logit contributions
arl-0.016
ay-0.015
 Today-0.015
ute-0.015
elly-0.015
Token the
Token ID262
Feature activation-3.31e+00

Pos logit contributions
arl+0.060
ay+0.059
elly+0.059
 Today+0.057
ute+0.056
Neg logit contributions
 put-0.038
 never-0.038
 pretended-0.037
 learned-0.036
 used-0.036
Token mess
Token ID2085
Feature activation-4.77e+00

Pos logit contributions
arl+0.073
ay+0.070
elly+0.070
 Today+0.068
ute+0.067
Neg logit contributions
 put-0.058
 never-0.057
 pretended-0.057
 hoped-0.055
 used-0.055
Token.
Token ID13
Feature activation-2.71e+00

Pos logit contributions
arl+0.099
ay+0.095
elly+0.094
ane+0.090
 Today+0.090
Neg logit contributions
 put-0.088
 pretended-0.087
 never-0.086
 learned-0.084
 remembered-0.084
Token They
Token ID1119
Feature activation+8.91e+00

Pos logit contributions
ane+0.050
arl+0.050
ay+0.050
igsaw+0.049
+0.049
Neg logit contributions
 put-0.058
 pretended-0.055
 hoped-0.055
 made-0.055
 never-0.054
Token also
Token ID635
Feature activation+9.96e+00

Pos logit contributions
 pretended+0.095
 remembered+0.095
 able+0.092
ck+0.088
 imagined+0.088
Neg logit contributions
arl-0.222
ay-0.202
oms-0.189
-0.189
 Today-0.186
Token tell
Token ID1560
Feature activation+1.28e+00

Pos logit contributions
 pretended+0.096
 himself+0.087
ck+0.086
 never+0.083
 imagined+0.083
Neg logit contributions
arl-0.257
ay-0.225
oms-0.221
 Today-0.218
elly-0.215
Token them
Token ID606
Feature activation+6.22e-01

Pos logit contributions
 pretended+0.019
 put+0.019
 punished+0.019
 used+0.019
 never+0.018
Neg logit contributions
arl-0.031
elly-0.029
ay-0.029
 Today-0.028
andel-0.027
Token to
Token ID284
Feature activation+4.17e+00

Pos logit contributions
 pretended+0.011
 put+0.011
 punished+0.011
 used+0.010
 remembered+0.010
Neg logit contributions
arl-0.012
elly-0.012
ay-0.012
 Today-0.012
ane-0.012
Token ask
Token ID1265
Feature activation+5.60e-01

Pos logit contributions
 pretended+0.052
 remembered+0.046
 forgot+0.044
 hoped+0.044
 used+0.043
Neg logit contributions
arl-0.114
ay-0.104
ute-0.099
 Today-0.098
-0.097
Token before
Token ID878
Feature activation-3.89e-01

Pos logit contributions
 put+0.007
 pretended+0.007
 never+0.007
 punished+0.007
 used+0.007
Neg logit contributions
arl-0.014
elly-0.014
ay-0.014
 Today-0.013
ute-0.013
Token mom
Token ID1995
Feature activation-1.56e+00

Pos logit contributions
 punished+0.018
 pretended+0.018
 forgot+0.017
 managed+0.017
 remembered+0.017
Neg logit contributions
arl-0.030
ay-0.028
 Today-0.028
ummy-0.027
ute-0.027
Token and
Token ID290
Feature activation+5.41e+00

Pos logit contributions
arl+0.032
elly+0.030
ay+0.030
ane+0.029
 Today+0.029
Neg logit contributions
 pretended-0.029
 put-0.028
 never-0.028
 punished-0.028
 used-0.028
Token dad
Token ID9955
Feature activation+6.77e-01

Pos logit contributions
 pretended+0.104
ck+0.104
ts+0.097
eling+0.094
 never+0.093
Neg logit contributions
arl-0.104
elly-0.087
ay-0.084
ummy-0.083
apping-0.081
Token.
Token ID13
Feature activation-3.16e+00

Pos logit contributions
 pretended+0.013
 put+0.013
 punished+0.013
 used+0.013
 never+0.012
Neg logit contributions
arl-0.013
elly-0.012
ay-0.012
ane-0.012
 Today-0.012
Token They
Token ID1119
Feature activation+8.71e+00

Pos logit contributions
igsaw+0.069
ane+0.067
ay+0.065
+0.064
arl+0.064
Neg logit contributions
 put-0.060
 hoped-0.058
 never-0.057
 learned-0.057
 made-0.056
Token also
Token ID635
Feature activation+9.94e+00

Pos logit contributions
 pretended+0.105
ck+0.098
ts+0.098
 remembered+0.095
 imagined+0.093
Neg logit contributions
arl-0.211
ay-0.195
arry-0.186
 Today-0.185
-0.183
Token say
Token ID910
Feature activation-3.76e-01

Pos logit contributions
 pretended+0.105
 forgot+0.096
ck+0.095
ts+0.094
 never+0.091
Neg logit contributions
arl-0.246
ay-0.219
 Today-0.216
elly-0.207
arry-0.202
Token they
Token ID484
Feature activation+5.95e+00

Pos logit contributions
elly+0.010
arl+0.010
ay+0.010
 Today+0.010
arry+0.010
Neg logit contributions
 put-0.005
 never-0.005
 learned-0.005
 made-0.005
 pretended-0.005
Token love
Token ID1842
Feature activation-6.04e-01

Pos logit contributions
ck+0.096
 pretended+0.096
 put+0.086
 his+0.084
 imagined+0.084
Neg logit contributions
arl-0.118
ay-0.118
ane-0.113
elly-0.111
 Today-0.109
Token them
Token ID606
Feature activation-2.40e+00

Pos logit contributions
arl+0.015
elly+0.014
ay+0.014
ummy+0.014
 Today+0.013
Neg logit contributions
 punished-0.009
 pretended-0.009
 forgot-0.009
 remembered-0.008
 put-0.008
Token.
Token ID13
Feature activation-3.28e+00

Pos logit contributions
arl+0.055
ay+0.054
elly+0.053
 Today+0.052
ane+0.052
Neg logit contributions
 put-0.038
 pretended-0.037
 never-0.036
 punished-0.036
 used-0.035
Token away
Token ID1497
Feature activation-2.19e+00

Pos logit contributions
arl+0.026
ay+0.025
elly+0.024
 Today+0.024
ane+0.023
Neg logit contributions
 put-0.016
 never-0.016
 pretended-0.016
 learned-0.016
 hoped-0.016
Token.
Token ID13
Feature activation-2.85e+00

Pos logit contributions
arl+0.055
ay+0.053
ane+0.052
elly+0.052
ute+0.051
Neg logit contributions
 put-0.034
 never-0.032
 used-0.031
 made-0.031
 pretended-0.031
Token
Token ID198
Feature activation-3.82e+00

Pos logit contributions
ane+0.069
ute+0.066
opus+0.065
andel+0.065
ay+0.064
Neg logit contributions
 put-0.048
 never-0.045
 hoped-0.043
 cleaned-0.042
 learned-0.042
Token
Token ID198
Feature activation-2.72e+00

Pos logit contributions
arl+0.074
ane+0.074
owers+0.073
elly+0.072
umm+0.071
Neg logit contributions
 put-0.081
 never-0.079
 learned-0.076
 used-0.074
 cleaned-0.073
TokenThey
Token ID2990
Feature activation+8.22e+00

Pos logit contributions
arl+0.063
ay+0.061
elly+0.060
ane+0.060
 Today+0.059
Neg logit contributions
 put-0.047
 never-0.046
 learned-0.044
 used-0.043
 made-0.043
Token also
Token ID635
Feature activation+9.94e+00

Pos logit contributions
 remembered+0.099
 pretended+0.097
 punished+0.092
 hoped+0.090
 used+0.090
Neg logit contributions
arl-0.202
-0.188
ay-0.188
 Today-0.183
ute-0.173
Token do
Token ID466
Feature activation+1.94e+00

Pos logit contributions
 never+0.100
 pretended+0.099
ck+0.095
 stayed+0.094
 forgot+0.094
Neg logit contributions
arl-0.252
 Today-0.230
ay-0.226
-0.226
oms-0.219
Token some
Token ID617
Feature activation+8.96e-01

Pos logit contributions
 pretended+0.019
 remembered+0.017
 punished+0.017
 wished+0.016
 forgot+0.016
Neg logit contributions
arl-0.056
 Today-0.053
-0.052
ute-0.052
ay-0.052
Token chores
Token ID46173
Feature activation-3.75e+00

Pos logit contributions
 never+0.013
 pretended+0.013
 put+0.013
 hoped+0.012
 learned+0.012
Neg logit contributions
arl-0.022
ay-0.021
elly-0.021
 Today-0.021
-0.021
Token.
Token ID13
Feature activation-2.63e+00

Pos logit contributions
arl+0.085
ay+0.082
elly+0.081
ane+0.079
 Today+0.078
Neg logit contributions
 put-0.064
 pretended-0.062
 never-0.061
 learned-0.059
 punished-0.059
Token They
Token ID1119
Feature activation+8.33e+00

Pos logit contributions
ane+0.063
ute+0.060
arl+0.059
opus+0.059
ay+0.058
Neg logit contributions
 put-0.045
 never-0.041
 hoped-0.040
 cleaned-0.039
 pretended-0.039
Token belong
Token ID5594
Feature activation-9.67e-01

Pos logit contributions
 pretended+0.071
 hoped+0.067
 remembered+0.065
 learned+0.065
 punished+0.065
Neg logit contributions
arl-0.115
ay-0.110
 Today-0.105
arry-0.103
ute-0.103
Token to
Token ID284
Feature activation+1.50e+00

Pos logit contributions
arl+0.020
elly+0.020
ay+0.019
ane+0.019
 Today+0.018
Neg logit contributions
 put-0.018
 pretended-0.017
 never-0.017
 learned-0.016
 punished-0.016
Token us
Token ID514
Feature activation-4.08e-01

Pos logit contributions
 put+0.018
 never+0.017
 pretended+0.017
 used+0.016
 learned+0.016
Neg logit contributions
arl-0.042
ay-0.040
elly-0.040
 Today-0.039
ane-0.039
Token.
Token ID13
Feature activation-2.79e+00

Pos logit contributions
arl+0.009
ay+0.009
elly+0.009
ane+0.009
 Today+0.009
Neg logit contributions
 put-0.007
 never-0.007
 pretended-0.007
 used-0.007
 learned-0.007
Token They
Token ID1119
Feature activation+8.71e+00

Pos logit contributions
arl+0.057
ute+0.055
andel+0.054
ane+0.054
anger+0.054
Neg logit contributions
 never-0.055
 put-0.054
 learned-0.053
 pretended-0.051
 used-0.051
Token also
Token ID635
Feature activation+9.94e+00

Pos logit contributions
ts+0.086
 pretended+0.084
ck+0.080
wed+0.079
 tightened+0.077
Neg logit contributions
ane-0.190
ay-0.187
arry-0.184
 Today-0.183
arl-0.180
Token told
Token ID1297
Feature activation+1.18e+00

Pos logit contributions
ts+0.082
 pretended+0.081
ck+0.072
wed+0.062
 counted+0.061
Neg logit contributions
arl-0.250
 Today-0.239
arry-0.237
-0.233
ay-0.232
Token him
Token ID683
Feature activation+1.50e+00

Pos logit contributions
 put+0.013
 pretended+0.012
 used+0.012
 never+0.012
 hoped+0.012
Neg logit contributions
arl-0.033
ay-0.032
elly-0.031
 Today-0.031
ummy-0.031
Token that
Token ID326
Feature activation+3.01e+00

Pos logit contributions
 pretended+0.025
 put+0.025
 punished+0.024
 used+0.023
 cleaned+0.023
Neg logit contributions
arl-0.031
elly-0.030
ane-0.030
ay-0.030
 Today-0.030
Token it
Token ID340
Feature activation+3.43e+00

Pos logit contributions
 put+0.039
 pretended+0.038
 punished+0.037
 never+0.036
 learned+0.036
Neg logit contributions
arl-0.075
elly-0.074
ay-0.073
 Today-0.073
ane-0.073
Token's
Token ID338
Feature activation+2.66e+00

Pos logit contributions
 pretended+0.052
 put+0.051
ck+0.048
 hoped+0.047
 punished+0.047
Neg logit contributions
ane-0.075
elly-0.075
ay-0.074
 Today-0.073
arl-0.072
Token for
Token ID329
Feature activation+1.88e+00

Pos logit contributions
arl+0.054
elly+0.053
ay+0.053
ane+0.051
+0.051
Neg logit contributions
 put-0.030
 never-0.028
 pretended-0.027
 learned-0.027
 used-0.027
Token the
Token ID262
Feature activation-7.29e-01

Pos logit contributions
 forgot+0.030
 pretended+0.030
 imagined+0.026
 remembered+0.026
 counted+0.025
Neg logit contributions
arl-0.044
-0.037
ay-0.036
apping-0.036
uttering-0.035
Token surprise
Token ID5975
Feature activation-3.83e+00

Pos logit contributions
arl+0.017
ay+0.016
elly+0.016
ane+0.016
 Today+0.016
Neg logit contributions
 put-0.012
 never-0.012
 pretended-0.011
 used-0.011
 learned-0.011
Token.
Token ID13
Feature activation-3.17e+00

Pos logit contributions
ay+0.072
arl+0.071
elly+0.070
 Today+0.068
ane+0.068
Neg logit contributions
 put-0.074
 pretended-0.073
 punished-0.073
 never-0.072
 learned-0.071
Token They
Token ID1119
Feature activation+8.69e+00

Pos logit contributions
ay+0.068
andel+0.067
ane+0.067
anger+0.066
ute+0.066
Neg logit contributions
 put-0.059
 hoped-0.058
 never-0.058
 learned-0.055
 pretended-0.054
Token also
Token ID635
Feature activation+9.92e+00

Pos logit contributions
eling+0.086
ts+0.085
ck+0.082
 permission+0.081
wed+0.079
Neg logit contributions
-0.185
ay-0.178
arl-0.176
arry-0.173
ane-0.168
Token said
Token ID531
Feature activation-8.89e-01

Pos logit contributions
ts+0.074
eling+0.071
ck+0.071
 himself+0.069
 permission+0.065
Neg logit contributions
arl-0.214
elly-0.206
ay-0.205
-0.202
arry-0.198
Token they
Token ID484
Feature activation+5.89e+00

Pos logit contributions
arl+0.022
elly+0.022
ay+0.021
 Today+0.021
arry+0.021
Neg logit contributions
 put-0.014
 never-0.014
 learned-0.013
 made-0.013
 pretended-0.013
Token were
Token ID547
Feature activation+3.18e+00

Pos logit contributions
ck+0.108
 forth+0.097
eling+0.095
 punished+0.095
 asking+0.094
Neg logit contributions
ay-0.096
-0.094
owers-0.092
ane-0.092
elly-0.090
Token sorry
Token ID7926
Feature activation-1.71e+00

Pos logit contributions
 pretended+0.061
 imagined+0.059
wed+0.059
 forgot+0.057
 tried+0.056
Neg logit contributions
arl-0.059
ay-0.051
apping-0.049
ummy-0.049
ane-0.047
Token for
Token ID329
Feature activation+1.06e+00

Pos logit contributions
arl+0.042
ay+0.041
elly+0.041
ane+0.040
 Today+0.039
Neg logit contributions
 put-0.027
 never-0.026
 pretended-0.025
 learned-0.024
 used-0.024
Token for
Token ID329
Feature activation+1.86e+00

Pos logit contributions
arl+0.028
ay+0.028
elly+0.028
+0.027
ane+0.027
Neg logit contributions
 put-0.016
 never-0.015
 learned-0.014
 pretended-0.014
 used-0.014
Token his
Token ID465
Feature activation+9.26e-01

Pos logit contributions
 pretended+0.029
 forgot+0.028
 imagined+0.025
 remembered+0.025
 counted+0.024
Neg logit contributions
arl-0.045
-0.037
ay-0.036
apping-0.036
ore-0.036
Token book
Token ID1492
Feature activation-6.69e+00

Pos logit contributions
 put+0.014
 never+0.013
 pretended+0.013
 learned+0.013
 used+0.013
Neg logit contributions
arl-0.023
ay-0.022
elly-0.022
ane-0.022
 Today-0.022
Token.
Token ID13
Feature activation-2.85e+00

Pos logit contributions
arl+0.154
ay+0.148
elly+0.147
 Today+0.143
ane+0.142
Neg logit contributions
 put-0.114
 never-0.110
 pretended-0.107
 learned-0.106
 used-0.106
Token They
Token ID1119
Feature activation+8.65e+00

Pos logit contributions
ay+0.057
arl+0.056
ane+0.055
ute+0.054
andel+0.054
Neg logit contributions
 put-0.058
 never-0.057
 hoped-0.056
 learned-0.055
 pretended-0.055
Token also
Token ID635
Feature activation+9.91e+00

Pos logit contributions
ck+0.070
wed+0.068
eling+0.068
ts+0.068
 pretended+0.064
Neg logit contributions
-0.199
arl-0.198
arry-0.194
ay-0.188
ane-0.187
Token wanted
Token ID2227
Feature activation+1.50e+00

Pos logit contributions
ck+0.064
ts+0.063
 pretended+0.060
 sure+0.058
 herself+0.056
Neg logit contributions
arl-0.235
-0.223
arry-0.217
elly-0.217
ay-0.215
Token to
Token ID284
Feature activation+3.66e+00

Pos logit contributions
 pretended+0.030
 forgot+0.029
 put+0.029
 remembered+0.029
 punished+0.029
Neg logit contributions
arl-0.025
elly-0.025
ay-0.025
ummy-0.024
 Today-0.023
Token record
Token ID1700
Feature activation-2.05e+00

Pos logit contributions
 pretended+0.042
 remembered+0.039
 cleaned+0.039
 hoped+0.038
 punished+0.038
Neg logit contributions
arl-0.098
ay-0.095
-0.092
 Today-0.091
ute-0.091
Token more
Token ID517
Feature activation-2.21e+00

Pos logit contributions
arl+0.055
ay+0.054
elly+0.053
 Today+0.052
ane+0.052
Neg logit contributions
 put-0.025
 never-0.024
 pretended-0.024
 used-0.023
 punished-0.023
Token things
Token ID1243
Feature activation-2.19e+00

Pos logit contributions
arl+0.057
+0.054
elly+0.053
ay+0.053
ane+0.052
Neg logit contributions
 put-0.034
 pretended-0.031
 never-0.031
 learned-0.031
 made-0.031
Token while
Token ID981
Feature activation-4.07e-01

Pos logit contributions
 put+0.023
 never+0.022
 learned+0.021
 used+0.021
 pretended+0.021
Neg logit contributions
arl-0.047
ay-0.045
elly-0.045
ane-0.044
 Today-0.044
Token they
Token ID484
Feature activation+6.45e+00

Pos logit contributions
arl+0.010
ay+0.010
elly+0.010
 Today+0.009
ane+0.009
Neg logit contributions
 put-0.006
 never-0.006
 pretended-0.006
 learned-0.006
 used-0.006
Token cleaned
Token ID20750
Feature activation-3.26e-01

Pos logit contributions
 punished+0.053
ck+0.052
 never+0.052
 pretended+0.049
 wounds+0.049
Neg logit contributions
ay-0.171
-0.171
owers-0.161
arry-0.158
ane-0.156
Token.
Token ID13
Feature activation-2.72e+00

Pos logit contributions
arl+0.008
ay+0.008
elly+0.008
 Today+0.008
ane+0.008
Neg logit contributions
 put-0.005
 never-0.004
 pretended-0.004
 learned-0.004
 used-0.004
Token They
Token ID1119
Feature activation+8.60e+00

Pos logit contributions
arl+0.053
ane+0.051
ay+0.050
ute+0.050
owers+0.049
Neg logit contributions
 put-0.056
 never-0.055
 learned-0.054
 hoped-0.053
 used-0.052
Token also
Token ID635
Feature activation+9.91e+00

Pos logit contributions
ck+0.099
eling+0.093
 permission+0.092
 wounds+0.089
 asking+0.083
Neg logit contributions
-0.185
ay-0.181
ane-0.172
arry-0.168
owers-0.167
Token learned
Token ID4499
Feature activation+1.87e+00

Pos logit contributions
ck+0.092
eling+0.078
 himself+0.070
 forth+0.069
ts+0.068
Neg logit contributions
arl-0.218
ay-0.215
elly-0.210
-0.208
igsaw-0.193
Token to
Token ID284
Feature activation+4.80e+00

Pos logit contributions
 put+0.027
 never+0.026
 pretended+0.025
 learned+0.025
 used+0.025
Neg logit contributions
arl-0.048
ay-0.046
elly-0.046
 Today-0.045
ane-0.045
Token respect
Token ID2461
Feature activation-6.17e-01

Pos logit contributions
 pretended+0.060
 hoped+0.054
 forgot+0.053
 punished+0.052
 remembered+0.052
Neg logit contributions
arl-0.131
 Today-0.120
ay-0.120
arry-0.118
ute-0.116
Token their
Token ID511
Feature activation-8.92e-01

Pos logit contributions
arl+0.016
ay+0.016
elly+0.016
 Today+0.015
ute+0.015
Neg logit contributions
 pretended-0.007
 put-0.007
 never-0.007
 forgot-0.007
 punished-0.007
Token toys
Token ID14958
Feature activation-2.78e+00

Pos logit contributions
arl+0.022
ay+0.021
elly+0.021
 Today+0.020
ane+0.020
Neg logit contributions
 put-0.014
 never-0.013
 pretended-0.013
 used-0.013
 learned-0.013
Token to
Token ID284
Feature activation+1.50e+00

Pos logit contributions
arl+0.045
ay+0.042
elly+0.042
 Today+0.041
ane+0.041
Neg logit contributions
 put-0.035
 pretended-0.034
 never-0.033
 used-0.033
 learned-0.032
Token the
Token ID262
Feature activation-1.77e+00

Pos logit contributions
 pretended+0.018
 put+0.018
 used+0.017
 punished+0.017
 cleaned+0.017
Neg logit contributions
arl-0.040
ay-0.038
elly-0.037
 Today-0.037
ummy-0.036
Token man
Token ID582
Feature activation-2.20e+00

Pos logit contributions
arl+0.038
ay+0.036
elly+0.036
ane+0.035
 Today+0.035
Neg logit contributions
 put-0.033
 never-0.032
 pretended-0.031
 learned-0.031
 used-0.031
Token.
Token ID13
Feature activation-3.15e+00

Pos logit contributions
arl+0.049
ay+0.047
elly+0.047
 Today+0.046
ane+0.046
Neg logit contributions
 put-0.038
 pretended-0.036
 never-0.036
 used-0.035
 learned-0.035
Token They
Token ID1119
Feature activation+8.89e+00

Pos logit contributions
ay+0.063
ane+0.061
arl+0.061
ute+0.060
owers+0.060
Neg logit contributions
 never-0.065
 put-0.064
 hoped-0.062
 learned-0.062
 used-0.059
Token also
Token ID635
Feature activation+9.89e+00

Pos logit contributions
 myself+0.089
 pretending+0.084
 forth+0.083
 pretended+0.082
 yours+0.080
Neg logit contributions
arl-0.184
arry-0.166
-0.160
ay-0.159
ari-0.152
Token had
Token ID550
Feature activation+4.79e+00

Pos logit contributions
 pretended+0.082
 herself+0.079
 myself+0.078
 himself+0.075
 forth+0.075
Neg logit contributions
arl-0.214
elly-0.196
arry-0.189
ay-0.180
ore-0.178
Token to
Token ID284
Feature activation+5.11e+00

Pos logit contributions
 pretended+0.081
ck+0.075
 forgot+0.073
eling+0.072
 remember+0.071
Neg logit contributions
arl-0.089
ay-0.083
elly-0.081
aris-0.077
-0.076
Token work
Token ID670
Feature activation-1.78e+00

Pos logit contributions
 pretended+0.068
 forgot+0.062
 remembered+0.062
 hoped+0.061
 shared+0.057
Neg logit contributions
arl-0.136
ay-0.123
 Today-0.121
ute-0.120
arry-0.117
Token hard
Token ID1327
Feature activation-2.26e+00

Pos logit contributions
arl+0.043
ay+0.041
elly+0.041
 Today+0.040
ane+0.040
Neg logit contributions
 put-0.028
 never-0.027
 pretended-0.027
 learned-0.026
 used-0.026
Token to
Token ID284
Feature activation+3.47e+00

Pos logit contributions
arl+0.057
ay+0.055
elly+0.054
ute+0.053
ane+0.053
Neg logit contributions
 put-0.035
 never-0.033
 made-0.033
 used-0.032
 learned-0.032
Tokenfive
Token ID13261
Feature activation-3.22e-01

Pos logit contributions
arl+0.029
ay+0.027
elly+0.027
 Today+0.027
ane+0.026
Neg logit contributions
 put-0.028
 never-0.027
 pretended-0.027
 learned-0.027
 used-0.026
Token their
Token ID511
Feature activation-1.44e+00

Pos logit contributions
arl+0.008
ay+0.008
elly+0.008
ane+0.008
 Today+0.008
Neg logit contributions
 put-0.005
 never-0.004
 pretended-0.004
 used-0.004
 punished-0.004
Token friends
Token ID2460
Feature activation-2.28e-01

Pos logit contributions
arl+0.026
elly+0.025
ay+0.024
ane+0.024
 Today+0.024
Neg logit contributions
 put-0.032
 never-0.030
 pretended-0.030
 learned-0.030
 used-0.029
Token.
Token ID13
Feature activation-2.94e+00

Pos logit contributions
arl+0.005
ay+0.005
elly+0.005
ane+0.005
 Today+0.005
Neg logit contributions
 put-0.004
 never-0.004
 pretended-0.004
 used-0.004
 learned-0.004
Token They
Token ID1119
Feature activation+8.73e+00

Pos logit contributions
anger+0.068
ane+0.067
andel+0.066
ute+0.065
arl+0.065
Neg logit contributions
 learned-0.049
 put-0.048
 never-0.046
 hoped-0.046
 made-0.045
Token also
Token ID635
Feature activation+9.88e+00

Pos logit contributions
 punished+0.130
 cleaned+0.125
 pretended+0.121
 remembered+0.120
ck+0.118
Neg logit contributions
ay-0.188
arl-0.186
ane-0.181
-0.179
 Today-0.176
Token hug
Token ID16225
Feature activation-3.25e-01

Pos logit contributions
ck+0.120
 cleaned+0.119
 punished+0.117
 pretended+0.113
 never+0.109
Neg logit contributions
arl-0.226
ay-0.222
 Today-0.216
ane-0.214
-0.206
Token and
Token ID290
Feature activation+7.31e+00

Pos logit contributions
arl+0.011
elly+0.010
ay+0.010
ane+0.010
+0.010
Neg logit contributions
 put-0.003
 never-0.002
 pretended-0.002
 made-0.002
 learned-0.002
Token high
Token ID1029
Feature activation-3.95e+00

Pos logit contributions
 punished+0.093
 never+0.090
 pretended+0.089
 cleaned+0.088
 hoped+0.088
Neg logit contributions
arl-0.178
ay-0.173
 Today-0.167
-0.164
igsaw-0.163
Token-
Token ID12
Feature activation-1.62e+00

Pos logit contributions
arl+0.098
ay+0.092
+0.092
elly+0.091
 Today+0.090
Neg logit contributions
 put-0.063
 pretended-0.059
 made-0.058
 never-0.057
 used-0.056
Tokenfive
Token ID13261
Feature activation-4.91e-01

Pos logit contributions
arl+0.034
elly+0.032
ay+0.032
 Today+0.031
+0.030
Neg logit contributions
 put-0.031
 never-0.031
 pretended-0.030
 learned-0.030
 used-0.029
Token kissed
Token ID27946
Feature activation-1.63e+00

Pos logit contributions
 never+0.081
wed+0.076
ck+0.076
 punished+0.072
eling+0.070
Neg logit contributions
arl-0.149
elly-0.142
-0.140
ay-0.136
 Today-0.134
Token their
Token ID511
Feature activation-2.21e+00

Pos logit contributions
arl+0.047
elly+0.046
ay+0.045
ane+0.045
 Today+0.044
Neg logit contributions
 put-0.019
 never-0.018
 pretended-0.017
 learned-0.017
 made-0.017
Token dolls
Token ID36062
Feature activation-3.79e+00

Pos logit contributions
arl+0.055
ay+0.053
elly+0.051
 Today+0.051
ute+0.050
Neg logit contributions
 never-0.033
 put-0.033
 pretended-0.032
 used-0.031
 learned-0.031
Token.
Token ID13
Feature activation-3.55e+00

Pos logit contributions
arl+0.083
ay+0.079
elly+0.078
 Today+0.076
ane+0.076
Neg logit contributions
 put-0.066
 never-0.065
 pretended-0.064
 punished-0.063
 used-0.062
Token They
Token ID1119
Feature activation+8.41e+00

Pos logit contributions
ane+0.084
igsaw+0.080
ay+0.078
ute+0.077
andel+0.077
Neg logit contributions
 put-0.064
 pretended-0.060
 hoped-0.059
 made-0.058
 learned-0.057
Token also
Token ID635
Feature activation+9.88e+00

Pos logit contributions
 permission+0.100
ck+0.094
eling+0.094
 asking+0.089
 finding+0.089
Neg logit contributions
-0.172
owers-0.165
arl-0.161
elly-0.160
ay-0.156
Token hugged
Token ID41130
Feature activation-2.52e-01

Pos logit contributions
 permission+0.082
 himself+0.080
 never+0.079
ck+0.076
eling+0.075
Neg logit contributions
elly-0.207
arl-0.203
owers-0.194
-0.192
ay-0.188
Token and
Token ID290
Feature activation+6.74e+00

Pos logit contributions
arl+0.006
ay+0.006
elly+0.006
ane+0.006
 Today+0.006
Neg logit contributions
 put-0.004
 never-0.004
 pretended-0.004
 learned-0.003
 used-0.003
Token kissed
Token ID27946
Feature activation-1.75e+00

Pos logit contributions
 never+0.080
ck+0.072
wed+0.071
eling+0.070
 punished+0.070
Neg logit contributions
arl-0.149
elly-0.139
-0.139
ay-0.138
owers-0.133
Token each
Token ID1123
Feature activation+5.31e-01

Pos logit contributions
arl+0.049
ay+0.048
elly+0.048
 Today+0.046
ane+0.046
Neg logit contributions
 put-0.021
 never-0.020
 pretended-0.020
 learned-0.019
 used-0.019
Token other
Token ID584
Feature activation-3.03e+00

Pos logit contributions
 never+0.006
 pretended+0.006
 put+0.006
 punished+0.006
 forgot+0.006
Neg logit contributions
arl-0.014
ay-0.014
elly-0.014
 Today-0.014
ane-0.013
Token it
Token ID340
Feature activation+1.09e+00

Pos logit contributions
 put+0.024
 never+0.024
 pretended+0.024
 punished+0.023
 forgot+0.023
Neg logit contributions
arl-0.055
ay-0.054
elly-0.054
ane-0.053
ute-0.052
Token come
Token ID1282
Feature activation-1.92e-01

Pos logit contributions
 punished+0.017
 put+0.017
 pretended+0.016
 never+0.016
 learned+0.016
Neg logit contributions
arl-0.024
ay-0.024
 Today-0.024
elly-0.024
ane-0.023
Token out
Token ID503
Feature activation-2.42e+00

Pos logit contributions
arl+0.005
elly+0.005
+0.005
ay+0.005
igsaw+0.005
Neg logit contributions
 put-0.003
 never-0.003
 pretended-0.002
 used-0.002
 made-0.002
Token of
Token ID286
Feature activation+1.32e+00

Pos logit contributions
arl+0.050
elly+0.047
ay+0.047
ane+0.046
+0.046
Neg logit contributions
 put-0.049
 never-0.047
 pretended-0.046
 used-0.046
 made-0.046
Token the
Token ID262
Feature activation-2.78e+00

Pos logit contributions
 forgot+0.017
 punished+0.017
 pretended+0.016
 learned+0.016
 never+0.015
Neg logit contributions
arl-0.035
ay-0.033
 Today-0.032
-0.032
elly-0.032
Token seaw
Token ID32085
Feature activation-1.41e+01

Pos logit contributions
arl+0.072
ay+0.070
elly+0.069
ane+0.068
 Today+0.068
Neg logit contributions
 put-0.041
 never-0.037
 made-0.037
 pretended-0.037
 used-0.036
Tokeneed
Token ID2308
Feature activation-6.53e+00

Pos logit contributions
 Today+0.216
arl+0.209
ane+0.205
ay+0.200
owers+0.195
Neg logit contributions
 put-0.335
 never-0.306
 made-0.304
 learned-0.303
 used-0.302
Token and
Token ID290
Feature activation+6.43e+00

Pos logit contributions
arl+0.159
ay+0.152
elly+0.150
 Today+0.147
ane+0.145
Neg logit contributions
 put-0.106
 never-0.101
 pretended-0.099
 made-0.098
 used-0.097
Token walk
Token ID2513
Feature activation-2.83e+00

Pos logit contributions
 punished+0.083
wed+0.077
 never+0.075
 cleaned+0.073
 fixed+0.067
Neg logit contributions
 Today-0.130
arl-0.128
ore-0.125
ifying-0.124
oles-0.122
Token around
Token ID1088
Feature activation+8.02e-02

Pos logit contributions
arl+0.068
ay+0.065
elly+0.065
 Today+0.063
ane+0.063
Neg logit contributions
 put-0.047
 never-0.045
 pretended-0.044
 used-0.043
 made-0.043
Token the
Token ID262
Feature activation-2.63e+00

Pos logit contributions
 put+0.001
 never+0.001
 pretended+0.001
 used+0.001
 made+0.001
Neg logit contributions
arl-0.002
ay-0.002
elly-0.002
ane-0.002
 Today-0.002
Token started
Token ID2067
Feature activation+2.99e+00

Pos logit contributions
 remind+0.040
ts+0.036
 make+0.036
 pretended+0.036
 share+0.036
Neg logit contributions
elly-0.087
arry-0.087
ane-0.086
ay-0.086
oles-0.085
Token to
Token ID284
Feature activation+4.69e+00

Pos logit contributions
 pretended+0.054
 put+0.054
 never+0.053
 learned+0.052
 punished+0.052
Neg logit contributions
arl-0.059
elly-0.057
 Today-0.056
ay-0.055
ute-0.054
Token pick
Token ID2298
Feature activation-7.06e-01

Pos logit contributions
 learned+0.066
 never+0.066
 shared+0.065
 pretended+0.065
wed+0.064
Neg logit contributions
 Today-0.102
arl-0.101
-0.096
arry-0.094
ute-0.093
Token up
Token ID510
Feature activation-5.45e-01

Pos logit contributions
arl+0.017
elly+0.017
ay+0.017
 Today+0.016
ane+0.016
Neg logit contributions
 never-0.011
 pretended-0.010
 put-0.010
 forgot-0.010
 punished-0.010
Token the
Token ID262
Feature activation-2.28e+00

Pos logit contributions
arl+0.016
elly+0.015
ay+0.015
 Today+0.015
+0.015
Neg logit contributions
 put-0.005
 never-0.005
 pretended-0.005
 punished-0.005
 learned-0.005
Token seaw
Token ID32085
Feature activation-1.38e+01

Pos logit contributions
arl+0.052
elly+0.050
ay+0.049
ute+0.048
 Today+0.047
Neg logit contributions
 never-0.038
 punished-0.037
 learned-0.036
 put-0.036
 hoped-0.036
Tokeneed
Token ID2308
Feature activation-6.05e+00

Pos logit contributions
 Today+0.202
arl+0.197
ane+0.192
ay+0.187
+0.182
Neg logit contributions
 put-0.342
 pretended-0.313
 used-0.313
 made-0.312
 never-0.310
Token and
Token ID290
Feature activation+6.61e+00

Pos logit contributions
arl+0.141
ay+0.135
elly+0.134
 Today+0.131
ane+0.130
Neg logit contributions
 put-0.101
 never-0.097
 pretended-0.096
 used-0.094
 learned-0.093
Token put
Token ID1234
Feature activation+1.73e+00

Pos logit contributions
wed+0.063
 punished+0.063
 never+0.059
 learned+0.056
ck+0.056
Neg logit contributions
 Today-0.148
-0.145
ute-0.142
ore-0.142
uddle-0.141
Token it
Token ID340
Feature activation+3.40e-01

Pos logit contributions
 forgot+0.027
 punished+0.026
 pretended+0.025
 never+0.025
 remembered+0.024
Neg logit contributions
ay-0.041
arl-0.039
-0.038
ore-0.037
anger-0.037
Token in
Token ID287
Feature activation+2.20e+00

Pos logit contributions
 pretended+0.006
 learned+0.006
 punished+0.006
 put+0.006
 forgot+0.006
Neg logit contributions
arl-0.007
ay-0.006
elly-0.006
ute-0.006
 Today-0.006
Token he
Token ID339
Feature activation+8.07e+00

Pos logit contributions
ay+0.018
 Today+0.018
arl+0.018
+0.018
elly+0.017
Neg logit contributions
 put-0.011
 punished-0.011
 never-0.011
 learned-0.011
 pretended-0.011
Token decided
Token ID3066
Feature activation+1.23e+00

Pos logit contributions
 herself+0.077
 remind+0.074
eling+0.074
 permission+0.071
 care+0.068
Neg logit contributions
ute-0.180
arry-0.178
elly-0.178
uddle-0.177
ay-0.171
Token to
Token ID284
Feature activation+4.58e+00

Pos logit contributions
 pretended+0.028
wed+0.026
ck+0.026
 put+0.026
 punished+0.026
Neg logit contributions
arl-0.017
elly-0.016
ane-0.016
ute-0.015
arry-0.015
Token remove
Token ID4781
Feature activation-6.28e-01

Pos logit contributions
 remembered+0.053
 pretended+0.053
 learned+0.052
 hoped+0.052
 forgot+0.050
Neg logit contributions
arl-0.119
ay-0.118
-0.114
 Today-0.113
ute-0.113
Token the
Token ID262
Feature activation-2.77e+00

Pos logit contributions
ay+0.016
arl+0.016
elly+0.016
ore+0.015
andel+0.015
Neg logit contributions
 forgot-0.008
 pretended-0.008
 never-0.008
 remembered-0.008
 punished-0.007
Token seaw
Token ID32085
Feature activation-1.38e+01

Pos logit contributions
arl+0.060
ay+0.059
elly+0.058
ute+0.056
ane+0.055
Neg logit contributions
 never-0.048
 punished-0.048
 pretended-0.047
 put-0.047
 shared-0.046
Tokeneed
Token ID2308
Feature activation-5.99e+00

Pos logit contributions
arl+0.183
 Today+0.175
ane+0.170
elly+0.169
ay+0.167
Neg logit contributions
 put-0.362
 pretended-0.338
 never-0.336
 made-0.335
 used-0.335
Token from
Token ID422
Feature activation+1.06e+00

Pos logit contributions
arl+0.130
ay+0.125
elly+0.124
ane+0.120
ute+0.120
Neg logit contributions
 put-0.105
 pretended-0.103
 never-0.103
 learned-0.101
 punished-0.100
Token the
Token ID262
Feature activation-2.45e+00

Pos logit contributions
 forgot+0.013
 learned+0.012
 punished+0.012
 remembered+0.012
 pretended+0.012
Neg logit contributions
arl-0.026
ay-0.025
-0.025
ore-0.025
 Today-0.025
Token water
Token ID1660
Feature activation-4.60e+00

Pos logit contributions
arl+0.053
ay+0.051
elly+0.050
ute+0.048
 Today+0.048
Neg logit contributions
 put-0.043
 pretended-0.043
 never-0.042
 punished-0.041
 used-0.041
Token so
Token ID523
Feature activation-3.23e-01

Pos logit contributions
arl+0.106
ay+0.102
elly+0.101
 Today+0.098
ane+0.098
Neg logit contributions
 put-0.078
 never-0.075
 pretended-0.074
 used-0.072
 learned-0.072
Token box
Token ID3091
Feature activation-3.96e+00

Pos logit contributions
arl+0.064
elly+0.061
ay+0.061
ane+0.059
 Today+0.059
Neg logit contributions
 put-0.056
 never-0.053
 pretended-0.053
 used-0.052
 learned-0.052
Token and
Token ID290
Feature activation+7.44e+00

Pos logit contributions
arl+0.088
ay+0.086
elly+0.085
 Today+0.083
ane+0.082
Neg logit contributions
 put-0.068
 never-0.066
 pretended-0.066
 punished-0.065
 learned-0.064
Token share
Token ID2648
Feature activation+1.66e-01

Pos logit contributions
 punished+0.110
 never+0.108
wed+0.101
 learned+0.097
 remembered+0.097
Neg logit contributions
arl-0.155
 Today-0.155
oms-0.152
ay-0.151
-0.149
Token the
Token ID262
Feature activation-2.01e+00

Pos logit contributions
 punished+0.002
 never+0.002
 pretended+0.002
 forgot+0.002
 put+0.002
Neg logit contributions
arl-0.004
ay-0.004
elly-0.004
 Today-0.004
ane-0.004
Token ch
Token ID442
Feature activation-8.31e+00

Pos logit contributions
ay+0.040
arl+0.040
 Today+0.039
elly+0.037
ane+0.036
Neg logit contributions
 never-0.037
 punished-0.037
 put-0.036
 forgot-0.036
 pretended-0.035
Tokenocol
Token ID4668
Feature activation-1.34e+01

Pos logit contributions
arl+0.110
elly+0.102
ay+0.101
 Today+0.098
ane+0.097
Neg logit contributions
 put-0.221
 never-0.213
 pretended-0.212
 used-0.210
 learned-0.209
Tokenates
Token ID689
Feature activation-5.67e+00

Pos logit contributions
arl+0.278
 Today+0.267
elly+0.265
ay+0.262
+0.256
Neg logit contributions
 put-0.243
 never-0.238
 used-0.234
 pretended-0.232
 learned-0.229
Token.
Token ID13
Feature activation-3.39e+00

Pos logit contributions
arl+0.113
ay+0.111
elly+0.111
ane+0.107
 Today+0.106
Neg logit contributions
 put-0.106
 pretended-0.105
 never-0.104
 punished-0.104
 cleaned-0.102
Token They
Token ID1119
Feature activation+8.36e+00

Pos logit contributions
ane+0.083
ute+0.077
arl+0.077
igsaw+0.077
elly+0.076
Neg logit contributions
 put-0.063
 hoped-0.055
 learned-0.054
 used-0.054
 made-0.054
Token are
Token ID389
Feature activation+4.40e+00

Pos logit contributions
 punished+0.127
 remembered+0.113
wed+0.111
 cleaned+0.108
 promised+0.108
Neg logit contributions
-0.172
arl-0.171
ay-0.167
 Today-0.161
owers-0.158
Token happy
Token ID3772
Feature activation+6.61e-01

Pos logit contributions
wed+0.081
 punished+0.079
 tried+0.077
eling+0.076
 prayed+0.074
Neg logit contributions
ay-0.069
apping-0.069
arl-0.069
 Today-0.065
ummy-0.064
Token beach
Token ID10481
Feature activation-1.21e+00

Pos logit contributions
arl+0.032
ay+0.030
elly+0.030
 Today+0.029
ane+0.029
Neg logit contributions
 put-0.030
 never-0.029
 pretended-0.029
 used-0.028
 learned-0.028
Token was
Token ID373
Feature activation+3.15e+00

Pos logit contributions
elly+0.028
ay+0.028
ane+0.028
ummy+0.027
 Today+0.027
Neg logit contributions
 put-0.016
 pretended-0.016
 punished-0.015
ck-0.015
 never-0.015
Token full
Token ID1336
Feature activation-1.70e+00

Pos logit contributions
 pretended+0.048
ck+0.047
 hoped+0.046
 put+0.046
 learned+0.045
Neg logit contributions
arl-0.066
ay-0.066
elly-0.066
 Today-0.065
-0.063
Token of
Token ID286
Feature activation+1.11e+00

Pos logit contributions
arl+0.031
ay+0.028
ane+0.028
elly+0.028
ute+0.028
Neg logit contributions
 put-0.038
 never-0.036
 made-0.036
 used-0.036
 cleaned-0.035
Token messy
Token ID24097
Feature activation-3.70e+00

Pos logit contributions
 never+0.019
 pretended+0.019
 punished+0.019
 forgot+0.019
 remembered+0.018
Neg logit contributions
ay-0.022
arl-0.022
elly-0.022
ummy-0.021
 Today-0.021
Token seaw
Token ID32085
Feature activation-1.33e+01

Pos logit contributions
arl+0.086
ay+0.082
elly+0.082
 Today+0.079
ane+0.079
Neg logit contributions
 put-0.062
 never-0.060
 pretended-0.059
 learned-0.057
 used-0.057
Tokeneed
Token ID2308
Feature activation-6.35e+00

Pos logit contributions
 Today+0.204
arl+0.196
ane+0.189
elly+0.178
+0.175
Neg logit contributions
 put-0.322
 never-0.296
 made-0.294
 used-0.294
 pretended-0.292
Token.
Token ID13
Feature activation-4.00e+00

Pos logit contributions
arl+0.136
elly+0.132
ay+0.132
ane+0.127
 Today+0.126
Neg logit contributions
 put-0.113
 never-0.109
 pretended-0.109
 learned-0.107
 punished-0.107
Token The
Token ID383
Feature activation-1.82e+00

Pos logit contributions
arl+0.098
ute+0.093
ane+0.087
ower+0.085
elly+0.085
Neg logit contributions
 put-0.070
 learned-0.066
 tried-0.063
 used-0.063
 never-0.063
Token girl
Token ID2576
Feature activation+5.11e+00

Pos logit contributions
arl+0.033
ay+0.031
elly+0.031
 Today+0.030
ane+0.030
Neg logit contributions
 put-0.039
 never-0.038
 pretended-0.038
 used-0.037
 punished-0.037
Token tried
Token ID3088
Feature activation+7.28e-01

Pos logit contributions
 remind+0.070
ws+0.067
ck+0.064
 permission+0.064
 share+0.063
Neg logit contributions
uddle-0.100
op-0.100
elly-0.097
oles-0.096
ane-0.096
Token not
Token ID407
Feature activation+2.45e+00

Pos logit contributions
 cleaned+0.001
 pretended+0.001
 punished+0.001
 put+0.001
 hoped+0.001
Neg logit contributions
 Today-0.002
arl-0.002
ay-0.002
ute-0.002
elly-0.002
Token like
Token ID588
Feature activation+3.46e-01

Pos logit contributions
 pretended+0.030
 punished+0.029
 remembered+0.028
 saved+0.028
 hoped+0.028
Neg logit contributions
arl-0.062
ay-0.061
elly-0.060
 Today-0.060
ute-0.058
Token to
Token ID284
Feature activation+2.98e+00

Pos logit contributions
 put+0.005
 pretended+0.005
 never+0.005
 punished+0.005
 learned+0.005
Neg logit contributions
arl-0.008
ay-0.008
elly-0.008
ane-0.008
 Today-0.008
Token share
Token ID2648
Feature activation-1.54e+00

Pos logit contributions
 remembered+0.037
 hoped+0.037
 saved+0.036
 punished+0.035
 managed+0.035
Neg logit contributions
ay-0.073
arl-0.071
 Today-0.069
ute-0.067
igsaw-0.066
Token his
Token ID465
Feature activation-1.68e+00

Pos logit contributions
arl+0.038
ay+0.036
elly+0.036
 Today+0.035
ane+0.035
Neg logit contributions
 put-0.023
 never-0.023
 pretended-0.022
 learned-0.022
 used-0.022
Token cr
Token ID1067
Feature activation-1.32e+01

Pos logit contributions
arl+0.043
ay+0.042
elly+0.041
 Today+0.040
ane+0.040
Neg logit contributions
 put-0.024
 never-0.023
 pretended-0.022
 punished-0.022
 used-0.022
Tokenay
Token ID323
Feature activation-6.12e+00

Pos logit contributions
arl+0.063
elly+0.043
+0.041
 Today+0.039
arry+0.027
Neg logit contributions
 put-0.452
 never-0.444
 made-0.441
 used-0.434
 pretended-0.430
Tokenons
Token ID684
Feature activation-6.88e+00

Pos logit contributions
ay+0.146
arl+0.146
elly+0.140
ane+0.138
 Today+0.136
Neg logit contributions
 put-0.096
 never-0.093
 pretended-0.092
 punished-0.090
 hoped-0.089
Token with
Token ID351
Feature activation+1.83e-01

Pos logit contributions
arl+0.150
ay+0.144
elly+0.144
ane+0.138
 Today+0.138
Neg logit contributions
 put-0.123
 never-0.119
 pretended-0.119
 learned-0.116
 used-0.115
Token his
Token ID465
Feature activation-8.84e-01

Pos logit contributions
 put+0.002
 never+0.002
 pretended+0.002
 punished+0.002
 learned+0.002
Neg logit contributions
arl-0.005
ay-0.005
elly-0.005
ane-0.005
 Today-0.005
Token sister
Token ID6621
Feature activation-3.48e+00

Pos logit contributions
arl+0.022
ay+0.022
elly+0.021
 Today+0.021
ane+0.021
Neg logit contributions
 put-0.013
 never-0.012
 pretended-0.012
 punished-0.012
 learned-0.012
Token.
Token ID13
Feature activation-3.82e+00

Pos logit contributions
arl+0.053
ay+0.050
elly+0.050
 Today+0.049
ane+0.048
Neg logit contributions
 put-0.040
 never-0.039
 pretended-0.039
 learned-0.038
 used-0.038
Token Can
Token ID1680
Feature activation+8.43e-01

Pos logit contributions
arl+0.074
ay+0.070
ane+0.069
ute+0.069
andel+0.069
Neg logit contributions
 put-0.078
 never-0.076
 pretended-0.074
 made-0.074
 learned-0.073
Token we
Token ID356
Feature activation+2.89e+00

Pos logit contributions
 put+0.016
 pretended+0.016
 never+0.015
 used+0.015
 learned+0.015
Neg logit contributions
arl-0.017
ay-0.016
elly-0.016
 Today-0.016
ane-0.016
Token share
Token ID2648
Feature activation-2.20e+00

Pos logit contributions
 pretended+0.032
 hoped+0.030
 punished+0.029
 remembered+0.028
 learned+0.028
Neg logit contributions
ay-0.080
arl-0.079
-0.075
ute-0.074
 Today-0.074
Token the
Token ID262
Feature activation-3.71e+00

Pos logit contributions
ay+0.055
arl+0.054
elly+0.053
 Today+0.051
ummy+0.051
Neg logit contributions
 pretended-0.029
 never-0.029
 punished-0.029
 forgot-0.029
 put-0.028
Token cr
Token ID1067
Feature activation-1.32e+01

Pos logit contributions
ay+0.091
arl+0.090
elly+0.087
 Today+0.086
ane+0.085
Neg logit contributions
 never-0.054
 put-0.053
 punished-0.053
 pretended-0.052
 hoped-0.051
Tokenay
Token ID323
Feature activation-6.89e+00

Pos logit contributions
arl+0.079
elly+0.052
+0.049
 Today+0.046
arry+0.044
Neg logit contributions
 put-0.438
 made-0.429
 never-0.425
 used-0.421
 fixed-0.418
Tokenon
Token ID261
Feature activation-7.76e+00

Pos logit contributions
arl+0.158
ay+0.152
elly+0.151
 Today+0.146
ane+0.146
Neg logit contributions
 put-0.117
 never-0.112
 pretended-0.111
 used-0.108
 learned-0.108
Token?"
Token ID1701
Feature activation-4.13e+00

Pos logit contributions
arl+0.176
elly+0.165
ay+0.162
 Today+0.160
+0.159
Neg logit contributions
 put-0.137
 never-0.131
 pretended-0.129
 made-0.128
 learned-0.127
Token
Token ID198
Feature activation-5.32e+00

Pos logit contributions
arl+0.091
ay+0.088
ane+0.088
igsaw+0.087
umm+0.085
Neg logit contributions
 put-0.082
 learned-0.077
 hoped-0.074
 made-0.074
 never-0.073
Token
Token ID198
Feature activation-4.24e+00

Pos logit contributions
arl+0.103
elly+0.101
ane+0.101
igsaw+0.100
umm+0.099
Neg logit contributions
 put-0.115
 learned-0.108
 never-0.107
 used-0.104
 made-0.102
Token He
Token ID679
Feature activation+6.99e+00

Pos logit contributions
arl+0.087
ute+0.083
ane+0.083
ay+0.082
owers+0.080
Neg logit contributions
 put-0.093
 never-0.089
 learned-0.089
 tried-0.087
 made-0.087
Token tries
Token ID8404
Feature activation-3.47e-01

Pos logit contributions
 never+0.106
 pretended+0.098
 cleaned+0.098
 learned+0.097
 used+0.097
Neg logit contributions
arl-0.165
ay-0.155
elly-0.154
 Today-0.148
arry-0.143
Token to
Token ID284
Feature activation+4.02e+00

Pos logit contributions
arl+0.008
ay+0.007
elly+0.007
 Today+0.007
ane+0.007
Neg logit contributions
 put-0.006
 pretended-0.006
 never-0.006
 learned-0.006
 used-0.006
Token grab
Token ID5552
Feature activation+5.05e-02

Pos logit contributions
 remembered+0.060
 hoped+0.060
 learned+0.059
 wished+0.057
 pretended+0.056
Neg logit contributions
arl-0.091
ay-0.082
-0.080
igsaw-0.075
 Today-0.075
Token the
Token ID262
Feature activation-3.82e+00

Pos logit contributions
 punished+0.001
 forgot+0.001
 never+0.001
 pretended+0.001
 learned+0.001
Neg logit contributions
ay-0.001
arl-0.001
elly-0.001
 Today-0.001
ane-0.001
Token cr
Token ID1067
Feature activation-1.32e+01

Pos logit contributions
arl+0.096
ay+0.095
elly+0.092
 Today+0.091
ane+0.090
Neg logit contributions
 put-0.055
 never-0.054
 pretended-0.053
 punished-0.051
 learned-0.051
Tokenay
Token ID323
Feature activation-6.70e+00

Pos logit contributions
arl+0.074
elly+0.048
 Today+0.045
+0.045
ute+0.042
Neg logit contributions
 put-0.432
 made-0.424
 never-0.420
 used-0.416
 fixed-0.414
Tokenon
Token ID261
Feature activation-6.96e+00

Pos logit contributions
arl+0.161
elly+0.152
ay+0.147
 Today+0.147
ute+0.145
Neg logit contributions
 put-0.109
 never-0.103
 pretended-0.102
 made-0.100
 used-0.100
Token from
Token ID422
Feature activation+2.34e-01

Pos logit contributions
arl+0.166
elly+0.157
ay+0.154
ane+0.151
 Today+0.151
Neg logit contributions
 put-0.116
 never-0.109
 pretended-0.106
 made-0.106
 used-0.106
Token Mia
Token ID32189
Feature activation-3.18e+00

Pos logit contributions
 punished+0.004
 cleaned+0.004
 forgot+0.004
 learned+0.004
 used+0.004
Neg logit contributions
arl-0.005
 Today-0.004
ay-0.004
elly-0.004
ummy-0.004
Token's
Token ID338
Feature activation-1.84e+00

Pos logit contributions
arl+0.082
elly+0.077
ay+0.077
ane+0.075
 Today+0.075
Neg logit contributions
 put-0.047
 never-0.045
 pretended-0.044
 used-0.043
 learned-0.043
Token happy
Token ID3772
Feature activation-3.11e-01

Pos logit contributions
 pretended+0.053
 forgot+0.051
 wrote+0.047
 never+0.046
 counted+0.045
Neg logit contributions
arl-0.074
elly-0.066
over-0.064
apping-0.062
 Today-0.062
Token to
Token ID284
Feature activation+2.77e+00

Pos logit contributions
arl+0.007
elly+0.007
ay+0.007
 Today+0.006
ane+0.006
Neg logit contributions
 put-0.005
 pretended-0.005
 never-0.005
 learned-0.005
 punished-0.005
Token see
Token ID766
Feature activation-6.27e-02

Pos logit contributions
 pretended+0.035
 punished+0.034
 hoped+0.034
 cleaned+0.033
 learned+0.033
Neg logit contributions
arl-0.073
ay-0.068
 Today-0.068
-0.066
elly-0.065
Token our
Token ID674
Feature activation-1.07e+00

Pos logit contributions
arl+0.002
ay+0.002
elly+0.002
 Today+0.002
ummy+0.002
Neg logit contributions
 pretended-0.001
 put-0.001
 never-0.001
 learned-0.001
 forgot-0.001
Token big
Token ID1263
Feature activation-4.85e+00

Pos logit contributions
arl+0.025
elly+0.024
ay+0.024
ummy+0.023
 Today+0.023
Neg logit contributions
 put-0.018
 never-0.017
 pretended-0.017
 punished-0.017
 learned-0.017
Token cuc
Token ID38421
Feature activation-1.31e+01

Pos logit contributions
arl+0.105
elly+0.101
ay+0.100
 Today+0.098
ummy+0.096
Neg logit contributions
 put-0.086
 never-0.086
 pretended-0.084
 learned-0.082
 punished-0.081
Tokenumber
Token ID4494
Feature activation-3.55e+00

Pos logit contributions
arl+0.203
ay+0.193
 Today+0.192
elly+0.186
ane+0.179
Neg logit contributions
 put-0.316
 used-0.303
 never-0.302
 made-0.298
 punished-0.298
Token."
Token ID526
Feature activation-3.53e+00

Pos logit contributions
arl+0.070
elly+0.067
ay+0.066
ane+0.066
 Today+0.065
Neg logit contributions
 pretended-0.066
 put-0.066
 never-0.065
 learned-0.065
 cleaned-0.064
Token Lily
Token ID20037
Feature activation+4.89e+00

Pos logit contributions
arl+0.093
ay+0.090
ane+0.090
elly+0.089
ute+0.088
Neg logit contributions
 put-0.051
 pretended-0.047
 never-0.046
 learned-0.046
 used-0.045
Token says
Token ID1139
Feature activation-1.58e+00

Pos logit contributions
 never+0.070
 put+0.069
 pretended+0.067
 punished+0.066
 used+0.065
Neg logit contributions
arl-0.120
elly-0.117
 Today-0.116
ay-0.116
ane-0.112
Token.
Token ID13
Feature activation-5.27e+00

Pos logit contributions
arl+0.038
ay+0.037
elly+0.037
ane+0.036
 Today+0.035
Neg logit contributions
 put-0.026
 never-0.024
 used-0.024
 pretended-0.023
 learned-0.023
Token It
Token ID632
Feature activation+5.07e+00

Pos logit contributions
ute+0.091
ane+0.090
ower+0.090
arl+0.090
owers+0.086
Neg logit contributions
 put-0.051
 learned-0.046
 hoped-0.045
 pretended-0.045
 tried-0.044
Token was
Token ID373
Feature activation+2.99e+00

Pos logit contributions
 punished+0.075
 permission+0.069
wed+0.066
 cleaned+0.065
 never+0.064
Neg logit contributions
elly-0.111
 Today-0.111
ay-0.110
-0.108
ane-0.106
Token hiding
Token ID11816
Feature activation-2.19e+00

Pos logit contributions
 punished+0.048
 put+0.048
 learned+0.048
 pretended+0.048
 forgot+0.047
Neg logit contributions
arl-0.067
ay-0.064
elly-0.063
 Today-0.062
ummy-0.060
Token under
Token ID739
Feature activation+1.23e+00

Pos logit contributions
arl+0.052
ay+0.050
elly+0.050
ane+0.048
 Today+0.048
Neg logit contributions
 put-0.035
 never-0.033
 pretended-0.033
 learned-0.033
 punished-0.032
Token a
Token ID257
Feature activation-1.54e+00

Pos logit contributions
 put+0.013
 never+0.013
 pretended+0.013
 punished+0.012
 learned+0.012
Neg logit contributions
arl-0.035
ay-0.034
elly-0.034
 Today-0.033
-0.033
Token seaw
Token ID32085
Feature activation-1.31e+01

Pos logit contributions
arl+0.039
elly+0.038
 Today+0.037
owers+0.037
arry+0.037
Neg logit contributions
 put-0.024
 made-0.021
 never-0.021
 used-0.021
 pretended-0.020
Tokeneed
Token ID2308
Feature activation-6.06e+00

Pos logit contributions
arl+0.183
 Today+0.183
ane+0.178
owers+0.174
+0.172
Neg logit contributions
 put-0.325
 never-0.307
 made-0.300
 used-0.297
 pretended-0.297
Token.
Token ID13
Feature activation-3.35e+00

Pos logit contributions
arl+0.144
ay+0.139
elly+0.137
 Today+0.135
ane+0.133
Neg logit contributions
 put-0.101
 never-0.096
 made-0.094
 pretended-0.093
 used-0.092
Token Lily
Token ID20037
Feature activation+4.84e+00

Pos logit contributions
ane+0.097
ute+0.097
ower+0.096
arl+0.095
ay+0.093
Neg logit contributions
 put-0.039
 learned-0.034
 hoped-0.032
 tried-0.032
 pretended-0.032
Token said
Token ID531
Feature activation-5.55e-01

Pos logit contributions
 punished+0.064
 remind+0.060
 never+0.056
 cleaned+0.056
wed+0.056
Neg logit contributions
elly-0.113
arry-0.107
 Today-0.105
ay-0.104
oles-0.104
Token,
Token ID11
Feature activation+1.84e+00

Pos logit contributions
arl+0.012
elly+0.012
ay+0.012
igsaw+0.011
+0.011
Neg logit contributions
 put-0.011
 never-0.010
 made-0.010
 tried-0.010
 used-0.010
Token still
Token ID991
Feature activation+6.55e+00

Pos logit contributions
 pretended+0.060
 remembered+0.058
 hoped+0.057
ck+0.057
wed+0.056
Neg logit contributions
arl-0.095
ay-0.095
ane-0.091
elly-0.090
owers-0.089
Token have
Token ID423
Feature activation+3.78e+00

Pos logit contributions
 pretended+0.082
 hoped+0.078
 remembered+0.076
ck+0.075
 punished+0.073
Neg logit contributions
arl-0.153
elly-0.153
ay-0.152
 Today-0.146
ore-0.145
Token to
Token ID284
Feature activation+3.98e+00

Pos logit contributions
 pretended+0.066
 put+0.061
ck+0.061
 never+0.060
 hoped+0.060
Neg logit contributions
arl-0.076
elly-0.075
ay-0.072
ummy-0.067
aris-0.067
Token remove
Token ID4781
Feature activation-1.40e+00

Pos logit contributions
 pretended+0.047
 hoped+0.045
 forgot+0.042
 remembered+0.042
 learned+0.041
Neg logit contributions
arl-0.111
ay-0.103
 Today-0.101
ute-0.099
arry-0.096
Token the
Token ID262
Feature activation-4.53e+00

Pos logit contributions
arl+0.041
ay+0.039
elly+0.039
 Today+0.038
ane+0.038
Neg logit contributions
 put-0.015
 never-0.014
 pretended-0.014
 learned-0.014
 used-0.014
Token cr
Token ID1067
Feature activation-1.31e+01

Pos logit contributions
arl+0.105
elly+0.100
ay+0.099
 Today+0.096
ane+0.096
Neg logit contributions
 put-0.078
 never-0.074
 pretended-0.074
 used-0.072
 learned-0.072
Tokenay
Token ID323
Feature activation-6.98e+00

Pos logit contributions
arl+0.071
+0.054
elly+0.052
 Today+0.052
aris+0.043
Neg logit contributions
 put-0.424
 made-0.418
 never-0.416
 used-0.409
 fixed-0.404
Tokenon
Token ID261
Feature activation-7.57e+00

Pos logit contributions
arl+0.190
elly+0.181
 Today+0.177
arry+0.174
+0.174
Neg logit contributions
 put-0.091
 never-0.084
 made-0.084
 pretended-0.082
 used-0.081
Token marks
Token ID8849
Feature activation-7.27e+00

Pos logit contributions
arl+0.183
elly+0.173
+0.171
 Today+0.170
ay+0.170
Neg logit contributions
 put-0.123
 never-0.116
 made-0.112
 used-0.112
 pretended-0.110
Token.
Token ID13
Feature activation-3.57e+00

Pos logit contributions
arl+0.171
elly+0.164
ay+0.162
 Today+0.160
arry+0.160
Neg logit contributions
 put-0.121
 never-0.114
 made-0.111
 used-0.111
 pretended-0.110
Token White
Token ID2635
Feature activation-1.68e+00

Pos logit contributions
arl+0.065
ane+0.064
ute+0.064
ay+0.062
elly+0.061
Neg logit contributions
 put-0.074
 never-0.073
 learned-0.070
 used-0.069
 pretended-0.069
Token brother
Token ID3956
Feature activation+7.65e-02

Pos logit contributions
arl+0.039
elly+0.038
 Today+0.037
ay+0.037
arry+0.037
Neg logit contributions
 put-0.021
 never-0.019
 pretended-0.019
 made-0.018
 cleaned-0.018
Token accidentally
Token ID14716
Feature activation+3.58e+00

Pos logit contributions
ck+0.001
 hoped+0.001
ts+0.001
 never+0.001
 punished+0.001
Neg logit contributions
ay-0.001
elly-0.001
 Today-0.001
ummy-0.001
arl-0.001
Token knocked
Token ID13642
Feature activation-1.31e+00

Pos logit contributions
 learned+0.046
 hoped+0.045
 never+0.043
 forgot+0.041
ts+0.040
Neg logit contributions
ore-0.072
anger-0.072
ay-0.072
ane-0.072
arl-0.071
Token over
Token ID625
Feature activation-3.91e-01

Pos logit contributions
arl+0.034
ay+0.033
elly+0.033
 Today+0.032
ane+0.031
Neg logit contributions
 pretended-0.018
 put-0.018
 never-0.017
 forgot-0.017
 hoped-0.017
Token the
Token ID262
Feature activation-3.91e+00

Pos logit contributions
arl+0.012
ay+0.011
elly+0.011
 Today+0.011
+0.011
Neg logit contributions
 put-0.004
 never-0.004
 pretended-0.004
 forgot-0.003
 hoped-0.003
Token v
Token ID410
Feature activation-1.30e+01

Pos logit contributions
arl+0.094
arry+0.092
elly+0.089
 Today+0.089
ay+0.088
Neg logit contributions
 put-0.066
 never-0.061
 made-0.060
 used-0.059
 cleaned-0.059
Tokenase
Token ID589
Feature activation-6.05e+00

Pos logit contributions
arl+0.183
 Today+0.181
arry+0.166
elly+0.157
owers+0.156
Neg logit contributions
 never-0.322
 put-0.315
 made-0.309
 learned-0.308
 cleaned-0.307
Token and
Token ID290
Feature activation+6.08e+00

Pos logit contributions
arl+0.157
elly+0.149
arry+0.146
ute+0.146
ane+0.145
Neg logit contributions
 put-0.090
 never-0.086
 made-0.085
 used-0.083
 cleaned-0.081
Token it
Token ID340
Feature activation+3.06e+00

Pos logit contributions
wed+0.099
asured+0.094
ck+0.092
 permission+0.090
anut+0.087
Neg logit contributions
ay-0.101
time-0.099
ore-0.097
 tornado-0.095
-0.094
Token broke
Token ID6265
Feature activation-3.07e+00

Pos logit contributions
 learned+0.042
 hoped+0.041
 pretended+0.041
 put+0.040
 shared+0.040
Neg logit contributions
ay-0.071
arl-0.067
elly-0.065
ane-0.065
-0.065
Token into
Token ID656
Feature activation+3.05e-01

Pos logit contributions
arl+0.070
ay+0.068
elly+0.068
ane+0.065
 Today+0.065
Neg logit contributions
 put-0.052
 never-0.050
 pretended-0.050
 learned-0.049
 punished-0.048
Token started
Token ID2067
Feature activation+2.98e+00

Pos logit contributions
 punished+0.075
 never+0.073
 learned+0.066
wed+0.063
 remind+0.061
Neg logit contributions
ay-0.167
ane-0.160
ore-0.155
aris-0.155
elly-0.154
Token eating
Token ID6600
Feature activation-5.94e-01

Pos logit contributions
 punished+0.056
 forgot+0.056
 learned+0.055
 never+0.055
 hoped+0.053
Neg logit contributions
ay-0.054
arl-0.054
 Today-0.053
ore-0.053
ane-0.052
Token the
Token ID262
Feature activation-2.21e+00

Pos logit contributions
arl+0.016
ay+0.015
elly+0.015
 Today+0.015
+0.015
Neg logit contributions
 put-0.007
 never-0.007
 pretended-0.007
 punished-0.007
 learned-0.007
Token delicious
Token ID12625
Feature activation-4.63e+00

Pos logit contributions
ay+0.048
arl+0.046
 Today+0.045
elly+0.045
owers+0.043
Neg logit contributions
 never-0.038
 forgot-0.037
 punished-0.036
 hoped-0.036
 remembered-0.036
Token ch
Token ID442
Feature activation-7.80e+00

Pos logit contributions
ay+0.105
arl+0.105
elly+0.102
 Today+0.100
ummy+0.099
Neg logit contributions
 never-0.075
 put-0.073
 pretended-0.072
 learned-0.072
 hoped-0.072
Tokenocol
Token ID4668
Feature activation-1.30e+01

Pos logit contributions
arl+0.108
elly+0.099
ay+0.099
 Today+0.099
ane+0.096
Neg logit contributions
 put-0.202
 never-0.193
 used-0.192
 pretended-0.191
 learned-0.190
Tokenates
Token ID689
Feature activation-4.40e+00

Pos logit contributions
arl+0.278
 Today+0.271
elly+0.264
ay+0.262
ute+0.253
Neg logit contributions
 put-0.224
 never-0.224
 used-0.220
 learned-0.214
 cleaned-0.212
Token.
Token ID13
Feature activation-3.68e+00

Pos logit contributions
arl+0.086
ay+0.086
elly+0.086
ane+0.084
ummy+0.082
Neg logit contributions
 put-0.081
 pretended-0.080
 never-0.080
 punished-0.080
 learned-0.079
Token She
Token ID1375
Feature activation+8.13e+00

Pos logit contributions
arl+0.087
elly+0.084
ute+0.083
ane+0.080
andel+0.079
Neg logit contributions
 put-0.067
 never-0.065
 learned-0.062
 hoped-0.061
 tried-0.060
Token was
Token ID373
Feature activation+4.46e+00

Pos logit contributions
 punished+0.102
 permission+0.096
 remind+0.091
wed+0.089
ck+0.087
Neg logit contributions
ay-0.174
-0.174
oles-0.169
elly-0.167
ummy-0.166
Token so
Token ID523
Feature activation+2.84e+00

Pos logit contributions
wed+0.076
 pretended+0.074
 forgot+0.073
ck+0.072
ts+0.072
Neg logit contributions
ay-0.081
 Today-0.078
apping-0.078
ummy-0.076
-0.074
Token you
Token ID345
Feature activation+1.57e+00

Pos logit contributions
 put+0.040
 pretended+0.039
 never+0.038
 used+0.037
 punished+0.037
Neg logit contributions
arl-0.061
ay-0.059
elly-0.058
 Today-0.057
ane-0.056
Token want
Token ID765
Feature activation-4.51e-01

Pos logit contributions
 never+0.022
 punished+0.021
 put+0.021
 pretended+0.021
 hoped+0.021
Neg logit contributions
arl-0.039
 Today-0.038
ay-0.038
elly-0.037
ute-0.034
Token to
Token ID284
Feature activation+1.45e+00

Pos logit contributions
ay+0.009
ummy+0.009
elly+0.009
arl+0.009
 Today+0.008
Neg logit contributions
 pretended-0.008
 forgot-0.008
 punished-0.008
 hoped-0.008
 never-0.008
Token borrow
Token ID8804
Feature activation-2.08e+00

Pos logit contributions
 punished+0.017
 hoped+0.016
 pretended+0.016
 never+0.016
 forgot+0.016
Neg logit contributions
ay-0.040
arl-0.039
 Today-0.038
ane-0.037
-0.037
Token another
Token ID1194
Feature activation-4.44e+00

Pos logit contributions
ay+0.056
arl+0.054
elly+0.053
 Today+0.052
ane+0.051
Neg logit contributions
 forgot-0.025
 pretended-0.025
 never-0.025
 put-0.025
 punished-0.025
Token cr
Token ID1067
Feature activation-1.30e+01

Pos logit contributions
arl+0.109
ay+0.105
elly+0.104
 Today+0.102
ane+0.101
Neg logit contributions
 put-0.068
 never-0.066
 pretended-0.065
 learned-0.063
 used-0.063
Tokenay
Token ID323
Feature activation-6.60e+00

Pos logit contributions
arl+0.073
elly+0.048
+0.044
owers+0.043
arry+0.040
Neg logit contributions
 put-0.434
 made-0.430
 never-0.420
 fixed-0.416
 used-0.415
Tokenon
Token ID261
Feature activation-8.20e+00

Pos logit contributions
arl+0.142
ay+0.141
elly+0.136
ane+0.134
 Today+0.132
Neg logit contributions
 put-0.119
 never-0.116
 pretended-0.115
 punished-0.112
 learned-0.112
Token?"
Token ID1701
Feature activation-3.57e+00

Pos logit contributions
arl+0.183
elly+0.170
+0.167
arry+0.166
ay+0.165
Neg logit contributions
 put-0.151
 made-0.144
 pretended-0.138
 never-0.138
 used-0.138
Token Lily
Token ID20037
Feature activation+3.28e+00

Pos logit contributions
arl+0.098
ay+0.095
elly+0.094
ane+0.093
ute+0.092
Neg logit contributions
 put-0.046
 never-0.043
 pretended-0.042
 learned-0.042
 used-0.041
Token asks
Token ID7893
Feature activation-2.21e+00

Pos logit contributions
 never+0.049
 put+0.047
 punished+0.046
 cleaned+0.045
 pretended+0.045
Neg logit contributions
arl-0.078
elly-0.077
 Today-0.077
ay-0.076
ane-0.074
Token him
Token ID683
Feature activation-6.29e-01

Pos logit contributions
arl+0.012
ay+0.011
elly+0.011
 Today+0.011
ane+0.011
Neg logit contributions
 put-0.004
 never-0.003
 pretended-0.003
 learned-0.003
 used-0.003
Token if
Token ID611
Feature activation+1.31e+00

Pos logit contributions
arl+0.016
ay+0.015
elly+0.015
 Today+0.015
ane+0.014
Neg logit contributions
 put-0.009
 never-0.009
 pretended-0.009
 learned-0.009
 used-0.009
Token he
Token ID339
Feature activation+5.38e+00

Pos logit contributions
 put+0.020
 pretended+0.019
 punished+0.019
 cleaned+0.019
 used+0.019
Neg logit contributions
arl-0.030
ane-0.029
elly-0.029
ay-0.028
 Today-0.028
Token took
Token ID1718
Feature activation+8.67e-01

Pos logit contributions
 punished+0.074
ck+0.068
eling+0.066
 remind+0.066
 permission+0.065
Neg logit contributions
elly-0.119
ane-0.116
ay-0.115
arry-0.107
-0.107
Token her
Token ID607
Feature activation-3.11e+00

Pos logit contributions
 forgot+0.012
 hoped+0.011
 never+0.011
 remembered+0.011
 pretended+0.011
Neg logit contributions
ay-0.022
arl-0.021
igsaw-0.020
 Today-0.020
elly-0.019
Token cr
Token ID1067
Feature activation-1.29e+01

Pos logit contributions
arl+0.085
elly+0.081
ay+0.079
ane+0.078
arry+0.078
Neg logit contributions
 put-0.041
 pretended-0.039
 never-0.038
 used-0.037
 made-0.037
Tokenay
Token ID323
Feature activation-6.42e+00

Pos logit contributions
arl+0.057
elly+0.040
 Today+0.036
+0.035
owers+0.030
Neg logit contributions
 put-0.442
 never-0.433
 made-0.432
 used-0.426
 fixed-0.425
Tokenons
Token ID684
Feature activation-5.61e+00

Pos logit contributions
arl+0.155
elly+0.147
 Today+0.142
ay+0.142
arry+0.140
Neg logit contributions
 put-0.103
 never-0.098
 pretended-0.096
 made-0.095
 used-0.095
Token.
Token ID13
Feature activation-4.16e+00

Pos logit contributions
arl+0.126
ay+0.121
elly+0.120
ane+0.116
 Today+0.116
Neg logit contributions
 put-0.098
 never-0.094
 pretended-0.094
 learned-0.091
 used-0.091
Token He
Token ID679
Feature activation+7.80e+00

Pos logit contributions
andel+0.101
arl+0.096
ute+0.095
elly+0.094
ane+0.093
Neg logit contributions
 put-0.070
 never-0.066
 hoped-0.065
 learned-0.064
 tried-0.064
Token said
Token ID531
Feature activation-6.63e-01

Pos logit contributions
 care+0.112
 permission+0.110
eling+0.108
ts+0.102
 supposed+0.098
Neg logit contributions
elly-0.136
arry-0.127
uffy-0.127
ay-0.124
uddle-0.123
Token "
Token ID366
Feature activation-4.17e-01

Pos logit contributions
 put+0.062
 never+0.059
 used+0.058
 pretended+0.058
 made+0.058
Neg logit contributions
arl-0.055
elly-0.053
ay-0.053
ane-0.051
ute-0.050
TokenCan
Token ID6090
Feature activation+1.89e+00

Pos logit contributions
arl+0.009
ay+0.008
elly+0.008
 Today+0.008
ane+0.008
Neg logit contributions
 put-0.008
 never-0.008
 pretended-0.008
 learned-0.007
 used-0.007
Token I
Token ID314
Feature activation+2.98e+00

Pos logit contributions
 put+0.036
 never+0.035
 pretended+0.033
 used+0.033
 learned+0.033
Neg logit contributions
arl-0.041
elly-0.039
ay-0.039
 Today-0.037
ane-0.037
Token take
Token ID1011
Feature activation+5.74e-03

Pos logit contributions
 punished+0.034
 hoped+0.033
 never+0.033
 pretended+0.032
 learned+0.032
Neg logit contributions
ay-0.083
arl-0.079
 Today-0.077
-0.076
elly-0.075
Token these
Token ID777
Feature activation-4.55e+00

Pos logit contributions
 forgot+0.000
 hoped+0.000
 never+0.000
 pretended+0.000
 punished+0.000
Neg logit contributions
ay-0.000
arl-0.000
elly-0.000
ane-0.000
ummy-0.000
Token cr
Token ID1067
Feature activation-1.29e+01

Pos logit contributions
arl+0.119
ay+0.114
elly+0.114
 Today+0.111
ane+0.111
Neg logit contributions
 put-0.063
 never-0.060
 pretended-0.059
 used-0.058
 learned-0.057
Tokenay
Token ID323
Feature activation-6.23e+00

Pos logit contributions
arl+0.074
elly+0.053
 Today+0.048
+0.043
arry+0.038
Neg logit contributions
 put-0.422
 made-0.413
 never-0.409
 used-0.406
 fixed-0.404
Tokenons
Token ID684
Feature activation-5.56e+00

Pos logit contributions
arl+0.154
ay+0.150
elly+0.148
ane+0.144
 Today+0.144
Neg logit contributions
 put-0.094
 never-0.090
 pretended-0.089
 learned-0.086
 used-0.086
Token home
Token ID1363
Feature activation-5.19e+00

Pos logit contributions
arl+0.125
elly+0.119
ay+0.118
 Today+0.115
ane+0.114
Neg logit contributions
 put-0.098
 never-0.094
 pretended-0.092
 made-0.091
 used-0.091
Token?"
Token ID1701
Feature activation-4.72e+00

Pos logit contributions
arl+0.121
elly+0.113
ay+0.110
arry+0.109
+0.109
Neg logit contributions
 put-0.093
 never-0.087
 made-0.086
 used-0.084
 pretended-0.083
Token Her
Token ID2332
Feature activation-1.66e+00

Pos logit contributions
arl+0.101
elly+0.095
ay+0.089
igsaw+0.088
ane+0.087
Neg logit contributions
 put-0.097
 never-0.092
 tried-0.090
 learned-0.090
 pretended-0.089
Token you
Token ID345
Feature activation+1.88e+00

Pos logit contributions
 put+0.032
 never+0.031
 pretended+0.030
 used+0.030
 made+0.029
Neg logit contributions
arl-0.040
elly-0.038
ay-0.037
ane-0.036
 Today-0.036
Token help
Token ID1037
Feature activation-1.21e+00

Pos logit contributions
 hoped+0.021
 pretended+0.021
 forgot+0.020
 learned+0.020
 never+0.020
Neg logit contributions
ay-0.052
arl-0.051
-0.049
 Today-0.049
ute-0.048
Token me
Token ID502
Feature activation-7.47e-01

Pos logit contributions
ay+0.028
arl+0.028
ummy+0.027
elly+0.026
ute+0.026
Neg logit contributions
 pretended-0.019
 hoped-0.019
 learned-0.019
 forgot-0.019
 remembered-0.018
Token get
Token ID651
Feature activation+8.42e-01

Pos logit contributions
arl+0.019
ay+0.019
ute+0.018
 Today+0.018
elly+0.018
Neg logit contributions
 pretended-0.010
 hoped-0.010
 never-0.010
 learned-0.010
 forgot-0.009
Token the
Token ID262
Feature activation-3.64e+00

Pos logit contributions
 pretended+0.013
 forgot+0.012
 hoped+0.012
 learned+0.012
 never+0.012
Neg logit contributions
arl-0.020
ay-0.020
elly-0.019
ummy-0.019
ore-0.019
Token cr
Token ID1067
Feature activation-1.29e+01

Pos logit contributions
arl+0.091
ay+0.089
elly+0.087
 Today+0.085
ane+0.084
Neg logit contributions
 put-0.054
 never-0.052
 pretended-0.052
 learned-0.050
 punished-0.050
Tokenay
Token ID323
Feature activation-6.30e+00

Pos logit contributions
arl+0.071
elly+0.057
 Today+0.046
aris+0.044
+0.043
Neg logit contributions
 put-0.420
 made-0.413
 fixed-0.404
 used-0.404
 never-0.402
Tokenons
Token ID684
Feature activation-4.98e+00

Pos logit contributions
arl+0.155
elly+0.147
 Today+0.142
ay+0.141
arry+0.140
Neg logit contributions
 put-0.099
 never-0.094
 pretended-0.092
 made-0.092
 used-0.091
Token from
Token ID422
Feature activation+1.06e+00

Pos logit contributions
arl+0.110
elly+0.105
ay+0.103
 Today+0.102
arry+0.100
Neg logit contributions
 put-0.091
 never-0.086
 made-0.085
 used-0.084
 pretended-0.084
Token the
Token ID262
Feature activation-2.85e+00

Pos logit contributions
 pretended+0.012
 forgot+0.012
 learned+0.012
 put+0.012
 never+0.011
Neg logit contributions
arl-0.029
ay-0.028
elly-0.027
ummy-0.027
 Today-0.027
Token cabinet
Token ID13447
Feature activation-7.22e+00

Pos logit contributions
arl+0.047
ay+0.044
elly+0.044
ane+0.042
 Today+0.042
Neg logit contributions
 put-0.068
 never-0.066
 pretended-0.065
 used-0.064
 learned-0.064
Token'm
Token ID1101
Feature activation+2.71e+00

Pos logit contributions
 punished+0.058
 never+0.058
ts+0.057
 hoped+0.057
ck+0.057
Neg logit contributions
elly-0.063
ay-0.060
 Today-0.060
-0.059
arl-0.059
Token trying
Token ID2111
Feature activation-1.57e-01

Pos logit contributions
 pretended+0.035
 learned+0.035
 hoped+0.035
wed+0.035
 shared+0.035
Neg logit contributions
arl-0.066
-0.064
ay-0.063
 Today-0.063
ute-0.062
Token to
Token ID284
Feature activation+3.92e+00

Pos logit contributions
arl+0.003
ay+0.003
elly+0.003
 Today+0.003
ute+0.003
Neg logit contributions
 put-0.003
 pretended-0.003
 never-0.003
 punished-0.003
 hoped-0.003
Token get
Token ID651
Feature activation+1.88e+00

Pos logit contributions
 hoped+0.050
 forgot+0.047
 remembered+0.047
 pretended+0.047
 learned+0.046
Neg logit contributions
ay-0.100
ute-0.097
arl-0.094
-0.090
arry-0.090
Token the
Token ID262
Feature activation-3.74e+00

Pos logit contributions
 hoped+0.029
 pretended+0.029
 forgot+0.029
 never+0.028
 remembered+0.027
Neg logit contributions
arl-0.042
ay-0.040
ore-0.040
elly-0.039
igsaw-0.039
Token cr
Token ID1067
Feature activation-1.28e+01

Pos logit contributions
arl+0.084
ay+0.083
elly+0.079
 Today+0.079
ane+0.078
Neg logit contributions
 put-0.064
 never-0.063
 learned-0.061
 pretended-0.061
 hoped-0.060
Tokenay
Token ID323
Feature activation-5.92e+00

Pos logit contributions
arl+0.070
elly+0.060
 Today+0.051
ute+0.050
+0.050
Neg logit contributions
 put-0.409
 made-0.405
 fixed-0.399
 used-0.396
 never-0.394
Tokenons
Token ID684
Feature activation-4.71e+00

Pos logit contributions
arl+0.149
elly+0.142
 Today+0.137
ay+0.136
ute+0.135
Neg logit contributions
 put-0.090
 never-0.084
 pretended-0.084
 made-0.083
 used-0.082
Token from
Token ID422
Feature activation+6.07e-01

Pos logit contributions
arl+0.108
elly+0.103
ay+0.103
 Today+0.100
ane+0.099
Neg logit contributions
 put-0.080
 never-0.077
 pretended-0.076
 used-0.074
 made-0.074
Token the
Token ID262
Feature activation-3.42e+00

Pos logit contributions
 put+0.007
 pretended+0.006
 never+0.006
 learned+0.006
 forgot+0.006
Neg logit contributions
arl-0.017
ay-0.017
elly-0.016
ane-0.016
 Today-0.016
Token cabinet
Token ID13447
Feature activation-6.42e+00

Pos logit contributions
arl+0.051
ay+0.048
elly+0.047
 Today+0.046
+0.044
Neg logit contributions
 put-0.085
 pretended-0.083
 never-0.083
 learned-0.081
 used-0.081
Token a
Token ID257
Feature activation-4.92e-01

Pos logit contributions
 forgot+0.009
 pretended+0.009
 put+0.009
 never+0.008
 punished+0.008
Neg logit contributions
ay-0.011
arl-0.010
elly-0.010
 Today-0.010
ane-0.010
Token big
Token ID1263
Feature activation-2.59e+00

Pos logit contributions
arl+0.012
elly+0.011
ay+0.011
 Today+0.011
ane+0.011
Neg logit contributions
 put-0.009
 never-0.008
 pretended-0.008
 used-0.008
 made-0.008
Token box
Token ID3091
Feature activation-5.26e+00

Pos logit contributions
arl+0.057
elly+0.054
ay+0.053
 Today+0.052
ane+0.052
Neg logit contributions
 put-0.048
 never-0.045
 pretended-0.045
 used-0.044
 learned-0.044
Token of
Token ID286
Feature activation-5.37e-01

Pos logit contributions
arl+0.095
ay+0.093
elly+0.091
ane+0.088
 Today+0.087
Neg logit contributions
 put-0.110
 pretended-0.109
 never-0.108
 punished-0.107
 learned-0.107
Token ch
Token ID442
Feature activation-7.09e+00

Pos logit contributions
ay+0.011
elly+0.010
ummy+0.010
 Today+0.010
arl+0.010
Neg logit contributions
 forgot-0.010
 never-0.010
 remembered-0.010
 managed-0.009
 hoped-0.009
Tokenocol
Token ID4668
Feature activation-1.28e+01

Pos logit contributions
arl+0.100
 Today+0.099
+0.098
ay+0.089
elly+0.088
Neg logit contributions
 put-0.176
 used-0.166
 never-0.165
 learned-0.165
 cleaned-0.164
Tokenates
Token ID689
Feature activation-5.78e+00

Pos logit contributions
arl+0.267
 Today+0.259
elly+0.254
ay+0.250
+0.244
Neg logit contributions
 put-0.231
 never-0.229
 used-0.225
 pretended-0.223
 cleaned-0.220
Token to
Token ID284
Feature activation+2.21e+00

Pos logit contributions
arl+0.128
ay+0.124
elly+0.124
ane+0.121
 Today+0.119
Neg logit contributions
 put-0.100
 never-0.097
 pretended-0.096
 learned-0.094
 punished-0.093
Token share
Token ID2648
Feature activation-1.46e+00

Pos logit contributions
 forgot+0.027
 punished+0.026
 remembered+0.026
 pretended+0.026
 never+0.025
Neg logit contributions
ay-0.056
arl-0.055
 Today-0.054
-0.052
ore-0.051
Token with
Token ID351
Feature activation+1.77e-01

Pos logit contributions
arl+0.034
ay+0.034
elly+0.033
 Today+0.032
ane+0.032
Neg logit contributions
 put-0.022
 pretended-0.022
 never-0.022
 punished-0.022
 forgot-0.021
Token the
Token ID262
Feature activation-2.43e+00

Pos logit contributions
 pretended+0.002
 put+0.002
 punished+0.002
 cleaned+0.002
 forgot+0.002
Neg logit contributions
ay-0.005
elly-0.005
ummy-0.004
ore-0.004
arl-0.004
Token He
Token ID679
Feature activation+8.48e+00

Pos logit contributions
ane+0.098
andel+0.095
owers+0.094
ute+0.094
ay+0.092
Neg logit contributions
 put-0.067
 his-0.063
 made-0.061
 used-0.061
 tried-0.060
Token remembers
Token ID18140
Feature activation+2.25e+00

Pos logit contributions
 never+0.126
 pretended+0.122
 punished+0.122
 cleaned+0.120
ts+0.119
Neg logit contributions
arl-0.180
elly-0.171
 Today-0.167
arry-0.157
uddle-0.155
Token he
Token ID339
Feature activation+5.42e+00

Pos logit contributions
 put+0.030
 pretended+0.030
 punished+0.029
 never+0.028
 learned+0.028
Neg logit contributions
arl-0.058
elly-0.056
 Today-0.053
ummy-0.053
ay-0.053
Token borrowed
Token ID22546
Feature activation-1.52e+00

Pos logit contributions
 pretended+0.063
 punished+0.062
ts+0.061
 never+0.059
ck+0.056
Neg logit contributions
elly-0.125
arl-0.116
ay-0.115
ore-0.113
ane-0.113
Token the
Token ID262
Feature activation-3.93e+00

Pos logit contributions
ay+0.042
arl+0.041
elly+0.040
ummy+0.039
 Today+0.039
Neg logit contributions
 forgot-0.019
 pretended-0.018
 never-0.018
 punished-0.017
 remembered-0.017
Token cr
Token ID1067
Feature activation-1.28e+01

Pos logit contributions
arl+0.089
ay+0.087
elly+0.085
 Today+0.084
ane+0.083
Neg logit contributions
 put-0.066
 never-0.065
 pretended-0.064
 punished-0.063
 learned-0.062
Tokenay
Token ID323
Feature activation-6.60e+00

Pos logit contributions
arl+0.070
elly+0.048
+0.045
 Today+0.042
ute+0.040
Neg logit contributions
 put-0.425
 made-0.418
 never-0.413
 used-0.411
 fixed-0.407
Tokenon
Token ID261
Feature activation-7.26e+00

Pos logit contributions
arl+0.154
elly+0.146
ay+0.145
 Today+0.141
ane+0.141
Neg logit contributions
 put-0.111
 never-0.106
 pretended-0.105
 used-0.103
 learned-0.102
Token.
Token ID13
Feature activation-3.98e+00

Pos logit contributions
arl+0.168
elly+0.159
ay+0.159
 Today+0.154
ane+0.154
Neg logit contributions
 put-0.124
 never-0.119
 pretended-0.117
 used-0.115
 made-0.114
Token
Token ID198
Feature activation-4.73e+00

Pos logit contributions
ane+0.094
owers+0.093
andel+0.093
ute+0.090
ay+0.088
Neg logit contributions
 put-0.066
 his-0.060
 learned-0.060
 used-0.060
 hoped-0.059
Token
Token ID198
Feature activation-3.65e+00

Pos logit contributions
arl+0.089
ane+0.089
owers+0.089
elly+0.088
+0.087
Neg logit contributions
 put-0.100
 never-0.095
 learned-0.093
 used-0.091
 made-0.089
Token they
Token ID484
Feature activation+6.08e+00

Pos logit contributions
 put+0.028
 punished+0.028
 never+0.027
 cleaned+0.027
 pretended+0.027
Neg logit contributions
ay-0.031
elly-0.031
arl-0.030
 Today-0.030
ane-0.029
Token disagreed
Token ID27884
Feature activation-2.30e+00

Pos logit contributions
 put+0.076
 punished+0.072
 pretended+0.071
 used+0.069
 cleaned+0.069
Neg logit contributions
ay-0.144
arl-0.144
ane-0.141
elly-0.141
-0.137
Token on
Token ID319
Feature activation+6.47e-01

Pos logit contributions
arl+0.059
ay+0.056
elly+0.056
ane+0.055
 Today+0.054
Neg logit contributions
 put-0.035
 never-0.034
 made-0.032
 used-0.032
 pretended-0.032
Token something
Token ID1223
Feature activation-1.02e+00

Pos logit contributions
 put+0.007
 pretended+0.006
 never+0.006
 used+0.006
 learned+0.006
Neg logit contributions
arl-0.019
ay-0.018
elly-0.018
 Today-0.018
ane-0.018
Token and
Token ID290
Feature activation+6.29e+00

Pos logit contributions
arl+0.024
ay+0.023
elly+0.023
 Today+0.023
ane+0.023
Neg logit contributions
 put-0.017
 never-0.016
 pretended-0.016
 used-0.015
 learned-0.015
Token they
Token ID484
Feature activation+7.78e+00

Pos logit contributions
wed+0.057
 put+0.055
 never+0.055
 cleaned+0.054
 pretended+0.054
Neg logit contributions
elly-0.148
arl-0.147
ay-0.145
 Today-0.144
ane-0.144
Token began
Token ID2540
Feature activation+2.57e+00

Pos logit contributions
wed+0.067
 put+0.065
ws+0.065
ck+0.064
 cleaned+0.063
Neg logit contributions
ay-0.172
ifying-0.168
ane-0.168
arry-0.165
arl-0.163
Token to
Token ID284
Feature activation+4.70e+00

Pos logit contributions
 put+0.048
 pretended+0.047
 never+0.046
 hoped+0.046
 cleaned+0.046
Neg logit contributions
arl-0.049
elly-0.048
 Today-0.047
ay-0.047
ute-0.046
Token scatter
Token ID41058
Feature activation-1.15e+00

Pos logit contributions
 put+0.066
 pretended+0.065
 hoped+0.065
 used+0.064
 cleaned+0.064
Neg logit contributions
arl-0.108
 Today-0.107
ay-0.102
-0.101
ute-0.101
Token in
Token ID287
Feature activation+1.30e+00

Pos logit contributions
arl+0.030
ay+0.029
elly+0.029
 Today+0.028
ane+0.027
Neg logit contributions
 put-0.015
 never-0.015
 pretended-0.015
 learned-0.014
 forgot-0.014
Token different
Token ID1180
Feature activation-2.49e-01

Pos logit contributions
 put+0.015
 pretended+0.014
 never+0.014
 forgot+0.014
 punished+0.014
Neg logit contributions
arl-0.035
ay-0.035
elly-0.034
 Today-0.034
-0.034
Token little
Token ID1310
Feature activation-2.44e+00

Pos logit contributions
arl+0.042
elly+0.040
ay+0.040
ane+0.039
 Today+0.038
Neg logit contributions
 put-0.038
 never-0.036
 pretended-0.035
 learned-0.035
 used-0.035
Token boy
Token ID2933
Feature activation+5.52e+00

Pos logit contributions
arl+0.045
elly+0.044
ay+0.044
 Today+0.042
ane+0.042
Neg logit contributions
 put-0.050
 never-0.050
 pretended-0.049
 learned-0.048
 punished-0.048
Token and
Token ID290
Feature activation+3.08e+00

Pos logit contributions
 punished+0.066
 pretended+0.065
wed+0.063
ck+0.063
ts+0.062
Neg logit contributions
ay-0.128
ane-0.125
-0.119
 Today-0.118
arry-0.118
Token his
Token ID465
Feature activation+1.41e-01

Pos logit contributions
 never+0.024
 put+0.024
 pretended+0.024
 punished+0.023
 used+0.023
Neg logit contributions
arl-0.094
ay-0.093
 Today-0.091
ane-0.090
elly-0.089
Token mom
Token ID1995
Feature activation+4.13e+00

Pos logit contributions
 put+0.002
 never+0.002
 pretended+0.002
 learned+0.002
 used+0.002
Neg logit contributions
arl-0.004
ay-0.003
elly-0.003
 Today-0.003
ane-0.003
Token and
Token ID290
Feature activation+4.41e+00

Pos logit contributions
 punished+0.050
ts+0.046
 pretended+0.045
ck+0.045
 hoped+0.043
Neg logit contributions
ay-0.107
ane-0.100
ummy-0.095
arry-0.093
aris-0.092
Token dad
Token ID9955
Feature activation+4.83e+00

Pos logit contributions
 never+0.075
 punished+0.073
 used+0.072
 pretended+0.071
 forgot+0.071
Neg logit contributions
ay-0.090
arl-0.089
ane-0.086
 Today-0.083
ute-0.082
Token had
Token ID550
Feature activation+5.03e+00

Pos logit contributions
 punished+0.068
ck+0.059
 wounds+0.057
 pretended+0.056
 put+0.056
Neg logit contributions
ay-0.109
ane-0.104
aris-0.095
owers-0.094
arry-0.093
Token a
Token ID257
Feature activation+1.45e+00

Pos logit contributions
ck+0.084
 punished+0.081
 pretended+0.077
 forgot+0.076
 put+0.074
Neg logit contributions
ay-0.100
aris-0.097
 Today-0.088
-0.086
igsaw-0.085
Token big
Token ID1263
Feature activation-8.00e-01

Pos logit contributions
 put+0.024
 never+0.023
 pretended+0.023
 learned+0.022
 used+0.022
Neg logit contributions
arl-0.034
elly-0.033
ay-0.033
ane-0.032
 Today-0.032
Token celebration
Token ID14395
Feature activation-3.05e+00

Pos logit contributions
arl+0.017
ay+0.017
elly+0.017
 Today+0.016
ane+0.016
Neg logit contributions
 put-0.014
 never-0.014
 pretended-0.014
 used-0.013
 learned-0.013
Token Sunday
Token ID3502
Feature activation-1.21e+00

Pos logit contributions
arl+0.063
ute+0.060
elly+0.059
ane+0.057
ay+0.056
Neg logit contributions
 never-0.055
 learned-0.054
 put-0.054
 used-0.051
 hoped-0.050
Token was
Token ID373
Feature activation+3.79e+00

Pos logit contributions
arl+0.029
elly+0.027
ay+0.027
 Today+0.026
ane+0.026
Neg logit contributions
 put-0.020
 never-0.020
 pretended-0.019
 learned-0.019
 made-0.019
Token very
Token ID845
Feature activation+3.18e+00

Pos logit contributions
 put+0.046
 pretended+0.045
 learned+0.042
 used+0.042
 hoped+0.042
Neg logit contributions
arl-0.099
ay-0.099
 Today-0.095
elly-0.095
ane-0.092
Token proud
Token ID6613
Feature activation-1.71e+00

Pos logit contributions
 put+0.043
 pretended+0.041
 never+0.041
 used+0.040
 learned+0.039
Neg logit contributions
arl-0.084
ay-0.080
elly-0.080
 Today-0.078
ane-0.077
Token and
Token ID290
Feature activation+5.77e+00

Pos logit contributions
arl+0.027
ay+0.026
elly+0.026
 Today+0.025
ane+0.025
Neg logit contributions
 put-0.040
 never-0.039
 pretended-0.039
 learned-0.038
 used-0.038
Token everyone
Token ID2506
Feature activation+5.27e+00

Pos logit contributions
 pretended+0.077
 put+0.076
wed+0.075
 punished+0.074
 cleaned+0.072
Neg logit contributions
ay-0.136
arl-0.131
 Today-0.128
elly-0.128
ummy-0.125
Token praised
Token ID15342
Feature activation-3.91e-01

Pos logit contributions
 pretended+0.061
 punished+0.059
wed+0.058
 put+0.058
ck+0.055
Neg logit contributions
ane-0.128
ore-0.126
ay-0.122
elly-0.121
apping-0.118
Token him
Token ID683
Feature activation-2.28e-01

Pos logit contributions
arl+0.012
elly+0.012
ane+0.012
ay+0.012
ute+0.011
Neg logit contributions
 put-0.004
 never-0.003
 used-0.003
 made-0.003
 learned-0.003
Token for
Token ID329
Feature activation+3.06e+00

Pos logit contributions
arl+0.006
ay+0.006
elly+0.006
 Today+0.005
ane+0.005
Neg logit contributions
 put-0.003
 never-0.003
 pretended-0.003
 used-0.003
 learned-0.003
Token being
Token ID852
Feature activation+3.94e+00

Pos logit contributions
 pretended+0.041
 forgot+0.040
 put+0.036
 hoped+0.036
 remembered+0.035
Neg logit contributions
arl-0.076
-0.070
ay-0.070
apping-0.067
ore-0.066
Token so
Token ID523
Feature activation+1.71e+00

Pos logit contributions
 pretended+0.056
 put+0.055
 forgot+0.052
 hoped+0.050
 never+0.050
Neg logit contributions
ay-0.091
arl-0.090
elly-0.089
apping-0.085
ane-0.084
Token to
Token ID284
Feature activation+2.25e+00

Pos logit contributions
arl+0.021
ane+0.021
elly+0.021
owers+0.020
ute+0.020
Neg logit contributions
 put-0.014
 never-0.013
 made-0.013
 used-0.013
 tried-0.012
Token her
Token ID607
Feature activation-7.51e-01

Pos logit contributions
 pretended+0.021
 forgot+0.020
 punished+0.019
 used+0.019
 hoped+0.019
Neg logit contributions
arl-0.065
ay-0.064
 Today-0.062
-0.061
ummy-0.061
Token mom
Token ID1995
Feature activation-1.06e+00

Pos logit contributions
arl+0.019
elly+0.018
ay+0.018
ane+0.018
 Today+0.018
Neg logit contributions
 put-0.011
 never-0.011
 pretended-0.011
 used-0.010
 learned-0.010
Token in
Token ID287
Feature activation+2.60e+00

Pos logit contributions
arl+0.023
elly+0.022
ay+0.022
ute+0.022
ane+0.022
Neg logit contributions
 put-0.020
 never-0.019
 pretended-0.018
 used-0.018
 made-0.018
Token tears
Token ID10953
Feature activation-9.63e-01

Pos logit contributions
 put+0.028
 never+0.026
 made+0.025
 pretended+0.025
 learned+0.025
Neg logit contributions
arl-0.077
elly-0.074
ay-0.073
ane-0.073
ute-0.073
Token and
Token ID290
Feature activation+6.98e+00

Pos logit contributions
arl+0.021
ay+0.020
elly+0.020
 Today+0.020
ane+0.020
Neg logit contributions
 put-0.017
 never-0.017
 pretended-0.016
 used-0.016
 learned-0.016
Token asked
Token ID1965
Feature activation+6.92e-01

Pos logit contributions
wed+0.075
ck+0.067
ts+0.064
 never+0.061
wy+0.061
Neg logit contributions
ay-0.151
 Today-0.150
-0.148
arry-0.147
ummy-0.146
Token,
Token ID11
Feature activation+1.62e+00

Pos logit contributions
 put+0.007
 pretended+0.007
 never+0.006
 used+0.006
 punished+0.006
Neg logit contributions
arl-0.020
ay-0.020
elly-0.019
 Today-0.019
ane-0.019
Token why
Token ID1521
Feature activation+4.15e-02

Pos logit contributions
 put+0.034
 never+0.033
 used+0.032
 made+0.031
 learned+0.031
Neg logit contributions
arl-0.032
elly-0.032
ay-0.032
ane-0.031
ute-0.030
Token would
Token ID561
Feature activation+4.17e+00

Pos logit contributions
 put+0.001
 pretended+0.001
 never+0.001
 punished+0.001
 learned+0.001
Neg logit contributions
arl-0.001
ay-0.001
elly-0.001
 Today-0.001
ane-0.001
Token you
Token ID345
Feature activation+2.77e+00

Pos logit contributions
 pretended+0.051
wed+0.048
 hoped+0.045
 learned+0.043
 cleaned+0.043
Neg logit contributions
ummy-0.100
-0.100
arl-0.098
 Today-0.098
ay-0.096
Token Tim
Token ID5045
Feature activation-2.58e+00

Pos logit contributions
arl+0.053
elly+0.051
ay+0.050
ane+0.050
ute+0.050
Neg logit contributions
 put-0.027
 pretended-0.025
 never-0.025
 used-0.024
 made-0.024
Tokenmy
Token ID1820
Feature activation-1.30e+00

Pos logit contributions
elly+0.054
arl+0.054
ay+0.054
ummy+0.052
 Today+0.052
Neg logit contributions
 punished-0.042
 pretended-0.042
 hoped-0.041
 wished-0.040
 never-0.040
Token and
Token ID290
Feature activation+3.65e+00

Pos logit contributions
ay+0.022
elly+0.022
arl+0.022
 Today+0.021
ummy+0.020
Neg logit contributions
 punished-0.027
 pretended-0.026
 forgot-0.026
 put-0.026
 hoped-0.025
Token Sally
Token ID25737
Feature activation-1.05e+00

Pos logit contributions
wed+0.073
 punished+0.072
ck+0.071
eling+0.068
 put+0.067
Neg logit contributions
 Today-0.058
arl-0.057
arry-0.055
ay-0.054
igsaw-0.053
Token.
Token ID13
Feature activation-4.98e+00

Pos logit contributions
arl+0.020
ay+0.019
elly+0.019
 Today+0.018
arry+0.018
Neg logit contributions
 put-0.021
 pretended-0.021
 punished-0.021
 never-0.020
 hoped-0.020
Token They
Token ID1119
Feature activation+6.37e+00

Pos logit contributions
arl+0.097
ane+0.094
ute+0.093
elly+0.092
ay+0.091
Neg logit contributions
 put-0.105
 pretended-0.101
 never-0.099
 used-0.098
 made-0.097
Token loved
Token ID6151
Feature activation+1.35e+00

Pos logit contributions
 punished+0.096
 wounds+0.093
ck+0.092
eling+0.086
 tightened+0.086
Neg logit contributions
ay-0.133
owers-0.131
 Today-0.126
ane-0.123
arl-0.123
Token to
Token ID284
Feature activation+2.84e+00

Pos logit contributions
 punished+0.026
 put+0.026
 forgot+0.025
 never+0.025
 pretended+0.025
Neg logit contributions
arl-0.025
ay-0.025
elly-0.024
ummy-0.023
 Today-0.023
Token play
Token ID711
Feature activation-3.76e+00

Pos logit contributions
 punished+0.035
 never+0.035
 put+0.034
 hoped+0.033
 learned+0.033
Neg logit contributions
arl-0.075
ay-0.073
 Today-0.073
-0.071
ute-0.070
Token together
Token ID1978
Feature activation-1.24e+00

Pos logit contributions
arl+0.090
ay+0.086
elly+0.086
ane+0.083
 Today+0.083
Neg logit contributions
 put-0.062
 never-0.059
 pretended-0.059
 used-0.057
 learned-0.057
Token every
Token ID790
Feature activation+3.96e-01

Pos logit contributions
arl+0.032
elly+0.030
ay+0.030
ane+0.030
 Today+0.030
Neg logit contributions
 put-0.018
 never-0.018
 pretended-0.017
 used-0.017
 made-0.017
Token you
Token ID345
Feature activation-1.95e-01

Pos logit contributions
 put+0.011
 pretended+0.011
 never+0.010
 used+0.010
 learned+0.010
Neg logit contributions
arl-0.016
ay-0.016
elly-0.016
 Today-0.015
ane-0.015
Token,
Token ID11
Feature activation+7.36e-01

Pos logit contributions
arl+0.004
ay+0.004
elly+0.004
 Today+0.004
ane+0.004
Neg logit contributions
 put-0.003
 pretended-0.003
 never-0.003
 used-0.003
 punished-0.003
Token too
Token ID1165
Feature activation-6.29e-01

Pos logit contributions
 put+0.012
 never+0.011
 pretended+0.011
 used+0.011
 learned+0.011
Neg logit contributions
arl-0.018
ay-0.017
elly-0.017
 Today-0.017
ane-0.016
Token.
Token ID13
Feature activation-2.97e+00

Pos logit contributions
ane+0.017
arl+0.017
anger+0.017
ute+0.017
ay+0.016
Neg logit contributions
 put-0.008
 never-0.008
 used-0.008
 made-0.007
 learned-0.007
Token You
Token ID921
Feature activation+4.45e+00

Pos logit contributions
arl+0.053
elly+0.050
ay+0.049
ute+0.049
ane+0.049
Neg logit contributions
 put-0.065
 never-0.065
 learned-0.062
 pretended-0.062
 made-0.062
Token are
Token ID389
Feature activation+2.86e+00

Pos logit contributions
ck+0.099
eling+0.087
wed+0.086
 asking+0.086
 forth+0.085
Neg logit contributions
ay-0.066
ane-0.055
owers-0.053
arl-0.053
-0.053
Token good
Token ID922
Feature activation-1.18e+00

Pos logit contributions
wed+0.047
 pretended+0.046
 forgot+0.045
 tried+0.043
 imagined+0.043
Neg logit contributions
arl-0.061
ay-0.060
ummy-0.056
 Today-0.054
elly-0.054
Token children
Token ID1751
Feature activation-1.74e+00

Pos logit contributions
arl+0.032
igsaw+0.031
ay+0.031
+0.031
elly+0.030
Neg logit contributions
 put-0.015
 made-0.014
 never-0.014
 pretended-0.014
 learned-0.014
Token.
Token ID13
Feature activation-3.26e+00

Pos logit contributions
arl+0.036
ay+0.035
elly+0.035
ane+0.034
 Today+0.033
Neg logit contributions
 put-0.032
 pretended-0.031
 never-0.031
 used-0.030
 punished-0.030
Token Now
Token ID2735
Feature activation+2.07e+00

Pos logit contributions
arl+0.059
ay+0.054
ute+0.054
ane+0.054
elly+0.054
Neg logit contributions
 put-0.071
 never-0.070
 learned-0.068
 pretended-0.067
 made-0.067
Token,
Token ID11
Feature activation+2.71e+00

Pos logit contributions
 put+0.032
 pretended+0.032
 never+0.032
 used+0.032
 learned+0.032
Neg logit contributions
arl-0.047
ay-0.046
 Today-0.044
elly-0.044
ane-0.043
Token to
Token ID284
Feature activation+3.90e+00

Pos logit contributions
 put+0.017
 pretended+0.017
 never+0.017
 punished+0.017
 learned+0.016
Neg logit contributions
arl-0.019
ay-0.019
elly-0.019
 Today-0.018
ummy-0.018
Token try
Token ID1949
Feature activation-3.58e-01

Pos logit contributions
 pretended+0.048
 hoped+0.045
 punished+0.044
 never+0.044
 forgot+0.043
Neg logit contributions
arl-0.102
-0.100
 Today-0.098
ay-0.097
ummy-0.095
Token.
Token ID13
Feature activation-2.62e+00

Pos logit contributions
arl+0.009
ay+0.009
elly+0.009
ane+0.008
 Today+0.008
Neg logit contributions
 put-0.005
 never-0.005
 pretended-0.005
 used-0.005
 learned-0.005
Token Lily
Token ID20037
Feature activation+4.72e+00

Pos logit contributions
arl+0.056
ute+0.054
ane+0.053
elly+0.053
ay+0.053
Neg logit contributions
 put-0.050
 never-0.048
 pretended-0.047
 learned-0.046
 used-0.046
Token took
Token ID1718
Feature activation+2.33e+00

Pos logit contributions
ck+0.054
 punished+0.053
 permission+0.052
ts+0.050
 remind+0.049
Neg logit contributions
elly-0.108
-0.106
 Today-0.104
ay-0.104
ummy-0.104
Token a
Token ID257
Feature activation+3.03e-02

Pos logit contributions
 pretended+0.030
 forgot+0.029
 never+0.029
 put+0.029
 hoped+0.028
Neg logit contributions
ay-0.061
arl-0.060
elly-0.058
 Today-0.058
ane-0.056
Token bite
Token ID13197
Feature activation-4.52e+00

Pos logit contributions
 put+0.000
 used+0.000
 tried+0.000
 made+0.000
 cleaned+0.000
Neg logit contributions
arl-0.001
elly-0.001
ane-0.001
arry-0.001
owers-0.001
Token and
Token ID290
Feature activation+6.71e+00

Pos logit contributions
arl+0.099
ay+0.093
elly+0.093
ane+0.091
 Today+0.091
Neg logit contributions
 put-0.083
 never-0.079
 pretended-0.078
 made-0.077
 used-0.077
Token said
Token ID531
Feature activation-8.55e-01

Pos logit contributions
wed+0.071
 punished+0.069
 never+0.068
 permission+0.067
ck+0.062
Neg logit contributions
-0.148
elly-0.140
ummy-0.136
ore-0.135
oles-0.135
Token,
Token ID11
Feature activation+1.87e+00

Pos logit contributions
arl+0.019
elly+0.018
ay+0.018
 Today+0.017
ane+0.017
Neg logit contributions
 put-0.017
 never-0.016
 made-0.016
 learned-0.015
 used-0.015
Token "
Token ID366
Feature activation-8.15e-01

Pos logit contributions
 put+0.037
 never+0.036
 made+0.034
 pretended+0.034
 tried+0.034
Neg logit contributions
elly-0.039
arl-0.039
ay-0.039
ane-0.037
ute-0.037
Token that
Token ID326
Feature activation+1.91e+00

Pos logit contributions
 pretended+0.037
 put+0.037
 learned+0.034
 never+0.034
 punished+0.034
Neg logit contributions
arl-0.062
elly-0.060
ay-0.060
ane-0.059
ute-0.058
Token even
Token ID772
Feature activation+4.14e+00

Pos logit contributions
 pretended+0.024
 put+0.023
 punished+0.023
 hoped+0.023
 forgot+0.022
Neg logit contributions
ay-0.046
 Today-0.046
elly-0.046
ane-0.045
ummy-0.045
Token if
Token ID611
Feature activation+2.10e+00

Pos logit contributions
 never+0.061
 put+0.060
 pretended+0.060
 hoped+0.058
 learned+0.057
Neg logit contributions
arl-0.096
elly-0.095
ay-0.091
 Today-0.089
ane-0.087
Token he
Token ID339
Feature activation+5.88e+00

Pos logit contributions
 pretended+0.030
 put+0.029
 hoped+0.028
 learned+0.028
 never+0.028
Neg logit contributions
arl-0.050
elly-0.049
ay-0.049
ummy-0.048
 Today-0.048
Token struggled
Token ID11615
Feature activation-4.12e-01

Pos logit contributions
 pretended+0.056
 punished+0.054
 put+0.052
 hoped+0.052
 never+0.050
Neg logit contributions
elly-0.152
-0.151
ane-0.151
ay-0.150
ore-0.146
Token,
Token ID11
Feature activation+1.68e+00

Pos logit contributions
arl+0.010
ay+0.009
elly+0.009
 Today+0.009
ane+0.009
Neg logit contributions
 put-0.007
 pretended-0.006
 never-0.006
 learned-0.006
 used-0.006
Token he
Token ID339
Feature activation+6.64e+00

Pos logit contributions
 pretended+0.022
 put+0.022
 hoped+0.021
 punished+0.021
 cleaned+0.021
Neg logit contributions
arl-0.041
ay-0.040
elly-0.040
 Today-0.039
-0.039
Token could
Token ID714
Feature activation+3.05e+00

Pos logit contributions
 pretended+0.096
ck+0.091
 punished+0.091
ts+0.089
 put+0.089
Neg logit contributions
ane-0.145
ay-0.136
-0.132
ore-0.132
elly-0.132
Token still
Token ID991
Feature activation+5.54e+00

Pos logit contributions
 pretended+0.037
 cleaned+0.035
 hoped+0.034
 punished+0.033
 learned+0.033
Neg logit contributions
-0.079
arl-0.077
 Today-0.077
ute-0.076
ay-0.076
Token do
Token ID466
Feature activation+1.14e+00

Pos logit contributions
 pretended+0.067
 cleaned+0.064
 punished+0.063
 put+0.061
 hoped+0.061
Neg logit contributions
-0.137
 Today-0.136
arl-0.135
ay-0.135
ute-0.134
Token great
Token ID1049
Feature activation-1.08e+00

Pos logit contributions
 pretended+0.019
 put+0.018
 cleaned+0.018
 hoped+0.018
 waited+0.017
Neg logit contributions
ay-0.023
igsaw-0.022
elly-0.022
 Today-0.022
arl-0.022
Token.
Token ID13
Feature activation-3.45e+00

Pos logit contributions
 put+0.002
 never+0.002
 used+0.002
 pretended+0.002
 made+0.002
Neg logit contributions
arl-0.003
elly-0.003
ay-0.003
 Today-0.003
arry-0.003
Token
Token ID198
Feature activation-4.35e+00

Pos logit contributions
ane+0.081
ute+0.080
arl+0.078
elly+0.077
ay+0.076
Neg logit contributions
 put-0.057
 learned-0.052
 never-0.052
 used-0.051
 hoped-0.050
Token
Token ID198
Feature activation-3.40e+00

Pos logit contributions
arl+0.091
umm+0.087
ane+0.086
owers+0.086
elly+0.085
Neg logit contributions
 put-0.087
 never-0.085
 learned-0.082
 used-0.079
 made-0.076
TokenOne
Token ID3198
Feature activation+1.49e-01

Pos logit contributions
arl+0.073
ay+0.070
elly+0.069
ane+0.068
 Today+0.067
Neg logit contributions
 put-0.065
 never-0.063
 learned-0.061
 pretended-0.061
 used-0.060
Token day
Token ID1110
Feature activation-2.47e+00

Pos logit contributions
 put+0.003
 never+0.003
 pretended+0.003
 used+0.003
 made+0.003
Neg logit contributions
arl-0.003
ay-0.003
elly-0.003
ane-0.003
-0.003
Token,
Token ID11
Feature activation+3.64e-01

Pos logit contributions
arl+0.061
elly+0.056
ute+0.055
ay+0.054
ane+0.054
Neg logit contributions
 put-0.045
 made-0.043
 tried-0.042
 used-0.042
 pretended-0.041
Token they
Token ID484
Feature activation+7.11e+00

Pos logit contributions
 put+0.005
 never+0.004
 pretended+0.004
 learned+0.004
 used+0.004
Neg logit contributions
arl-0.010
ay-0.010
elly-0.010
 Today-0.009
ane-0.009
Token play
Token ID711
Feature activation-2.92e+00

Pos logit contributions
 never+0.069
 punished+0.069
ck+0.069
 pretended+0.069
 put+0.067
Neg logit contributions
arl-0.187
ay-0.182
ane-0.180
elly-0.177
 Today-0.177
Token match
Token ID2872
Feature activation-2.52e+00

Pos logit contributions
arl+0.075
ay+0.071
elly+0.071
ane+0.069
 Today+0.069
Neg logit contributions
 put-0.044
 never-0.041
 pretended-0.041
 learned-0.040
 used-0.040
Token in
Token ID287
Feature activation+1.48e+00

Pos logit contributions
arl+0.065
ay+0.062
elly+0.062
 Today+0.061
ane+0.060
Neg logit contributions
 put-0.036
 never-0.035
 pretended-0.034
 used-0.033
 learned-0.033
Token the
Token ID262
Feature activation-2.21e+00

Pos logit contributions
 punished+0.016
 forgot+0.016
 pretended+0.016
 never+0.016
 put+0.016
Neg logit contributions
ay-0.040
arl-0.039
elly-0.039
 Today-0.038
igsaw-0.038
TokenL
Token ID43
Feature activation-4.23e+00

Pos logit contributions
ay+0.087
arl+0.085
igsaw+0.083
 Today+0.083
ane+0.083
Neg logit contributions
 put-0.090
 never-0.089
 learned-0.085
 used-0.081
 made-0.079
Tokenily
Token ID813
Feature activation+4.67e+00

Pos logit contributions
arl+0.102
ay+0.099
elly+0.097
 Today+0.095
ane+0.095
Neg logit contributions
 put-0.068
 never-0.065
 pretended-0.064
 learned-0.063
 used-0.062
Token's
Token ID338
Feature activation-7.12e-01

Pos logit contributions
 punished+0.053
 remind+0.052
 permission+0.050
ck+0.048
 never+0.048
Neg logit contributions
elly-0.104
-0.101
ane-0.100
uddle-0.099
olly-0.099
Token mom
Token ID1995
Feature activation+3.88e+00

Pos logit contributions
arl+0.014
ay+0.014
ummy+0.013
 Today+0.013
elly+0.013
Neg logit contributions
 pretended-0.014
 put-0.014
 never-0.014
 punished-0.014
 used-0.014
Token heard
Token ID2982
Feature activation+2.14e-01

Pos logit contributions
 never+0.041
 punished+0.040
 permission+0.038
 pretended+0.038
 remind+0.037
Neg logit contributions
ay-0.092
elly-0.089
arl-0.087
-0.087
omed-0.087
Token her
Token ID607
Feature activation-3.78e-01

Pos logit contributions
 put+0.001
 never+0.001
 pretended+0.001
 made+0.001
 learned+0.001
Neg logit contributions
arl-0.007
elly-0.007
ay-0.007
ane-0.007
ute-0.007
Token and
Token ID290
Feature activation+6.83e+00

Pos logit contributions
arl+0.010
ay+0.010
elly+0.010
ane+0.009
+0.009
Neg logit contributions
 put-0.005
 never-0.005
 pretended-0.005
 learned-0.005
 used-0.005
Token smiled
Token ID13541
Feature activation-1.94e+00

Pos logit contributions
wed+0.097
 never+0.096
 punished+0.094
 pretended+0.089
 remind+0.088
Neg logit contributions
arl-0.145
oms-0.138
arry-0.134
elly-0.134
ay-0.134
Token too
Token ID1165
Feature activation-8.07e-01

Pos logit contributions
arl+0.053
+0.053
ane+0.052
ay+0.051
anger+0.051
Neg logit contributions
 put-0.026
 made-0.024
 learned-0.022
 pretended-0.022
 used-0.022
Token.
Token ID13
Feature activation-3.66e+00

Pos logit contributions
arl+0.023
ay+0.023
ane+0.022
ute+0.022
anger+0.022
Neg logit contributions
 put-0.011
 never-0.010
 used-0.009
 learned-0.009
 made-0.009
Token She
Token ID1375
Feature activation+8.00e+00

Pos logit contributions
ane+0.091
ute+0.091
ay+0.089
igsaw+0.089
andel+0.085
Neg logit contributions
 put-0.058
 hoped-0.055
 learned-0.053
 made-0.053
 wished-0.051
Token butter
Token ID9215
Feature activation-5.27e+00

Pos logit contributions
arl+0.049
ay+0.047
elly+0.047
 Today+0.045
ane+0.045
Neg logit contributions
 put-0.034
 never-0.033
 pretended-0.033
 learned-0.032
 used-0.032
Token around
Token ID1088
Feature activation+2.18e-01

Pos logit contributions
arl+0.121
ay+0.116
elly+0.116
ane+0.112
 Today+0.112
Neg logit contributions
 put-0.088
 never-0.085
 pretended-0.084
 learned-0.082
 used-0.082
Token in
Token ID287
Feature activation+1.94e+00

Pos logit contributions
 put+0.002
 pretended+0.002
 never+0.002
 punished+0.002
 learned+0.002
Neg logit contributions
arl-0.006
ay-0.006
elly-0.006
 Today-0.006
-0.006
Token the
Token ID262
Feature activation-1.71e+00

Pos logit contributions
 punished+0.025
 pretended+0.024
 forgot+0.024
 hoped+0.023
 never+0.023
Neg logit contributions
ay-0.051
arl-0.049
 Today-0.048
elly-0.048
ummy-0.048
Token bowl
Token ID9396
Feature activation-5.43e+00

Pos logit contributions
arl+0.037
ay+0.036
elly+0.035
 Today+0.034
ane+0.034
Neg logit contributions
 put-0.031
 never-0.030
 pretended-0.030
 used-0.029
 learned-0.029
Token.
Token ID13
Feature activation-3.20e+00

Pos logit contributions
arl+0.116
ay+0.112
elly+0.111
 Today+0.107
ane+0.107
Neg logit contributions
 put-0.099
 never-0.096
 pretended-0.095
 learned-0.093
 used-0.093
Token It
Token ID632
Feature activation+5.28e+00

Pos logit contributions
arl+0.073
elly+0.069
ute+0.069
ane+0.066
andel+0.064
Neg logit contributions
 put-0.060
 never-0.057
 used-0.055
 tried-0.055
 pretended-0.054
Token became
Token ID2627
Feature activation+3.46e+00

Pos logit contributions
 punished+0.077
 permission+0.076
 never+0.068
 learned+0.067
 pretended+0.065
Neg logit contributions
ay-0.111
-0.108
elly-0.108
oles-0.104
owers-0.104
Token smoother
Token ID32686
Feature activation-3.14e+00

Pos logit contributions
 never+0.054
 punished+0.053
 pretended+0.053
 learned+0.053
 forgot+0.053
Neg logit contributions
ay-0.073
arl-0.071
elly-0.070
 Today-0.069
ummy-0.069
Token and
Token ID290
Feature activation+6.34e+00

Pos logit contributions
arl+0.066
elly+0.065
ay+0.065
 Today+0.061
ute+0.061
Neg logit contributions
 put-0.056
 never-0.055
 pretended-0.055
 learned-0.054
 punished-0.054
Token more
Token ID517
Feature activation+3.10e-01

Pos logit contributions
 punished+0.096
 pretended+0.093
 learned+0.093
 permission+0.092
 never+0.091
Neg logit contributions
ay-0.123
ummy-0.122
elly-0.117
umm-0.115
arl-0.114
Token and
Token ID290
Feature activation+5.65e+00

Pos logit contributions
arl+0.030
elly+0.028
ay+0.028
ane+0.028
ute+0.028
Neg logit contributions
 put-0.018
 never-0.017
 made-0.017
 used-0.016
 pretended-0.016
Token it
Token ID340
Feature activation+4.11e+00

Pos logit contributions
 punished+0.070
 put+0.067
 pretended+0.067
 learned+0.066
 never+0.065
Neg logit contributions
ay-0.131
ane-0.130
arl-0.129
 Today-0.128
elly-0.127
Token started
Token ID2067
Feature activation+1.24e+00

Pos logit contributions
 permission+0.046
 punished+0.046
 pretended+0.044
wed+0.044
 put+0.043
Neg logit contributions
ay-0.096
elly-0.094
ane-0.094
time-0.091
ute-0.091
Token to
Token ID284
Feature activation+4.20e+00

Pos logit contributions
 put+0.022
 never+0.021
 pretended+0.021
 learned+0.021
 punished+0.021
Neg logit contributions
arl-0.027
ay-0.026
elly-0.026
 Today-0.025
ane-0.025
Token get
Token ID651
Feature activation+2.19e+00

Pos logit contributions
 put+0.070
 pretended+0.069
 learned+0.069
 punished+0.069
 never+0.069
Neg logit contributions
arl-0.092
 Today-0.087
ay-0.086
-0.084
elly-0.084
Token long
Token ID890
Feature activation-2.17e+00

Pos logit contributions
 never+0.043
 put+0.043
 pretended+0.043
 learned+0.043
 hoped+0.042
Neg logit contributions
arl-0.040
ay-0.039
elly-0.037
 Today-0.037
ummy-0.036
Token.
Token ID13
Feature activation-3.21e+00

Pos logit contributions
arl+0.048
ay+0.046
elly+0.046
 Today+0.044
ane+0.044
Neg logit contributions
 put-0.038
 never-0.037
 pretended-0.036
 learned-0.036
 used-0.035
Token
Token ID220
Feature activation-5.49e+00

Pos logit contributions
arl+0.080
ute+0.074
ane+0.073
ay+0.071
elly+0.071
Neg logit contributions
 put-0.055
 never-0.053
 tried-0.051
 learned-0.050
 used-0.049
Token
Token ID198
Feature activation-3.84e+00

Pos logit contributions
arl+0.116
elly+0.114
andel+0.112
umm+0.112
ane+0.108
Neg logit contributions
 put-0.101
 never-0.099
 used-0.094
 learned-0.093
 sure-0.092
Token
Token ID198
Feature activation-3.02e+00

Pos logit contributions
arl+0.082
ane+0.076
ute+0.075
elly+0.074
owers+0.074
Neg logit contributions
 never-0.078
 put-0.075
 learned-0.072
 used-0.071
 tried-0.069
TokenWhen
Token ID2215
Feature activation+4.35e-01

Pos logit contributions
arl+0.069
ay+0.064
ane+0.064
elly+0.063
ute+0.062
Neg logit contributions
 never-0.055
 put-0.055
 learned-0.052
 used-0.051
 pretended-0.050
Token radio
Token ID5243
Feature activation-4.33e+00

Pos logit contributions
arl+0.042
ay+0.040
elly+0.039
 Today+0.039
ane+0.038
Neg logit contributions
 put-0.031
 never-0.030
 pretended-0.030
 learned-0.030
 used-0.029
Token to
Token ID284
Feature activation+3.62e+00

Pos logit contributions
arl+0.100
ay+0.096
elly+0.095
ane+0.093
 Today+0.093
Neg logit contributions
 put-0.071
 never-0.069
 pretended-0.068
 learned-0.067
 used-0.066
Token call
Token ID869
Feature activation-1.68e+00

Pos logit contributions
 pretended+0.037
 remembered+0.035
 forgot+0.035
 learned+0.035
 hoped+0.034
Neg logit contributions
arl-0.104
ay-0.100
 Today-0.096
ute-0.096
-0.094
Token them
Token ID606
Feature activation-1.54e+00

Pos logit contributions
arl+0.048
elly+0.047
ay+0.046
+0.045
ane+0.045
Neg logit contributions
 put-0.020
 never-0.018
 pretended-0.017
 made-0.017
 learned-0.017
Token."
Token ID526
Feature activation-4.79e+00

Pos logit contributions
arl+0.040
elly+0.039
+0.039
ay+0.038
igsaw+0.038
Neg logit contributions
 put-0.023
 never-0.021
 pretended-0.021
 used-0.020
 made-0.020
Token
Token ID198
Feature activation-5.27e+00

Pos logit contributions
arl+0.104
ute+0.102
ane+0.101
elly+0.100
andel+0.098
Neg logit contributions
 put-0.094
 learned-0.087
 tried-0.086
 used-0.086
 never-0.085
Token
Token ID198
Feature activation-4.06e+00

Pos logit contributions
arl+0.100
elly+0.099
ane+0.098
owers+0.095
ay+0.093
Neg logit contributions
 put-0.116
 never-0.111
 learned-0.108
 used-0.106
 tried-0.104
TokenHe
Token ID1544
Feature activation+7.46e+00

Pos logit contributions
arl+0.082
ay+0.078
elly+0.077
arry+0.075
 Today+0.074
Neg logit contributions
 put-0.078
 pretended-0.077
 never-0.075
 made-0.074
 used-0.073
Token took
Token ID1718
Feature activation+2.28e+00

Pos logit contributions
 never+0.063
 punished+0.062
 remind+0.056
 care+0.055
eling+0.055
Neg logit contributions
arl-0.194
ay-0.190
elly-0.189
arry-0.187
anger-0.185
Token them
Token ID606
Feature activation-1.04e+00

Pos logit contributions
 forgot+0.031
 pretended+0.030
 never+0.030
 learned+0.029
 remembered+0.029
Neg logit contributions
ay-0.059
arl-0.057
elly-0.053
andel-0.052
 Today-0.052
Token by
Token ID416
Feature activation-3.73e-01

Pos logit contributions
arl+0.022
ay+0.021
elly+0.020
ane+0.020
 Today+0.020
Neg logit contributions
 put-0.018
 pretended-0.018
 forgot-0.018
 never-0.018
 punished-0.017
Token back
Token ID736
Feature activation-1.20e+00

Pos logit contributions
arl+0.013
elly+0.013
+0.012
ane+0.012
arry+0.012
Neg logit contributions
 put-0.010
 never-0.010
 used-0.010
 made-0.009
 learned-0.009
Token.
Token ID13
Feature activation-4.21e+00

Pos logit contributions
+0.031
arl+0.031
elly+0.030
owers+0.029
ane+0.029
Neg logit contributions
 put-0.017
 never-0.016
 used-0.015
 made-0.015
 pretended-0.015
Token
Token ID198
Feature activation-5.04e+00

Pos logit contributions
arl+0.097
elly+0.089
ifying+0.084
andel+0.084
ute+0.083
Neg logit contributions
 put-0.078
 never-0.073
 used-0.071
 made-0.069
 found-0.069
Token
Token ID198
Feature activation-3.83e+00

Pos logit contributions
arl+0.118
umm+0.110
ifying+0.106
elly+0.105
owers+0.105
Neg logit contributions
 put-0.093
 never-0.092
 used-0.086
 learned-0.085
 found-0.085
TokenOne
Token ID3198
Feature activation-8.00e-01

Pos logit contributions
arl+0.081
elly+0.073
ay+0.073
+0.072
ane+0.072
Neg logit contributions
 put-0.077
 never-0.076
 used-0.072
 learned-0.071
 made-0.071
Token day
Token ID1110
Feature activation-2.57e+00

Pos logit contributions
arl+0.018
+0.017
ay+0.017
elly+0.017
ane+0.017
Neg logit contributions
 put-0.015
 never-0.014
 made-0.014
 pretended-0.014
 used-0.014
Token,
Token ID11
Feature activation-6.88e-01

Pos logit contributions
arl+0.060
elly+0.055
ane+0.053
ay+0.053
ute+0.053
Neg logit contributions
 put-0.050
 made-0.046
 used-0.046
 pretended-0.046
 tried-0.045
Token Sus
Token ID8932
Feature activation-2.87e-01

Pos logit contributions
ay+0.016
arl+0.016
elly+0.016
 Today+0.015
+0.015
Neg logit contributions
 put-0.010
 never-0.010
 learned-0.010
 punished-0.010
 pretended-0.010
Tokenie
Token ID494
Feature activation+4.08e+00

Pos logit contributions
elly+0.006
ane+0.006
arl+0.006
ay+0.006
ummy+0.006
Neg logit contributions
 put-0.005
 pretended-0.005
 never-0.005
 punished-0.004
 learned-0.004
Token wanted
Token ID2227
Feature activation+7.94e-01

Pos logit contributions
 put+0.043
 never+0.042
 punished+0.042
 pretended+0.041
ck+0.040
Neg logit contributions
elly-0.105
ane-0.101
ay-0.101
 Today-0.101
arl-0.099
Token to
Token ID284
Feature activation+3.47e+00

Pos logit contributions
 pretended+0.017
 forgot+0.016
 put+0.016
 punished+0.016
 hoped+0.016
Neg logit contributions
elly-0.013
ay-0.013
arl-0.013
ane-0.013
 Today-0.013
Token out
Token ID503
Feature activation-2.35e+00

Pos logit contributions
arl+0.110
elly+0.106
arry+0.105
ane+0.104
ay+0.103
Neg logit contributions
 put-0.057
 never-0.055
 made-0.052
 used-0.052
 pretended-0.052
Token of
Token ID286
Feature activation+1.55e+00

Pos logit contributions
arl+0.055
elly+0.053
ay+0.053
 Today+0.051
ane+0.051
Neg logit contributions
 put-0.039
 never-0.038
 pretended-0.036
 used-0.036
 made-0.036
Token the
Token ID262
Feature activation-2.91e+00

Pos logit contributions
 pretended+0.021
 forgot+0.021
 learned+0.020
 remembered+0.020
 shared+0.020
Neg logit contributions
arl-0.038
ay-0.038
ummy-0.036
elly-0.036
igsaw-0.035
Token window
Token ID4324
Feature activation-6.61e+00

Pos logit contributions
arl+0.067
arry+0.064
ane+0.064
ay+0.063
elly+0.063
Neg logit contributions
 put-0.051
 never-0.048
 made-0.047
 used-0.046
 cleaned-0.046
Token!"
Token ID2474
Feature activation-4.52e+00

Pos logit contributions
arl+0.164
elly+0.154
ay+0.154
+0.151
ute+0.151
Neg logit contributions
 put-0.103
 never-0.100
 pretended-0.096
 made-0.096
 used-0.094
Token
Token ID198
Feature activation-6.13e+00

Pos logit contributions
arl+0.095
andel+0.091
ute+0.091
elly+0.091
ane+0.089
Neg logit contributions
 put-0.090
 learned-0.088
 never-0.086
 tried-0.084
 made-0.082
Token
Token ID198
Feature activation-4.79e+00

Pos logit contributions
arl+0.117
elly+0.115
owers+0.113
ane+0.112
andel+0.112
Neg logit contributions
 put-0.133
 never-0.132
 learned-0.128
 cleaned-0.120
 used-0.119
TokenTom
Token ID13787
Feature activation+4.02e+00

Pos logit contributions
arl+0.094
ay+0.090
elly+0.089
 Today+0.086
ane+0.085
Neg logit contributions
 put-0.097
 pretended-0.094
 never-0.093
 used-0.092
 made-0.090
Token was
Token ID373
Feature activation+4.72e+00

Pos logit contributions
 remind+0.047
 pretended+0.044
 punished+0.044
ts+0.042
ck+0.041
Neg logit contributions
ay-0.092
arry-0.090
uddle-0.088
elly-0.087
-0.087
Token very
Token ID845
Feature activation+3.90e+00

Pos logit contributions
 pretended+0.081
wed+0.074
 forgot+0.074
 wrote+0.073
 put+0.073
Neg logit contributions
 Today-0.088
apping-0.088
arl-0.087
elly-0.083
-0.083
Token scared
Token ID12008
Feature activation-2.32e+00

Pos logit contributions
 pretended+0.060
 put+0.059
 never+0.058
 made+0.055
 used+0.054
Neg logit contributions
arl-0.094
elly-0.090
ay-0.087
 Today-0.086
ute-0.085
Token about
Token ID546
Feature activation+2.72e+00

Pos logit contributions
 put+0.011
 pretended+0.011
 never+0.011
 used+0.010
 punished+0.010
Neg logit contributions
arl-0.016
ay-0.015
elly-0.015
 Today-0.015
ane-0.015
Token her
Token ID607
Feature activation-2.66e-01

Pos logit contributions
 pretended+0.028
 put+0.028
 punished+0.027
 forgot+0.026
 cleaned+0.026
Neg logit contributions
arl-0.076
ay-0.074
 Today-0.073
elly-0.073
-0.072
Token sailing
Token ID28499
Feature activation-3.35e+00

Pos logit contributions
arl+0.006
ay+0.006
elly+0.006
 Today+0.006
ane+0.006
Neg logit contributions
 put-0.004
 never-0.004
 pretended-0.004
 learned-0.004
 used-0.004
Token adventure
Token ID8855
Feature activation-3.49e+00

Pos logit contributions
arl+0.078
elly+0.074
ay+0.073
 Today+0.071
arry+0.070
Neg logit contributions
 put-0.059
 never-0.056
 made-0.055
 pretended-0.055
 used-0.054
Token.
Token ID13
Feature activation-3.03e+00

Pos logit contributions
arl+0.083
elly+0.078
ay+0.077
 Today+0.076
ane+0.075
Neg logit contributions
 put-0.059
 never-0.057
 pretended-0.055
 used-0.055
 made-0.055
Token<|endoftext|>
Token ID50256
Feature activation-8.43e+00

Pos logit contributions
arl+0.063
ute+0.062
ane+0.059
elly+0.058
andel+0.057
Neg logit contributions
 never-0.059
 put-0.058
 learned-0.057
 hoped-0.055
 used-0.054
TokenOne
Token ID3198
Feature activation-5.85e-01

Pos logit contributions
arl+0.197
andel+0.194
ower+0.181
ute+0.180
igsaw+0.177
Neg logit contributions
 made-0.159
 put-0.155
 found-0.154
 used-0.152
 tried-0.149
Token day
Token ID1110
Feature activation-1.66e+00

Pos logit contributions
arl+0.012
elly+0.011
ay+0.011
ane+0.011
 Today+0.011
Neg logit contributions
 put-0.012
 never-0.011
 pretended-0.011
 learned-0.011
 used-0.011
Token,
Token ID11
Feature activation-2.12e+00

Pos logit contributions
arl+0.041
elly+0.038
ay+0.037
ane+0.037
ute+0.036
Neg logit contributions
 put-0.030
 tried-0.028
 made-0.028
 used-0.028
 never-0.028
Token Mrs
Token ID9074
Feature activation-6.15e+00

Pos logit contributions
arl+0.071
elly+0.066
ay+0.066
ane+0.066
ute+0.064
Neg logit contributions
 put-0.019
 never-0.018
 used-0.017
 pretended-0.016
 made-0.016
Token.
Token ID13
Feature activation-6.39e+00

Pos logit contributions
arl+0.151
ay+0.143
ute+0.141
elly+0.140
ane+0.139
Neg logit contributions
 put-0.099
 never-0.092
 pretended-0.091
 used-0.091
 made-0.090
Token he
Token ID339
Feature activation+8.10e+00

Pos logit contributions
wed+0.095
wy+0.087
ws+0.087
ps+0.087
ck+0.085
Neg logit contributions
aris-0.105
ay-0.105
 Nice-0.104
ogging-0.101
arry-0.099
Token laughed
Token ID13818
Feature activation-1.83e+00

Pos logit contributions
 permission+0.101
 punished+0.087
 remind+0.087
ts+0.085
eling+0.085
Neg logit contributions
ane-0.169
ute-0.167
ay-0.166
uddle-0.160
arry-0.160
Token and
Token ID290
Feature activation+6.83e+00

Pos logit contributions
arl+0.042
ay+0.041
elly+0.040
 Today+0.040
ane+0.039
Neg logit contributions
 put-0.030
 never-0.029
 pretended-0.028
 punished-0.028
 learned-0.028
Token laughed
Token ID13818
Feature activation-1.79e+00

Pos logit contributions
wed+0.082
 punished+0.079
wy+0.078
 permission+0.074
eling+0.072
Neg logit contributions
 Nice-0.141
 Today-0.136
ogging-0.134
ay-0.134
apping-0.133
Token.
Token ID13
Feature activation-3.97e+00

Pos logit contributions
arl+0.041
ay+0.040
elly+0.040
 Today+0.039
ane+0.038
Neg logit contributions
 put-0.029
 never-0.028
 pretended-0.028
 learned-0.027
 used-0.027
Token<|endoftext|>
Token ID50256
Feature activation-8.43e+00

Pos logit contributions
arl+0.076
elly+0.072
ay+0.072
ane+0.069
ute+0.069
Neg logit contributions
 put-0.084
 never-0.081
 pretended-0.080
 learned-0.079
 used-0.079
TokenOnce
Token ID7454
Feature activation-5.54e+00

Pos logit contributions
arl+0.218
andel+0.213
ute+0.209
ower+0.203
elly+0.203
Neg logit contributions
 put-0.139
 made-0.136
 never-0.134
 found-0.131
 used-0.130
Token upon
Token ID2402
Feature activation-1.49e+00

Pos logit contributions
arl+0.099
elly+0.093
+0.090
owers+0.089
ay+0.089
Neg logit contributions
 put-0.124
 never-0.121
 used-0.117
 made-0.117
 pretended-0.116
Token a
Token ID257
Feature activation-4.86e+00

Pos logit contributions
arl+0.041
ay+0.040
elly+0.040
 Today+0.039
ane+0.039
Neg logit contributions
 put-0.017
 pretended-0.016
 never-0.016
 punished-0.016
 used-0.015
Token time
Token ID640
Feature activation-4.50e+00

Pos logit contributions
ane+0.108
arl+0.106
anger+0.102
ute+0.100
owers+0.099
Neg logit contributions
 put-0.092
 never-0.092
 learned-0.085
 made-0.085
 pretended-0.085
Token,
Token ID11
Feature activation-2.95e+00

Pos logit contributions
arl+0.133
andel+0.130
umm+0.126
elly+0.125
ute+0.124
Neg logit contributions
 never-0.056
 put-0.053
 tried-0.052
 found-0.052
 made-0.052
Token when
Token ID618
Feature activation+4.53e-01

Pos logit contributions
arl+0.057
ay+0.055
elly+0.054
 Today+0.052
ute+0.052
Neg logit contributions
 pretended-0.051
 put-0.050
 never-0.050
 learned-0.050
 hoped-0.049
Token he
Token ID339
Feature activation+4.88e+00

Pos logit contributions
 put+0.006
 pretended+0.006
 never+0.006
 punished+0.006
 learned+0.006
Neg logit contributions
arl-0.011
elly-0.011
ay-0.010
 Today-0.010
ane-0.010
Token needed
Token ID2622
Feature activation+1.24e+00

Pos logit contributions
 put+0.048
 never+0.048
 pretended+0.047
 punished+0.045
 cleaned+0.043
Neg logit contributions
arl-0.135
ay-0.134
elly-0.134
ane-0.130
-0.129
Token it
Token ID340
Feature activation-9.24e-01

Pos logit contributions
 pretended+0.016
 forgot+0.015
 put+0.014
 hoped+0.014
 punished+0.014
Neg logit contributions
arl-0.032
ay-0.032
-0.031
elly-0.031
 Today-0.030
Token.
Token ID13
Feature activation-3.55e+00

Pos logit contributions
arl+0.019
ay+0.018
elly+0.018
 Today+0.018
ane+0.017
Neg logit contributions
 put-0.017
 pretended-0.017
 never-0.017
 learned-0.016
 punished-0.016
Token<|endoftext|>
Token ID50256
Feature activation-8.75e+00

Pos logit contributions
arl+0.074
ute+0.070
andel+0.069
elly+0.068
ane+0.068
Neg logit contributions
 never-0.069
 put-0.068
 learned-0.068
 made-0.066
 used-0.066
TokenOne
Token ID3198
Feature activation-9.45e-01

Pos logit contributions
arl+0.229
andel+0.227
ute+0.217
ower+0.217
umm+0.216
Neg logit contributions
 put-0.141
 made-0.138
 never-0.132
 used-0.131
 found-0.130
Token day
Token ID1110
Feature activation-1.98e+00

Pos logit contributions
arl+0.019
ay+0.018
elly+0.018
 Today+0.017
ane+0.017
Neg logit contributions
 put-0.019
 never-0.018
 pretended-0.018
 used-0.018
 learned-0.018
Token,
Token ID11
Feature activation-2.47e+00

Pos logit contributions
arl+0.048
elly+0.045
andel+0.045
ane+0.044
ay+0.044
Neg logit contributions
 put-0.035
 made-0.033
 tried-0.033
 used-0.033
 never-0.031
Token a
Token ID257
Feature activation-2.85e+00

Pos logit contributions
arl+0.075
elly+0.072
ay+0.072
ane+0.071
ute+0.070
Neg logit contributions
 put-0.026
 never-0.024
 pretended-0.023
 used-0.023
 made-0.023
Token boy
Token ID2933
Feature activation+5.01e-01

Pos logit contributions
arl+0.068
ane+0.068
 Today+0.066
ay+0.066
anger+0.065
Neg logit contributions
 put-0.049
 used-0.043
 made-0.042
 cleaned-0.041
 pretended-0.041
Token blue
Token ID4171
Feature activation-6.37e+00

Pos logit contributions
arl+0.088
elly+0.081
ay+0.079
+0.078
arry+0.078
Neg logit contributions
 put-0.072
 never-0.068
 made-0.068
 pretended-0.066
 used-0.066
Token wings
Token ID12098
Feature activation-2.68e+00

Pos logit contributions
arl+0.162
igsaw+0.148
elly+0.146
aris+0.144
arry+0.143
Neg logit contributions
 put-0.105
 made-0.103
 never-0.099
 tried-0.095
 used-0.095
Token of
Token ID286
Feature activation+1.10e+00

Pos logit contributions
arl+0.058
ay+0.057
elly+0.055
ane+0.055
 Today+0.054
Neg logit contributions
 put-0.045
 pretended-0.045
 punished-0.044
 never-0.044
 learned-0.043
Token the
Token ID262
Feature activation-3.19e+00

Pos logit contributions
 put+0.014
 pretended+0.014
 punished+0.014
 never+0.014
 forgot+0.014
Neg logit contributions
arl-0.028
ay-0.028
elly-0.027
 Today-0.026
ane-0.026
Token bird
Token ID6512
Feature activation-1.64e+00

Pos logit contributions
arl+0.059
elly+0.055
ay+0.054
arry+0.053
 Today+0.052
Neg logit contributions
 put-0.072
 never-0.070
 made-0.068
 pretended-0.068
 used-0.068
Token fl
Token ID781
Feature activation-8.15e+00

Pos logit contributions
arl+0.038
ay+0.038
elly+0.037
 Today+0.036
ane+0.036
Neg logit contributions
 put-0.026
 never-0.025
 pretended-0.025
 punished-0.024
 learned-0.024
Tokenapping
Token ID5912
Feature activation-2.60e+00

Pos logit contributions
 Today+0.085
igsaw+0.075
elly+0.072
arl+0.071
 Pole+0.066
Neg logit contributions
 never-0.219
 put-0.219
 used-0.216
ck-0.213
 made-0.210
Token around
Token ID1088
Feature activation+4.08e-01

Pos logit contributions
arl+0.064
ay+0.063
elly+0.061
 Today+0.060
ane+0.060
Neg logit contributions
 put-0.038
 pretended-0.036
 never-0.036
 punished-0.036
 learned-0.035
Token.
Token ID13
Feature activation-3.99e+00

Pos logit contributions
 put+0.007
 never+0.006
 pretended+0.006
 used+0.006
 learned+0.006
Neg logit contributions
arl-0.010
ay-0.009
elly-0.009
ane-0.009
 Today-0.009
Token He
Token ID679
Feature activation+7.68e+00

Pos logit contributions
arl+0.087
elly+0.081
ute+0.080
ay+0.079
ane+0.079
Neg logit contributions
 put-0.077
 learned-0.073
 never-0.073
 used-0.072
 pretended-0.072
Token had
Token ID550
Feature activation+4.93e+00

Pos logit contributions
 punished+0.103
 permission+0.089
 cleaned+0.089
wed+0.088
 remind+0.087
Neg logit contributions
ay-0.170
arry-0.167
oles-0.166
elly-0.165
ute-0.164
Token crown
Token ID12389
Feature activation-4.72e+00

Pos logit contributions
 put+0.014
 never+0.013
 pretended+0.013
 used+0.013
 learned+0.013
Neg logit contributions
arl-0.019
ay-0.018
elly-0.018
 Today-0.018
ane-0.018
Token and
Token ID290
Feature activation+6.01e+00

Pos logit contributions
arl+0.113
elly+0.109
ay+0.107
 Today+0.106
arry+0.104
Neg logit contributions
 put-0.076
 never-0.074
 pretended-0.072
 made-0.071
 used-0.070
Token a
Token ID257
Feature activation+1.45e+00

Pos logit contributions
 punished+0.078
ck+0.076
wed+0.072
 put+0.071
 cleaned+0.070
Neg logit contributions
ay-0.141
ane-0.133
elly-0.130
 Today-0.127
ummy-0.127
Token swing
Token ID9628
Feature activation-3.92e+00

Pos logit contributions
 put+0.024
 never+0.023
 pretended+0.023
 used+0.022
 learned+0.022
Neg logit contributions
arl-0.034
ay-0.032
elly-0.032
 Today-0.031
ane-0.031
Token.
Token ID13
Feature activation-3.01e+00

Pos logit contributions
arl+0.094
elly+0.089
 Today+0.087
ay+0.087
arry+0.086
Neg logit contributions
 put-0.065
 never-0.063
 made-0.061
 pretended-0.060
 used-0.059
Token<|endoftext|>
Token ID50256
Feature activation-8.46e+00

Pos logit contributions
arl+0.056
elly+0.053
ute+0.050
ay+0.050
ane+0.049
Neg logit contributions
 never-0.066
 put-0.066
 learned-0.062
 hoped-0.062
 made-0.062
TokenOnce
Token ID7454
Feature activation-5.16e+00

Pos logit contributions
arl+0.186
andel+0.181
ower+0.169
ute+0.169
igsaw+0.166
Neg logit contributions
 made-0.171
 put-0.168
 found-0.167
 used-0.163
 tried-0.161
Token there
Token ID612
Feature activation-1.25e+00

Pos logit contributions
arl+0.099
elly+0.093
+0.090
ute+0.088
umm+0.088
Neg logit contributions
 put-0.109
 never-0.107
 made-0.104
 used-0.102
 forgot-0.102
Token was
Token ID373
Feature activation-3.48e-01

Pos logit contributions
ay+0.032
arl+0.031
 Today+0.031
elly+0.031
ane+0.031
Neg logit contributions
 put-0.016
 punished-0.015
 pretended-0.015
 never-0.015
 used-0.015
Token a
Token ID257
Feature activation-2.27e+00

Pos logit contributions
arl+0.011
ay+0.010
elly+0.010
ane+0.010
arry+0.010
Neg logit contributions
 put-0.003
 never-0.003
 pretended-0.003
 used-0.003
 learned-0.003
Token boy
Token ID2933
Feature activation-6.32e-01

Pos logit contributions
arl+0.053
ane+0.051
ay+0.051
owers+0.050
elly+0.049
Neg logit contributions
 put-0.042
 used-0.037
 never-0.037
 pretended-0.037
 made-0.036