TOP ACTIVATIONS
MAX = 4.358

careless . They learned a hard lesson . The end .
mom . They learned a hard lesson . They did not
dog . They learned a hard lesson . Not all dogs
eating . They learned a hard lesson . They said ,
mystery . They learned a hard lesson . They learned that
alert . They learned a hard lesson . They never stole
treasure . They learned a hard lesson . They should have
mom . They learned a hard lesson . <|endoftext|> It was
bulb . They learned a hard lesson . The fox was
day . They learned a hard lesson . Fire is not
bs . They learned a hard lesson . <|endoftext|> L ily
honest . They learned a hard lesson . <|endoftext|> L ily
mistake . They learned a hard lesson . They should never
animals . She learned a hard lesson . She was not
Tom and Lily learned a hard lesson . They never climbed
okay . They learned a hard lesson . They were poor
cookies . They learned a hard lesson . They had a
toys . They learned a hard lesson : lying is bad
day . They learned a hard lesson . They should not
jumped . They learned a hard lesson that day . They

MIN ACTIVATIONS
MIN = -3.952

never wanted to leave the group again . They were so
and the deer was never bored again . <|endoftext|> One day
extra careful and never leave anyone behind . <|endoftext|> Once upon
she had never sung in front of anyone before . But
sail his boat in the big blue sea . One day
the old cat was never seen again . <|endoftext|> Once upon
L ily and Ben were twins who liked to play outside
said , " Hi , can I play with you ?"
on , Jane was never bored . She had many smooth
away , never to be seen again . The
, " Hi Pedro , can I ride you ?" Pedro
. " M ummy , can I ride in it ?"
said , " Hi , can I play with you ?"
" Hello little bird , can you pass me a tw
the small gorilla was never seen again . <|endoftext|> Once upon
The original city was never seen again . <|endoftext|> Once upon
They thought , " How can I make the boats go
. " How can we get the jet back
." " How can you talk to a bird
to think . " How can I roll like the ball

INTERVAL 2.280 - 4.358
CONTAINS 0.066%

, gru ff voice calling her name . She looked up
in the blankets and made a tent on the floor .
and scared . They worked hard to find food and help
Spot . Spot had a long tail that w agged when
. She learned that it 's important to help others and

INTERVAL 0.203 - 2.280
CONTAINS 37.217%

unknown adventure . When they arrived at the park
. Her mom listened and put some ice in the lemon
M ummy ! Look at me ! â € Beth exclaimed
day . They were the best of friends . <|endoftext|> One
Lu cy walked around the attic and noticed

INTERVAL -1.874 - 0.203
CONTAINS 62.387%

wanted to take a big challenge and he decided to catch
it and I just keep trying ." Blue thought
one of your toys or books ." Ben thinks for a
she was there and she said she just wanted to stay
Jill was counting slowly . She looked around and saw a

INTERVAL -3.952 - -1.874
CONTAINS 0.330%

Hey , that 's my ball ! Why did you kick
dog was gone and he felt much better . He played
The ghost said , " Let me help you un pack
Will you swing me too ?" The man laughed
skip . She skipped everywhere she went , even to the
Token careless
Token ID36138
Feature activation+1.31e-01

Pos logit contributions
ages+0.000
zag+0.000
tr+0.000
ained+0.000
ometer+0.000
Neg logit contributions
ivated-0.000
ternally-0.000
 unatt-0.000
 My-0.000
 en-0.000
Token.
Token ID13
Feature activation+3.71e-01

Pos logit contributions
zag+0.005
ages+0.005
tr+0.005
ained+0.005
ometer+0.005
Neg logit contributions
ivated-0.004
 unatt-0.004
 en-0.004
 My-0.004
ternally-0.004
Token They
Token ID1119
Feature activation+3.88e-01

Pos logit contributions
zag+0.014
ages+0.014
tr+0.013
ained+0.013
ometer+0.012
Neg logit contributions
 My-0.013
 en-0.013
ivated-0.012
 I-0.012
 unatt-0.012
Token learned
Token ID4499
Feature activation+1.95e+00

Pos logit contributions
zag+0.016
ages+0.016
ained+0.015
tr+0.015
ometer+0.014
Neg logit contributions
 en-0.012
ivated-0.012
 unatt-0.012
 My-0.012
ternally-0.012
Token a
Token ID257
Feature activation+2.89e+00

Pos logit contributions
zag+0.099
ops+0.098
ages+0.094
ained+0.093
ahs+0.092
Neg logit contributions
 back-0.047
 I-0.044
 My-0.043
 en-0.043
 me-0.042
Token hard
Token ID1327
Feature activation+4.36e+00

Pos logit contributions
packs+0.114
ained+0.112
aked+0.106
ates+0.105
ages+0.101
Neg logit contributions
 back-0.102
 en-0.098
 else-0.095
 me-0.094
 I-0.092
Token lesson
Token ID11483
Feature activation+2.16e+00

Pos logit contributions
aj+0.180
packs+0.160
ccoli+0.158
akers+0.153
ends+0.152
Neg logit contributions
 back-0.133
 tune-0.132
's-0.127
 corner-0.124
 voice-0.124
Token.
Token ID13
Feature activation+9.76e-01

Pos logit contributions
ages+0.128
ccoli+0.128
zag+0.126
aj+0.124
tr+0.124
Neg logit contributions
 alone-0.034
 I-0.031
 back-0.026
 else-0.025
 unatt-0.025
Token The
Token ID383
Feature activation+9.60e-01

Pos logit contributions
zag+0.041
ages+0.039
tr+0.036
ained+0.035
tails+0.035
Neg logit contributions
 My-0.034
 I-0.033
 en-0.032
 alone-0.030
 Int-0.030
Token end
Token ID886
Feature activation+1.69e+00

Pos logit contributions
ages+0.040
zag+0.040
ccoli+0.036
tails+0.036
ometer+0.035
Neg logit contributions
 en-0.031
 unatt-0.030
 me-0.030
 alone-0.030
 I-0.029
Token.
Token ID13
Feature activation+7.88e-01

Pos logit contributions
ages+0.098
ained+0.093
zag+0.092
tails+0.089
live+0.089
Neg logit contributions
 I-0.028
 alone-0.026
 else-0.025
 My-0.023
 me-0.023
Token mom
Token ID1995
Feature activation+2.38e-01

Pos logit contributions
ages+0.055
zag+0.054
ained+0.053
tr+0.049
ine+0.049
Neg logit contributions
 en-0.029
 alone-0.029
 unatt-0.028
 me-0.028
 cheer-0.027
Token.
Token ID13
Feature activation+8.57e-01

Pos logit contributions
zag+0.010
ages+0.010
tr+0.009
ained+0.009
ometer+0.009
Neg logit contributions
 unatt-0.007
ivated-0.007
 en-0.007
 My-0.007
ternally-0.007
Token They
Token ID1119
Feature activation+5.30e-01

Pos logit contributions
zag+0.036
ages+0.034
ained+0.031
tr+0.031
olving+0.030
Neg logit contributions
 My-0.029
 I-0.029
 en-0.028
 Int-0.027
 alone-0.027
Token learned
Token ID4499
Feature activation+1.89e+00

Pos logit contributions
zag+0.026
ages+0.025
ained+0.024
tr+0.023
ometer+0.023
Neg logit contributions
 en-0.014
 unatt-0.013
ivated-0.013
 alone-0.013
ternally-0.013
Token a
Token ID257
Feature activation+2.74e+00

Pos logit contributions
zag+0.101
ages+0.093
ops+0.093
live+0.090
ccoli+0.089
Neg logit contributions
 back-0.045
 en-0.041
 I-0.041
 me-0.041
 alone-0.040
Token hard
Token ID1327
Feature activation+4.29e+00

Pos logit contributions
ained+0.098
packs+0.097
ops+0.095
aked+0.095
ages+0.094
Neg logit contributions
 back-0.099
 calm-0.097
 en-0.095
 I-0.094
 cheer-0.093
Token lesson
Token ID11483
Feature activation+1.84e+00

Pos logit contributions
aj+0.182
ends+0.166
packs+0.163
girls+0.161
live+0.161
Neg logit contributions
 voice-0.126
 tune-0.121
 fright-0.120
 corner-0.120
 back-0.117
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
zag+0.104
ages+0.103
ccoli+0.101
tr+0.100
aj+0.098
Neg logit contributions
 alone-0.034
 I-0.033
 unatt-0.028
 back-0.027
 me-0.025
Token They
Token ID1119
Feature activation+1.15e+00

Pos logit contributions
zag+0.044
ages+0.041
ahs+0.037
tr+0.037
tails+0.037
Neg logit contributions
 I-0.041
 My-0.040
 en-0.038
 alone-0.036
 Int-0.036
Token did
Token ID750
Feature activation+2.48e+00

Pos logit contributions
zag+0.056
ages+0.053
ained+0.051
ccoli+0.050
ometer+0.050
Neg logit contributions
 en-0.030
 alone-0.029
 unatt-0.028
 I-0.028
ternally-0.028
Token not
Token ID407
Feature activation+1.05e+00

Pos logit contributions
aked+0.133
uns+0.132
inea+0.131
mons+0.130
ages+0.129
Neg logit contributions
 back-0.058
 alone-0.054
 I-0.052
 calm-0.050
 me-0.050
Token dog
Token ID3290
Feature activation-5.33e-01

Pos logit contributions
ages+0.033
zag+0.033
ained+0.030
ccoli+0.030
tr+0.029
Neg logit contributions
 en-0.017
 unatt-0.017
 alone-0.017
 I-0.016
 My-0.016
Token.
Token ID13
Feature activation+5.38e-01

Pos logit contributions
ternally+0.018
ivated+0.018
 en+0.018
 My+0.018
 unatt+0.017
Neg logit contributions
zag-0.020
ages-0.020
tr-0.019
ained-0.018
ometer-0.018
Token They
Token ID1119
Feature activation+4.54e-01

Pos logit contributions
zag+0.019
ages+0.019
tr+0.017
ained+0.017
tails+0.016
Neg logit contributions
 My-0.021
 en-0.020
 I-0.020
ivated-0.020
 alone-0.020
Token learned
Token ID4499
Feature activation+1.70e+00

Pos logit contributions
zag+0.022
ages+0.021
ained+0.020
tr+0.020
ometer+0.020
Neg logit contributions
 en-0.011
 unatt-0.011
ivated-0.011
ternally-0.011
 My-0.011
Token a
Token ID257
Feature activation+2.99e+00

Pos logit contributions
zag+0.088
ops+0.084
ages+0.082
ained+0.081
ahs+0.080
Neg logit contributions
 back-0.040
 I-0.039
 en-0.039
 My-0.038
 alone-0.037
Token hard
Token ID1327
Feature activation+4.29e+00

Pos logit contributions
packs+0.114
ained+0.109
aked+0.102
aj+0.102
ates+0.101
Neg logit contributions
 back-0.106
 en-0.106
 else-0.104
 I-0.101
 calm-0.100
Token lesson
Token ID11483
Feature activation+1.97e+00

Pos logit contributions
aj+0.184
packs+0.167
ccoli+0.162
ends+0.160
akers+0.157
Neg logit contributions
 tune-0.128
 back-0.123
 corner-0.119
 voice-0.116
 alone-0.114
Token.
Token ID13
Feature activation+8.65e-01

Pos logit contributions
ages+0.114
zag+0.113
ccoli+0.113
tr+0.111
aj+0.111
Neg logit contributions
 alone-0.032
 I-0.030
 else-0.025
 unatt-0.025
 back-0.025
Token Not
Token ID1892
Feature activation+1.96e+00

Pos logit contributions
zag+0.034
ages+0.033
tr+0.030
tails+0.029
ained+0.029
Neg logit contributions
 My-0.032
 I-0.032
 en-0.030
 alone-0.029
 Int-0.029
Token all
Token ID477
Feature activation+6.90e-01

Pos logit contributions
zag+0.095
ages+0.094
aj+0.091
ine+0.091
tails+0.090
Neg logit contributions
 I-0.056
 alone-0.054
 en-0.054
 me-0.050
 else-0.049
Token dogs
Token ID6844
Feature activation-3.53e-01

Pos logit contributions
zag+0.030
ages+0.029
tr+0.028
ained+0.027
ometer+0.026
Neg logit contributions
 I-0.021
 alone-0.021
 en-0.021
 My-0.020
ternally-0.019
Token eating
Token ID6600
Feature activation+4.45e-01

Pos logit contributions
zag+0.051
ages+0.050
tr+0.050
ometer+0.046
ained+0.046
Neg logit contributions
 I-0.038
 en-0.036
 me-0.035
 alone-0.035
 unatt-0.035
Token.
Token ID13
Feature activation+8.67e-01

Pos logit contributions
zag+0.022
ages+0.022
tr+0.021
ained+0.020
ometer+0.020
Neg logit contributions
 en-0.010
 unatt-0.010
 My-0.010
ivated-0.010
ternally-0.010
Token They
Token ID1119
Feature activation+5.62e-01

Pos logit contributions
zag+0.036
ages+0.034
tr+0.031
ained+0.031
tails+0.030
Neg logit contributions
 My-0.030
 I-0.030
 en-0.029
 Int-0.028
ivated-0.027
Token learned
Token ID4499
Feature activation+1.90e+00

Pos logit contributions
zag+0.027
ages+0.026
ained+0.025
tr+0.024
ometer+0.024
Neg logit contributions
 en-0.015
 unatt-0.014
ivated-0.014
 alone-0.014
ternally-0.014
Token a
Token ID257
Feature activation+2.60e+00

Pos logit contributions
zag+0.107
ops+0.100
ages+0.099
ained+0.098
tails+0.097
Neg logit contributions
 back-0.038
 en-0.036
 I-0.035
 so-0.035
 My-0.034
Token hard
Token ID1327
Feature activation+4.28e+00

Pos logit contributions
packs+0.091
ained+0.090
aked+0.088
ages+0.086
aj+0.083
Neg logit contributions
 en-0.103
 else-0.098
 I-0.095
 My-0.095
 back-0.094
Token lesson
Token ID11483
Feature activation+2.22e+00

Pos logit contributions
aj+0.176
packs+0.166
tails+0.158
ends+0.155
uth+0.149
Neg logit contributions
's-0.123
 back-0.121
 corner-0.120
 me-0.119
 tune-0.117
Token.
Token ID13
Feature activation+1.11e+00

Pos logit contributions
ages+0.127
aj+0.125
ccoli+0.124
zag+0.124
tr+0.123
Neg logit contributions
 I-0.037
 alone-0.037
 else-0.030
 back-0.029
 unatt-0.029
Token They
Token ID1119
Feature activation+1.13e+00

Pos logit contributions
zag+0.048
ages+0.046
tr+0.042
tails+0.041
ahs+0.041
Neg logit contributions
 I-0.038
 My-0.037
 en-0.036
 Int-0.034
 alone-0.033
Token said
Token ID531
Feature activation+6.70e-01

Pos logit contributions
zag+0.054
ages+0.051
ained+0.050
ometer+0.048
tr+0.047
Neg logit contributions
 en-0.031
 alone-0.029
 unatt-0.029
 I-0.029
ivated-0.028
Token,
Token ID11
Feature activation+5.33e-01

Pos logit contributions
zag+0.030
ages+0.029
tr+0.028
ained+0.028
ine+0.026
Neg logit contributions
 en-0.020
 My-0.020
 I-0.019
ivated-0.019
 unatt-0.019
Token mystery
Token ID10715
Feature activation-7.74e-01

Pos logit contributions
ages+0.016
zag+0.016
ained+0.015
tr+0.014
ine+0.014
Neg logit contributions
 unatt-0.012
 en-0.012
ivated-0.011
 My-0.011
 alone-0.011
Token.
Token ID13
Feature activation+6.44e-01

Pos logit contributions
ivated+0.029
ternally+0.029
 My+0.028
 en+0.027
 Int+0.027
Neg logit contributions
zag-0.028
ages-0.028
tr-0.026
ometer-0.025
packs-0.025
Token They
Token ID1119
Feature activation+3.89e-01

Pos logit contributions
zag+0.023
ages+0.022
tr+0.019
ained+0.019
tails+0.019
Neg logit contributions
 My-0.026
 en-0.026
 I-0.026
ivated-0.024
 alone-0.024
Token learned
Token ID4499
Feature activation+1.76e+00

Pos logit contributions
zag+0.019
ages+0.018
ained+0.017
tr+0.017
ometer+0.017
Neg logit contributions
 en-0.010
 unatt-0.010
ivated-0.010
ternally-0.009
 My-0.009
Token a
Token ID257
Feature activation+2.91e+00

Pos logit contributions
zag+0.095
ops+0.091
ages+0.089
ccoli+0.087
ahs+0.087
Neg logit contributions
 back-0.039
 en-0.037
 I-0.036
 alone-0.036
 My-0.034
Token hard
Token ID1327
Feature activation+4.28e+00

Pos logit contributions
packs+0.113
aj+0.105
ained+0.104
ages+0.103
aked+0.102
Neg logit contributions
 en-0.106
 back-0.100
 else-0.100
 I-0.098
 calm-0.096
Token lesson
Token ID11483
Feature activation+2.13e+00

Pos logit contributions
aj+0.181
packs+0.163
tails+0.158
ccoli+0.156
girls+0.154
Neg logit contributions
 corner-0.126
 tune-0.125
 back-0.122
 alone-0.122
 fright-0.119
Token.
Token ID13
Feature activation+9.51e-01

Pos logit contributions
ccoli+0.128
ages+0.126
zag+0.125
aj+0.125
uffy+0.122
Neg logit contributions
 alone-0.033
 I-0.030
 unatt-0.024
 back-0.024
 else-0.024
Token They
Token ID1119
Feature activation+1.07e+00

Pos logit contributions
zag+0.036
ages+0.034
tr+0.031
ahs+0.030
tails+0.030
Neg logit contributions
 I-0.037
 My-0.037
 en-0.036
 alone-0.034
 Int-0.033
Token learned
Token ID4499
Feature activation+1.92e+00

Pos logit contributions
zag+0.051
ages+0.049
ained+0.046
ccoli+0.046
ometer+0.045
Neg logit contributions
 en-0.029
 alone-0.028
 unatt-0.027
 I-0.027
ternally-0.026
Token that
Token ID326
Feature activation+7.35e-01

Pos logit contributions
zag+0.112
ops+0.110
ages+0.108
ccoli+0.106
ahs+0.105
Neg logit contributions
 back-0.032
 I-0.029
 en-0.028
 alone-0.028
 My-0.026
Token alert
Token ID7995
Feature activation-3.41e-01

Pos logit contributions
zag+0.026
tr+0.025
ages+0.024
ometer+0.023
ained+0.023
Neg logit contributions
 en-0.017
 alone-0.016
 unatt-0.016
ivated-0.015
ternally-0.015
Token.
Token ID13
Feature activation+9.74e-01

Pos logit contributions
ivated+0.012
ternally+0.012
 My+0.012
 en+0.011
 unatt+0.011
Neg logit contributions
ages-0.013
zag-0.013
ained-0.012
tr-0.012
ometer-0.011
Token They
Token ID1119
Feature activation+6.45e-01

Pos logit contributions
zag+0.041
ages+0.039
ogo+0.035
tails+0.035
ahs+0.035
Neg logit contributions
 I-0.034
 My-0.034
 en-0.033
 Int-0.031
 alone-0.031
Token learned
Token ID4499
Feature activation+1.82e+00

Pos logit contributions
zag+0.033
ages+0.032
ained+0.030
tr+0.030
ometer+0.030
Neg logit contributions
 en-0.015
 unatt-0.015
 alone-0.015
ivated-0.014
ternally-0.014
Token a
Token ID257
Feature activation+2.79e+00

Pos logit contributions
zag+0.099
ages+0.095
ops+0.095
ccoli+0.092
ahs+0.091
Neg logit contributions
 back-0.038
 en-0.035
 I-0.035
 alone-0.033
 My-0.033
Token hard
Token ID1327
Feature activation+4.24e+00

Pos logit contributions
packs+0.107
ained+0.101
aked+0.100
ages+0.099
aj+0.098
Neg logit contributions
 en-0.105
 else-0.098
 back-0.096
 I-0.095
 calm-0.092
Token lesson
Token ID11483
Feature activation+2.10e+00

Pos logit contributions
aj+0.181
ccoli+0.167
tails+0.163
packs+0.159
girls+0.158
Neg logit contributions
 tune-0.115
 corner-0.113
 alone-0.112
 back-0.111
's-0.110
Token.
Token ID13
Feature activation+1.21e+00

Pos logit contributions
ccoli+0.124
ages+0.122
zag+0.122
aj+0.120
tr+0.120
Neg logit contributions
 alone-0.033
 I-0.031
 unatt-0.026
 back-0.025
 else-0.023
Token They
Token ID1119
Feature activation+1.24e+00

Pos logit contributions
zag+0.049
ages+0.046
ahs+0.042
tails+0.042
ies+0.042
Neg logit contributions
 I-0.045
 My-0.045
 en-0.042
 Int-0.040
 alone-0.039
Token never
Token ID1239
Feature activation+6.55e-01

Pos logit contributions
zag+0.061
ages+0.058
ained+0.055
ccoli+0.055
ometer+0.054
Neg logit contributions
 en-0.032
 alone-0.031
 unatt-0.030
 I-0.029
ivated-0.029
Token stole
Token ID18240
Feature activation+3.28e-01

Pos logit contributions
zag+0.030
ages+0.030
ained+0.028
ometer+0.028
tr+0.028
Neg logit contributions
 en-0.018
 unatt-0.017
 alone-0.017
 I-0.017
 My-0.017
Token treasure
Token ID14068
Feature activation+6.16e-01

Pos logit contributions
ages+0.012
zag+0.012
ained+0.011
tr+0.011
ometer+0.011
Neg logit contributions
 unatt-0.012
 en-0.012
ternally-0.012
ivated-0.012
 My-0.012
Token.
Token ID13
Feature activation+5.29e-01

Pos logit contributions
ages+0.026
zag+0.026
ained+0.025
tr+0.024
ometer+0.023
Neg logit contributions
 unatt-0.018
 alone-0.018
 en-0.018
ternally-0.017
ivated-0.017
Token They
Token ID1119
Feature activation+7.59e-02

Pos logit contributions
zag+0.017
ages+0.016
tr+0.015
ained+0.014
tails+0.014
Neg logit contributions
 My-0.023
 en-0.023
 I-0.022
ivated-0.022
 alone-0.022
Token learned
Token ID4499
Feature activation+1.81e+00

Pos logit contributions
ages+0.003
zag+0.003
tr+0.003
ained+0.003
ometer+0.003
Neg logit contributions
ivated-0.002
 unatt-0.002
 My-0.002
 en-0.002
ternally-0.002
Token a
Token ID257
Feature activation+2.82e+00

Pos logit contributions
zag+0.097
ops+0.092
ages+0.091
ahs+0.089
ained+0.089
Neg logit contributions
 back-0.041
 I-0.040
 en-0.039
 My-0.038
 so-0.038
Token hard
Token ID1327
Feature activation+4.23e+00

Pos logit contributions
packs+0.100
ained+0.095
aj+0.093
ates+0.091
ages+0.090
Neg logit contributions
 en-0.108
 back-0.106
 else-0.104
 I-0.103
 My-0.100
Token lesson
Token ID11483
Feature activation+2.15e+00

Pos logit contributions
aj+0.173
ccoli+0.153
omo+0.150
packs+0.149
akers+0.146
Neg logit contributions
 back-0.139
 alone-0.134
's-0.126
 corner-0.126
 to-0.124
Token.
Token ID13
Feature activation+1.05e+00

Pos logit contributions
ccoli+0.131
ages+0.129
aj+0.128
zag+0.127
tr+0.125
Neg logit contributions
 alone-0.033
 I-0.028
 back-0.025
 else-0.022
 unatt-0.022
Token They
Token ID1119
Feature activation+1.02e+00

Pos logit contributions
zag+0.041
ages+0.037
tr+0.035
ahs+0.035
tails+0.034
Neg logit contributions
 I-0.041
 My-0.041
 en-0.040
 alone-0.038
 Int-0.037
Token should
Token ID815
Feature activation+1.49e+00

Pos logit contributions
zag+0.047
ages+0.046
ained+0.044
ccoli+0.042
ometer+0.042
Neg logit contributions
 en-0.029
 alone-0.028
 unatt-0.027
ivated-0.026
ternally-0.026
Token have
Token ID423
Feature activation-2.61e-01

Pos logit contributions
ages+0.063
zag+0.061
ometer+0.059
ained+0.059
tr+0.058
Neg logit contributions
 I-0.050
 me-0.048
 cheer-0.046
 alone-0.046
 en-0.046
Token mom
Token ID1995
Feature activation+1.72e-01

Pos logit contributions
ages+0.085
ained+0.084
zag+0.082
ine+0.077
live+0.077
Neg logit contributions
 me-0.036
 en-0.035
 alone-0.034
 cheer-0.034
 I-0.033
Token.
Token ID13
Feature activation+5.77e-01

Pos logit contributions
zag+0.007
ages+0.007
tr+0.007
ained+0.007
ometer+0.007
Neg logit contributions
ivated-0.005
 unatt-0.005
 en-0.005
 My-0.005
ternally-0.005
Token They
Token ID1119
Feature activation+4.65e-01

Pos logit contributions
zag+0.023
ages+0.022
ained+0.020
tr+0.020
ccoli+0.020
Neg logit contributions
 My-0.020
 I-0.020
 en-0.020
ivated-0.019
 alone-0.019
Token learned
Token ID4499
Feature activation+1.92e+00

Pos logit contributions
zag+0.021
ages+0.021
ained+0.020
tr+0.019
ometer+0.019
Neg logit contributions
 en-0.013
 unatt-0.013
ivated-0.013
ternally-0.012
 alone-0.012
Token a
Token ID257
Feature activation+2.62e+00

Pos logit contributions
zag+0.102
ages+0.094
ops+0.094
ained+0.092
wl+0.091
Neg logit contributions
 back-0.047
 I-0.045
 en-0.043
 me-0.043
 My-0.042
Token hard
Token ID1327
Feature activation+4.20e+00

Pos logit contributions
ained+0.092
packs+0.090
ages+0.088
aked+0.088
tails+0.084
Neg logit contributions
 back-0.098
 en-0.096
 I-0.096
 else-0.095
 calm-0.094
Token lesson
Token ID11483
Feature activation+1.63e+00

Pos logit contributions
aj+0.167
ends+0.164
tails+0.163
igi+0.160
packs+0.158
Neg logit contributions
 tune-0.111
 corner-0.109
 back-0.108
 voice-0.106
 show-0.106
Token.
Token ID13
Feature activation+9.57e-01

Pos logit contributions
ages+0.090
zag+0.090
ccoli+0.087
tr+0.086
tails+0.085
Neg logit contributions
 alone-0.030
 I-0.030
 unatt-0.027
 My-0.025
 back-0.024
Token<|endoftext|>
Token ID50256
Feature activation+3.69e-01

Pos logit contributions
zag+0.038
ages+0.036
tr+0.032
tails+0.032
ahs+0.032
Neg logit contributions
 I-0.037
 My-0.036
 en-0.035
 alone-0.033
 Int-0.032
TokenIt
Token ID1026
Feature activation+8.55e-01

Pos logit contributions
ages+0.011
zag+0.011
tr+0.009
ained+0.009
ometer+0.009
Neg logit contributions
 My-0.016
ivated-0.016
 unatt-0.016
 en-0.016
ternally-0.016
Token was
Token ID373
Feature activation+1.88e+00

Pos logit contributions
ages+0.039
zag+0.038
ained+0.036
tr+0.036
ometer+0.035
Neg logit contributions
 en-0.023
 My-0.023
 I-0.022
 alone-0.022
 me-0.021
Token bulb
Token ID28287
Feature activation+1.33e-01

Pos logit contributions
ivated+0.001
 My+0.001
 unatt+0.001
ternally+0.001
 en+0.001
Neg logit contributions
zag-0.001
ages-0.001
tr-0.001
ained-0.001
ometer-0.001
Token.
Token ID13
Feature activation+6.72e-01

Pos logit contributions
zag+0.006
ages+0.006
tr+0.005
ained+0.005
ometer+0.005
Neg logit contributions
ivated-0.004
 unatt-0.004
 en-0.004
 My-0.004
ternally-0.004
Token They
Token ID1119
Feature activation+2.75e-01

Pos logit contributions
zag+0.025
ages+0.024
tr+0.022
ained+0.021
ccoli+0.021
Neg logit contributions
 en-0.026
 My-0.026
 I-0.025
 Int-0.024
ivated-0.024
Token learned
Token ID4499
Feature activation+1.71e+00

Pos logit contributions
zag+0.013
ages+0.013
ained+0.012
tr+0.012
ometer+0.012
Neg logit contributions
 en-0.007
ivated-0.007
 unatt-0.007
 My-0.007
ternally-0.007
Token a
Token ID257
Feature activation+2.97e+00

Pos logit contributions
zag+0.091
ops+0.087
ages+0.086
ccoli+0.084
ahs+0.083
Neg logit contributions
 back-0.037
 en-0.036
 I-0.035
 My-0.034
 alone-0.034
Token hard
Token ID1327
Feature activation+4.18e+00

Pos logit contributions
packs+0.108
aj+0.101
ates+0.098
ained+0.098
ages+0.094
Neg logit contributions
 en-0.111
 I-0.107
 back-0.107
 else-0.104
 My-0.104
Token lesson
Token ID11483
Feature activation+1.91e+00

Pos logit contributions
aj+0.168
packs+0.159
uth+0.144
omo+0.140
akers+0.139
Neg logit contributions
 alone-0.133
 back-0.133
's-0.129
 me-0.125
 fright-0.125
Token.
Token ID13
Feature activation+1.04e+00

Pos logit contributions
ages+0.111
ccoli+0.110
zag+0.110
aj+0.108
tr+0.106
Neg logit contributions
 alone-0.033
 I-0.030
 back-0.026
 unatt-0.026
 else-0.025
Token The
Token ID383
Feature activation+1.29e+00

Pos logit contributions
zag+0.043
ages+0.040
tr+0.037
ahs+0.036
tails+0.036
Neg logit contributions
 My-0.038
 I-0.038
 en-0.037
 alone-0.034
 Int-0.034
Token fox
Token ID21831
Feature activation-3.18e-01

Pos logit contributions
ages+0.068
zag+0.066
packs+0.063
ained+0.061
ccoli+0.060
Neg logit contributions
 en-0.034
 me-0.034
 alone-0.033
 I-0.029
 nearby-0.029
Token was
Token ID373
Feature activation-8.44e-02

Pos logit contributions
ivated+0.011
 My+0.011
 unatt+0.011
ternally+0.011
 en+0.011
Neg logit contributions
ages-0.012
zag-0.012
tr-0.011
ained-0.010
ccoli-0.010
Token day
Token ID1110
Feature activation-1.25e-01

Pos logit contributions
zag+0.023
ages+0.023
ained+0.021
tr+0.020
tails+0.020
Neg logit contributions
 unatt-0.027
 en-0.027
 alone-0.026
 I-0.026
 My-0.026
Token.
Token ID13
Feature activation+8.38e-01

Pos logit contributions
ternally+0.004
ivated+0.004
 en+0.004
 My+0.004
 unatt+0.004
Neg logit contributions
ages-0.005
zag-0.005
tr-0.005
ained-0.005
ometer-0.004
Token They
Token ID1119
Feature activation+6.28e-01

Pos logit contributions
zag+0.039
ages+0.038
tails+0.034
ained+0.034
tr+0.033
Neg logit contributions
 I-0.025
 My-0.025
 en-0.024
 Int-0.023
 alone-0.022
Token learned
Token ID4499
Feature activation+1.63e+00

Pos logit contributions
zag+0.030
ages+0.029
ained+0.028
tr+0.027
ometer+0.027
Neg logit contributions
 en-0.016
 unatt-0.016
 alone-0.016
ivated-0.015
ternally-0.015
Token a
Token ID257
Feature activation+2.54e+00

Pos logit contributions
zag+0.087
ages+0.083
ops+0.081
ained+0.080
ccoli+0.079
Neg logit contributions
 back-0.035
 I-0.034
 en-0.033
 My-0.033
 me-0.032
Token hard
Token ID1327
Feature activation+4.15e+00

Pos logit contributions
packs+0.090
aked+0.088
ages+0.088
ained+0.085
ment+0.081
Neg logit contributions
 en-0.097
 back-0.094
 I-0.094
 else-0.092
 My-0.091
Token lesson
Token ID11483
Feature activation+2.03e+00

Pos logit contributions
aj+0.161
packs+0.158
igi+0.158
tails+0.153
ends+0.152
Neg logit contributions
 tune-0.121
 corner-0.116
's-0.113
 me-0.111
 back-0.110
Token.
Token ID13
Feature activation+1.16e+00

Pos logit contributions
ages+0.114
zag+0.114
ccoli+0.114
tr+0.110
uffy+0.109
Neg logit contributions
 I-0.036
 alone-0.035
 unatt-0.030
 back-0.029
 me-0.027
Token Fire
Token ID3764
Feature activation+1.61e+00

Pos logit contributions
zag+0.050
ages+0.047
tails+0.043
ahs+0.042
ies+0.042
Neg logit contributions
 I-0.041
 My-0.040
 en-0.038
 Int-0.035
My-0.035
Token is
Token ID318
Feature activation+1.74e+00

Pos logit contributions
ages+0.064
zag+0.062
tails+0.060
ine+0.058
tr+0.058
Neg logit contributions
 I-0.049
 alone-0.049
 unatt-0.047
ternally-0.046
 en-0.046
Token not
Token ID407
Feature activation+1.44e+00

Pos logit contributions
zag+0.080
ages+0.074
ops+0.072
tails+0.071
ometer+0.069
Neg logit contributions
 en-0.058
 alone-0.057
 I-0.056
 back-0.055
 me-0.054
Tokenbs
Token ID1443
Feature activation-4.67e-01

Pos logit contributions
zag+0.022
ages+0.021
ained+0.021
tr+0.020
tails+0.019
Neg logit contributions
 unatt-0.017
 en-0.017
ivated-0.017
ternally-0.017
 My-0.016
Token.
Token ID13
Feature activation+8.53e-01

Pos logit contributions
ivated+0.016
ternally+0.016
 en+0.015
 My+0.015
 Int+0.015
Neg logit contributions
zag-0.018
ages-0.018
tr-0.017
ained-0.016
ometer-0.016
Token They
Token ID1119
Feature activation+4.65e-01

Pos logit contributions
zag+0.034
ages+0.033
tr+0.030
tails+0.030
ained+0.029
Neg logit contributions
 My-0.030
 I-0.030
 en-0.029
 Int-0.028
 alone-0.027
Token learned
Token ID4499
Feature activation+1.73e+00

Pos logit contributions
zag+0.022
ages+0.022
ained+0.020
tr+0.020
ometer+0.020
Neg logit contributions
 en-0.012
 unatt-0.012
ivated-0.012
 alone-0.012
 My-0.011
Token a
Token ID257
Feature activation+2.79e+00

Pos logit contributions
zag+0.090
ops+0.086
ages+0.085
ccoli+0.085
ahs+0.082
Neg logit contributions
 back-0.040
 en-0.038
 I-0.037
 My-0.036
 alone-0.035
Token hard
Token ID1327
Feature activation+4.11e+00

Pos logit contributions
packs+0.106
ained+0.097
aked+0.096
ages+0.095
aj+0.095
Neg logit contributions
 en-0.105
 back-0.099
 else-0.099
 I-0.096
 calm-0.093
Token lesson
Token ID11483
Feature activation+2.12e+00

Pos logit contributions
aj+0.170
ccoli+0.158
packs+0.155
tails+0.149
akers+0.145
Neg logit contributions
 back-0.120
 alone-0.120
 tune-0.119
 en-0.117
 corner-0.116
Token.
Token ID13
Feature activation+1.09e+00

Pos logit contributions
ccoli+0.125
ages+0.123
zag+0.122
aj+0.121
tr+0.120
Neg logit contributions
 alone-0.034
 I-0.032
 unatt-0.026
 back-0.026
 else-0.025
Token<|endoftext|>
Token ID50256
Feature activation+2.84e-01

Pos logit contributions
zag+0.046
ages+0.044
tr+0.040
tails+0.039
ahs+0.039
Neg logit contributions
 I-0.038
 My-0.037
 en-0.036
 alone-0.033
 Int-0.033
TokenL
Token ID43
Feature activation+1.40e-01

Pos logit contributions
ages+0.008
zag+0.008
tr+0.007
ained+0.007
ometer+0.007
Neg logit contributions
ivated-0.013
 My-0.013
 en-0.012
 unatt-0.012
ternally-0.012
Tokenily
Token ID813
Feature activation-2.09e-02

Pos logit contributions
ages+0.006
zag+0.006
tr+0.006
ained+0.006
ometer+0.006
Neg logit contributions
ivated-0.004
 unatt-0.004
 en-0.004
 My-0.004
ternally-0.004
Token honest
Token ID5508
Feature activation+2.39e-01

Pos logit contributions
ivated+0.034
 Int+0.033
ternally+0.033
 My+0.033
 I+0.031
Neg logit contributions
ages-0.038
ained-0.033
zag-0.033
ends-0.032
ies-0.031
Token.
Token ID13
Feature activation+9.67e-01

Pos logit contributions
zag+0.010
ages+0.010
tr+0.010
ained+0.009
ometer+0.009
Neg logit contributions
 unatt-0.007
ivated-0.007
 en-0.007
 My-0.007
ternally-0.007
Token They
Token ID1119
Feature activation+7.91e-01

Pos logit contributions
zag+0.038
ages+0.036
tails+0.033
tr+0.032
ained+0.032
Neg logit contributions
 My-0.036
 I-0.036
 en-0.036
 Int-0.033
 alone-0.033
Token learned
Token ID4499
Feature activation+2.05e+00

Pos logit contributions
zag+0.039
ages+0.038
ained+0.036
ometer+0.035
ccoli+0.035
Neg logit contributions
 en-0.020
 unatt-0.019
 alone-0.019
ivated-0.019
ternally-0.018
Token a
Token ID257
Feature activation+2.77e+00

Pos logit contributions
zag+0.114
ops+0.112
ages+0.112
ccoli+0.109
live+0.108
Neg logit contributions
 back-0.040
 en-0.036
 so-0.035
 I-0.035
 My-0.034
Token hard
Token ID1327
Feature activation+4.11e+00

Pos logit contributions
packs+0.103
aked+0.098
ained+0.097
ages+0.096
tails+0.091
Neg logit contributions
 en-0.106
 else-0.101
 I-0.099
 back-0.097
 My-0.096
Token lesson
Token ID11483
Feature activation+2.27e+00

Pos logit contributions
aj+0.158
ccoli+0.156
tails+0.155
packs+0.148
akers+0.147
Neg logit contributions
 tune-0.122
 alone-0.117
 back-0.117
 corner-0.117
 show-0.113
Token.
Token ID13
Feature activation+1.23e+00

Pos logit contributions
ccoli+0.134
ages+0.132
aj+0.130
zag+0.130
tr+0.129
Neg logit contributions
 alone-0.036
 I-0.034
 back-0.027
 unatt-0.027
 else-0.025
Token<|endoftext|>
Token ID50256
Feature activation+2.12e-01

Pos logit contributions
zag+0.052
ages+0.049
tails+0.044
ahs+0.044
tr+0.044
Neg logit contributions
 I-0.045
 My-0.044
 en-0.042
 alone-0.039
 Int-0.039
TokenL
Token ID43
Feature activation+1.81e-01

Pos logit contributions
ages+0.006
zag+0.006
tr+0.005
ained+0.005
ometer+0.005
Neg logit contributions
ivated-0.009
 My-0.009
 unatt-0.009
 en-0.009
ternally-0.009
Tokenily
Token ID813
Feature activation+1.73e-01

Pos logit contributions
ages+0.008
zag+0.008
tr+0.007
ained+0.007
ometer+0.007
Neg logit contributions
ivated-0.006
 en-0.005
 My-0.005
 unatt-0.005
ternally-0.005
Token mistake
Token ID7457
Feature activation-5.21e-02

Pos logit contributions
ages+0.026
zag+0.026
ained+0.025
tr+0.023
ccoli+0.023
Neg logit contributions
 en-0.025
 unatt-0.025
ternally-0.025
 alone-0.025
ivated-0.024
Token.
Token ID13
Feature activation-2.86e-03

Pos logit contributions
ivated+0.002
ternally+0.002
 en+0.002
 unatt+0.002
 My+0.002
Neg logit contributions
ages-0.002
zag-0.002
tr-0.002
ained-0.002
ometer-0.002
Token They
Token ID1119
Feature activation+4.89e-01

Pos logit contributions
ivated+0.000
 unatt+0.000
ternally+0.000
 en+0.000
 My+0.000
Neg logit contributions
ages-0.000
zag-0.000
tr-0.000
ained-0.000
ometer-0.000
Token learned
Token ID4499
Feature activation+1.90e+00

Pos logit contributions
zag+0.022
ages+0.021
ained+0.020
tr+0.020
ometer+0.020
Neg logit contributions
 en-0.014
 unatt-0.014
ivated-0.014
ternally-0.013
 My-0.013
Token a
Token ID257
Feature activation+2.96e+00

Pos logit contributions
zag+0.103
ops+0.098
ages+0.096
ained+0.095
ccoli+0.093
Neg logit contributions
 back-0.041
 I-0.038
 so-0.038
 en-0.037
 My-0.037
Token hard
Token ID1327
Feature activation+4.09e+00

Pos logit contributions
packs+0.106
ained+0.100
ates+0.098
aj+0.098
ops+0.094
Neg logit contributions
 back-0.112
 en-0.109
 me-0.106
 I-0.106
 My-0.102
Token lesson
Token ID11483
Feature activation+1.85e+00

Pos logit contributions
aj+0.168
packs+0.153
ccoli+0.145
ends+0.141
akers+0.139
Neg logit contributions
 back-0.131
 alone-0.125
 fright-0.122
 corner-0.122
 tune-0.121
Token.
Token ID13
Feature activation+6.05e-01

Pos logit contributions
ages+0.103
ccoli+0.102
tr+0.101
zag+0.100
aj+0.098
Neg logit contributions
 alone-0.036
 I-0.033
 unatt-0.029
 back-0.028
 else-0.028
Token They
Token ID1119
Feature activation+9.86e-01

Pos logit contributions
zag+0.024
ages+0.023
tr+0.021
ained+0.021
tails+0.021
Neg logit contributions
 My-0.021
 I-0.021
 en-0.021
ivated-0.020
 Int-0.020
Token should
Token ID815
Feature activation+1.60e+00

Pos logit contributions
zag+0.045
ages+0.043
ained+0.042
ccoli+0.040
ometer+0.040
Neg logit contributions
 en-0.027
 alone-0.026
ternally-0.026
 unatt-0.026
 I-0.026
Token never
Token ID1239
Feature activation+1.93e-01

Pos logit contributions
ages+0.068
zag+0.066
ometer+0.064
ained+0.064
tr+0.063
Neg logit contributions
 I-0.053
 me-0.050
 cheer-0.048
 alone-0.047
 en-0.047
Token animals
Token ID4695
Feature activation-6.33e-01

Pos logit contributions
ages+0.027
zag+0.026
ained+0.025
ccoli+0.024
tr+0.024
Neg logit contributions
 en-0.025
 unatt-0.024
 My-0.024
 alone-0.023
ivated-0.023
Token.
Token ID13
Feature activation+5.56e-01

Pos logit contributions
ternally+0.022
ivated+0.022
 My+0.021
 Int+0.021
 en+0.021
Neg logit contributions
ages-0.024
zag-0.024
tr-0.022
ained-0.021
ometer-0.021
Token She
Token ID1375
Feature activation+2.08e-01

Pos logit contributions
zag+0.029
ages+0.029
tr+0.026
ained+0.026
tails+0.026
Neg logit contributions
 My-0.013
 I-0.012
 en-0.012
ivated-0.012
 alone-0.012
Token learned
Token ID4499
Feature activation+1.22e+00

Pos logit contributions
zag+0.010
ages+0.010
tr+0.009
ained+0.009
ometer+0.009
Neg logit contributions
 en-0.005
ivated-0.005
 unatt-0.005
 My-0.005
ternally-0.005
Token a
Token ID257
Feature activation+2.72e+00

Pos logit contributions
zag+0.063
ages+0.061
ccoli+0.058
ained+0.057
ometer+0.057
Neg logit contributions
 en-0.029
 My-0.029
 I-0.028
 me-0.027
 alone-0.027
Token hard
Token ID1327
Feature activation+4.08e+00

Pos logit contributions
packs+0.100
aj+0.095
ages+0.095
ained+0.094
aked+0.092
Neg logit contributions
 en-0.106
 I-0.098
 My-0.096
 else-0.095
 back-0.094
Token lesson
Token ID11483
Feature activation+1.87e+00

Pos logit contributions
aj+0.176
packs+0.164
omo+0.151
ccoli+0.151
girls+0.151
Neg logit contributions
 tune-0.119
 alone-0.117
 back-0.115
 corner-0.115
 en-0.113
Token.
Token ID13
Feature activation+8.96e-01

Pos logit contributions
ages+0.106
ccoli+0.106
zag+0.105
aj+0.101
tr+0.101
Neg logit contributions
 alone-0.038
 I-0.036
 unatt-0.031
 me-0.030
 back-0.029
Token She
Token ID1375
Feature activation+9.03e-01

Pos logit contributions
zag+0.048
ages+0.047
tr+0.043
tails+0.043
ahs+0.043
Neg logit contributions
 I-0.020
 My-0.020
 en-0.019
 alone-0.018
 Int-0.017
Token was
Token ID373
Feature activation-2.07e-01

Pos logit contributions
zag+0.043
ages+0.041
ained+0.040
ometer+0.038
tr+0.038
Neg logit contributions
 en-0.024
 I-0.023
 alone-0.022
 unatt-0.022
 My-0.022
Token not
Token ID407
Feature activation+7.91e-01

Pos logit contributions
ivated+0.007
ternally+0.007
 unatt+0.007
 My+0.007
 en+0.007
Neg logit contributions
ages-0.008
zag-0.008
ained-0.007
tr-0.007
ccoli-0.007
Token Tom
Token ID4186
Feature activation+8.17e-02

Pos logit contributions
zag+0.031
ages+0.030
tr+0.028
tails+0.027
ained+0.027
Neg logit contributions
 My-0.026
 en-0.026
 I-0.026
 Int-0.025
ivated-0.025
Token and
Token ID290
Feature activation+3.78e-01

Pos logit contributions
ages+0.003
zag+0.003
tr+0.003
ained+0.003
ometer+0.003
Neg logit contributions
ivated-0.003
 unatt-0.003
 en-0.003
 My-0.003
ternally-0.003
Token Lily
Token ID20037
Feature activation+1.55e-02

Pos logit contributions
zag+0.020
ages+0.020
ained+0.018
tr+0.018
ometer+0.018
Neg logit contributions
 en-0.008
 My-0.008
ivated-0.008
 unatt-0.008
 alone-0.008
Token learned
Token ID4499
Feature activation+2.02e+00

Pos logit contributions
ages+0.001
zag+0.001
tr+0.001
ained+0.001
ometer+0.001
Neg logit contributions
ivated-0.000
 My-0.000
 unatt-0.000
 en-0.000
ternally-0.000
Token a
Token ID257
Feature activation+2.86e+00

Pos logit contributions
zag+0.113
ops+0.104
ccoli+0.103
ages+0.102
vals+0.102
Neg logit contributions
 back-0.044
 en-0.043
 alone-0.040
 so-0.040
 me-0.036
Token hard
Token ID1327
Feature activation+4.07e+00

Pos logit contributions
packs+0.105
ained+0.099
aj+0.098
aked+0.097
live+0.095
Neg logit contributions
 en-0.108
 else-0.098
 back-0.098
 I-0.098
 My-0.096
Token lesson
Token ID11483
Feature activation+2.17e+00

Pos logit contributions
aj+0.169
tails+0.154
packs+0.148
ends+0.146
girls+0.144
Neg logit contributions
 back-0.116
 corner-0.113
 en-0.113
 alone-0.112
 tune-0.112
Token.
Token ID13
Feature activation+1.41e+00

Pos logit contributions
ccoli+0.125
tr+0.123
zag+0.123
ages+0.122
tails+0.120
Neg logit contributions
 alone-0.038
 I-0.036
 unatt-0.030
 back-0.029
 My-0.027
Token They
Token ID1119
Feature activation+1.34e+00

Pos logit contributions
zag+0.058
ages+0.054
w+0.050
tr+0.050
tails+0.050
Neg logit contributions
 I-0.051
 en-0.050
 My-0.049
 alone-0.047
 Int-0.046
Token never
Token ID1239
Feature activation+8.19e-01

Pos logit contributions
zag+0.065
ages+0.062
ained+0.060
ometer+0.059
ccoli+0.059
Neg logit contributions
 en-0.035
 alone-0.033
 I-0.032
ternally-0.032
 cheer-0.032
Token climbed
Token ID19952
Feature activation+1.05e+00

Pos logit contributions
zag+0.039
ages+0.038
ained+0.036
ometer+0.035
tr+0.035
Neg logit contributions
 en-0.021
 alone-0.021
 unatt-0.021
 I-0.021
 My-0.020
Token okay
Token ID8788
Feature activation-2.14e-02

Pos logit contributions
ivated+0.015
 My+0.015
 Int+0.015
ternally+0.014
 unatt+0.014
Neg logit contributions
ages-0.020
zag-0.019
ained-0.019
tr-0.018
ccoli-0.018
Token.
Token ID13
Feature activation+1.23e+00

Pos logit contributions
ivated+0.001
ternally+0.001
 en+0.001
 unatt+0.001
 My+0.001
Neg logit contributions
zag-0.001
ages-0.001
tr-0.001
ained-0.001
ometer-0.001
Token They
Token ID1119
Feature activation+6.83e-01

Pos logit contributions
zag+0.060
ages+0.057
ogo+0.053
ahs+0.052
tails+0.052
Neg logit contributions
 I-0.036
 My-0.035
 en-0.033
 Int-0.032
My-0.031
Token learned
Token ID4499
Feature activation+1.66e+00

Pos logit contributions
zag+0.032
ages+0.031
ained+0.029
tr+0.028
ometer+0.028
Neg logit contributions
 en-0.018
 unatt-0.018
 alone-0.018
ivated-0.018
ternally-0.018
Token a
Token ID257
Feature activation+2.64e+00

Pos logit contributions
zag+0.088
ages+0.081
ops+0.081
ained+0.080
live+0.078
Neg logit contributions
 back-0.040
 en-0.038
 I-0.037
 My-0.037
 me-0.036
Token hard
Token ID1327
Feature activation+4.06e+00

Pos logit contributions
packs+0.095
ained+0.092
aked+0.091
aj+0.088
ages+0.088
Neg logit contributions
 en-0.101
 back-0.098
 else-0.097
 I-0.097
 My-0.094
Token lesson
Token ID11483
Feature activation+1.77e+00

Pos logit contributions
aj+0.171
packs+0.160
igi+0.155
akers+0.149
uth+0.147
Neg logit contributions
 tune-0.121
's-0.116
 cheer-0.113
 voice-0.112
 back-0.112
Token.
Token ID13
Feature activation+1.27e+00

Pos logit contributions
ages+0.101
zag+0.100
ccoli+0.096
tr+0.096
tails+0.095
Neg logit contributions
 alone-0.032
 I-0.030
 unatt-0.029
 back-0.026
 else-0.025
Token They
Token ID1119
Feature activation+1.11e+00

Pos logit contributions
zag+0.056
ages+0.053
ahs+0.048
tails+0.047
ogo+0.047
Neg logit contributions
 I-0.043
 My-0.042
 en-0.041
 Int-0.038
 alone-0.037
Token were
Token ID547
Feature activation+2.11e-01

Pos logit contributions
zag+0.053
ages+0.050
ained+0.048
ometer+0.047
ccoli+0.047
Neg logit contributions
 en-0.030
 alone-0.029
 unatt-0.028
ternally-0.028
 I-0.028
Token poor
Token ID3595
Feature activation+5.76e-01

Pos logit contributions
zag+0.008
ages+0.008
tr+0.008
ained+0.008
ometer+0.008
Neg logit contributions
 en-0.007
ivated-0.007
 unatt-0.007
 My-0.007
ternally-0.007
Token cookies
Token ID14746
Feature activation+2.97e-01

Pos logit contributions
ivated+0.003
 My+0.003
ternally+0.003
 en+0.003
 unatt+0.003
Neg logit contributions
ages-0.003
zag-0.003
tr-0.003
ained-0.003
ometer-0.003
Token.
Token ID13
Feature activation+9.05e-01

Pos logit contributions
zag+0.013
ages+0.013
tr+0.012
ained+0.012
ometer+0.011
Neg logit contributions
 unatt-0.009
ivated-0.009
 en-0.009
 My-0.008
ternally-0.008
Token They
Token ID1119
Feature activation+4.05e-01

Pos logit contributions
zag+0.038
ages+0.036
tails+0.033
ogo+0.032
ahs+0.032
Neg logit contributions
 I-0.033
 My-0.032
 en-0.031
 Int-0.030
My-0.029
Token learned
Token ID4499
Feature activation+1.79e+00

Pos logit contributions
zag+0.019
ages+0.018
ained+0.017
tr+0.017
ometer+0.017
Neg logit contributions
 en-0.011
 unatt-0.011
ivated-0.011
ternally-0.010
 My-0.010
Token a
Token ID257
Feature activation+2.83e+00

Pos logit contributions
zag+0.095
ages+0.088
ops+0.088
tails+0.086
ained+0.086
Neg logit contributions
 back-0.042
 I-0.040
 My-0.039
 en-0.039
 me-0.038
Token hard
Token ID1327
Feature activation+4.06e+00

Pos logit contributions
packs+0.102
ained+0.100
aked+0.099
ages+0.097
ates+0.094
Neg logit contributions
 else-0.104
 en-0.103
 I-0.100
 calm-0.099
 back-0.099
Token lesson
Token ID11483
Feature activation+1.87e+00

Pos logit contributions
aj+0.158
tails+0.154
packs+0.150
ccoli+0.150
uth+0.146
Neg logit contributions
 corner-0.116
 back-0.115
 tune-0.115
 alone-0.114
's-0.111
Token.
Token ID13
Feature activation+1.11e+00

Pos logit contributions
zag+0.110
ages+0.109
ccoli+0.109
tr+0.105
uffy+0.104
Neg logit contributions
 alone-0.029
 I-0.028
 unatt-0.024
 else-0.023
 back-0.022
Token They
Token ID1119
Feature activation+1.01e+00

Pos logit contributions
zag+0.046
ages+0.043
tails+0.040
ahs+0.040
ogo+0.039
Neg logit contributions
 I-0.041
 My-0.041
 en-0.039
 Int-0.036
My-0.035
Token had
Token ID550
Feature activation+3.43e-01

Pos logit contributions
zag+0.047
ages+0.045
ained+0.043
ccoli+0.042
ometer+0.042
Neg logit contributions
 en-0.027
 alone-0.026
 unatt-0.026
 I-0.026
ternally-0.025
Token a
Token ID257
Feature activation+1.36e+00

Pos logit contributions
zag+0.016
ages+0.015
tr+0.014
ained+0.014
ometer+0.014
Neg logit contributions
 en-0.009
 unatt-0.009
 My-0.009
ternally-0.009
ivated-0.009
Token toys
Token ID14958
Feature activation-6.62e-01

Pos logit contributions
ivated+0.002
 My+0.002
ternally+0.002
 unatt+0.002
 en+0.002
Neg logit contributions
ages-0.002
zag-0.002
tr-0.001
ained-0.001
ometer-0.001
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
 My+0.021
ivated+0.021
ternally+0.020
 Int+0.020
 en+0.020
Neg logit contributions
zag-0.027
ages-0.027
tr-0.025
ained-0.025
ometer-0.024
Token They
Token ID1119
Feature activation+5.16e-01

Pos logit contributions
zag+0.040
ages+0.039
ogo+0.034
tr+0.034
ahs+0.034
Neg logit contributions
 I-0.037
 en-0.037
 My-0.037
 Int-0.035
 alone-0.034
Token learned
Token ID4499
Feature activation+1.84e+00

Pos logit contributions
zag+0.024
ages+0.024
ained+0.023
tr+0.022
ometer+0.022
Neg logit contributions
 en-0.014
 unatt-0.013
ivated-0.013
 alone-0.013
ternally-0.013
Token a
Token ID257
Feature activation+2.70e+00

Pos logit contributions
zag+0.100
ages+0.094
ops+0.093
ccoli+0.091
ained+0.090
Neg logit contributions
 back-0.040
 en-0.039
 I-0.037
 me-0.036
 so-0.036
Token hard
Token ID1327
Feature activation+4.05e+00

Pos logit contributions
packs+0.095
ained+0.090
aked+0.089
ages+0.089
aj+0.086
Neg logit contributions
 en-0.103
 back-0.100
 I-0.099
 cheer-0.097
 My-0.096
Token lesson
Token ID11483
Feature activation+2.09e+00

Pos logit contributions
aj+0.166
igi+0.155
packs+0.154
uth+0.150
akers+0.149
Neg logit contributions
 cheer-0.122
 tune-0.121
 corner-0.121
 back-0.118
 alone-0.116
Token:
Token ID25
Feature activation+1.65e+00

Pos logit contributions
ages+0.121
ccoli+0.120
zag+0.119
aj+0.117
tr+0.117
Neg logit contributions
 alone-0.035
 I-0.033
 back-0.028
 unatt-0.028
 else-0.025
Token lying
Token ID9105
Feature activation+2.01e-01

Pos logit contributions
zag+0.079
ages+0.073
ogo+0.072
tr+0.071
live+0.070
Neg logit contributions
 I-0.051
 en-0.048
 My-0.047
 alone-0.042
 me-0.041
Token is
Token ID318
Feature activation+2.13e+00

Pos logit contributions
zag+0.008
ages+0.008
tr+0.007
ained+0.007
ometer+0.007
Neg logit contributions
ivated-0.007
 unatt-0.007
 en-0.007
 My-0.007
ternally-0.007
Token bad
Token ID2089
Feature activation+1.02e+00

Pos logit contributions
zag+0.102
ages+0.091
ops+0.090
ira+0.089
tails+0.089
Neg logit contributions
 en-0.067
 alone-0.066
 back-0.065
 I-0.063
 unatt-0.063
Token day
Token ID1110
Feature activation+2.03e-01

Pos logit contributions
ained+0.062
ages+0.059
ends+0.057
zag+0.057
ometers+0.057
Neg logit contributions
 alone-0.066
 back-0.065
 en-0.064
 I-0.063
 unatt-0.062
Token.
Token ID13
Feature activation+3.32e-01

Pos logit contributions
zag+0.009
ages+0.009
tr+0.008
ained+0.008
ometer+0.008
Neg logit contributions
ivated-0.006
 unatt-0.006
 en-0.006
 My-0.006
ternally-0.006
Token They
Token ID1119
Feature activation-2.97e-01

Pos logit contributions
zag+0.012
ages+0.012
tr+0.011
ained+0.011
tails+0.011
Neg logit contributions
 My-0.012
 en-0.012
ivated-0.012
 I-0.012
 unatt-0.012
Token learned
Token ID4499
Feature activation+1.57e+00

Pos logit contributions
ivated+0.011
ternally+0.010
 My+0.010
 unatt+0.010
 en+0.010
Neg logit contributions
ages-0.011
zag-0.011
tr-0.010
ained-0.010
tails-0.010
Token a
Token ID257
Feature activation+2.79e+00

Pos logit contributions
zag+0.080
ages+0.077
ops+0.075
ained+0.074
ine+0.074
Neg logit contributions
 back-0.037
 I-0.036
 en-0.036
 My-0.034
 alone-0.034
Token hard
Token ID1327
Feature activation+4.04e+00

Pos logit contributions
packs+0.099
ained+0.093
ates+0.090
ages+0.089
aj+0.089
Neg logit contributions
 back-0.110
 en-0.106
 I-0.103
 else-0.102
 My-0.099
Token lesson
Token ID11483
Feature activation+1.54e+00

Pos logit contributions
aj+0.166
packs+0.146
akers+0.141
ends+0.139
igi+0.139
Neg logit contributions
 tune-0.131
 back-0.126
's-0.121
 fright-0.121
 corner-0.118
Token.
Token ID13
Feature activation+7.34e-01

Pos logit contributions
zag+0.085
ages+0.084
ccoli+0.083
tr+0.081
aj+0.080
Neg logit contributions
 alone-0.029
 I-0.028
 unatt-0.026
 back-0.024
 en-0.023
Token They
Token ID1119
Feature activation+6.06e-01

Pos logit contributions
zag+0.028
ages+0.027
tr+0.025
tails+0.024
ained+0.024
Neg logit contributions
 I-0.027
 My-0.027
 en-0.026
 alone-0.025
 Int-0.025
Token should
Token ID815
Feature activation+1.42e+00

Pos logit contributions
zag+0.026
ages+0.025
ained+0.023
tr+0.023
ometer+0.023
Neg logit contributions
 en-0.019
 unatt-0.018
 alone-0.018
ivated-0.018
ternally-0.018
Token not
Token ID407
Feature activation+5.44e-01

Pos logit contributions
ages+0.058
zag+0.056
ometer+0.055
ained+0.054
tr+0.053
Neg logit contributions
 I-0.049
 me-0.046
 cheer-0.045
 en-0.045
 alone-0.045
Token jumped
Token ID11687
Feature activation+5.74e-01

Pos logit contributions
zag+0.047
ages+0.045
ained+0.043
ometer+0.043
tr+0.042
Neg logit contributions
 en-0.024
 alone-0.024
 I-0.023
 unatt-0.023
 My-0.022
Token.
Token ID13
Feature activation+8.53e-01

Pos logit contributions
ages+0.027
zag+0.027
tr+0.025
ained+0.024
ometer+0.024
Neg logit contributions
 en-0.015
 unatt-0.015
ivated-0.015
 alone-0.015
ternally-0.014
Token They
Token ID1119
Feature activation+7.02e-01

Pos logit contributions
zag+0.031
ages+0.029
tails+0.026
w+0.026
tr+0.026
Neg logit contributions
 en-0.034
 My-0.034
 I-0.034
 Int-0.032
 alone-0.031
Token learned
Token ID4499
Feature activation+1.90e+00

Pos logit contributions
zag+0.033
ages+0.032
ained+0.030
ometer+0.030
tr+0.029
Neg logit contributions
 en-0.020
 unatt-0.019
 alone-0.018
ivated-0.018
ternally-0.018
Token a
Token ID257
Feature activation+2.71e+00

Pos logit contributions
zag+0.101
ops+0.095
ages+0.094
uffy+0.092
ained+0.092
Neg logit contributions
 en-0.042
 back-0.042
 so-0.039
 My-0.039
 I-0.038
Token hard
Token ID1327
Feature activation+4.03e+00

Pos logit contributions
packs+0.093
aj+0.085
ained+0.084
aked+0.083
ages+0.082
Neg logit contributions
 en-0.112
 I-0.103
 else-0.103
 My-0.102
 back-0.101
Token lesson
Token ID11483
Feature activation+2.07e+00

Pos logit contributions
aj+0.165
packs+0.150
ccoli+0.140
tails+0.136
igi+0.132
Neg logit contributions
 en-0.129
 alone-0.125
 tune-0.124
 back-0.124
's-0.122
Token that
Token ID326
Feature activation+3.39e-01

Pos logit contributions
ages+0.118
ccoli+0.117
zag+0.116
aj+0.116
tr+0.115
Neg logit contributions
 alone-0.036
 I-0.035
 back-0.029
 unatt-0.028
 else-0.028
Token day
Token ID1110
Feature activation+1.31e+00

Pos logit contributions
zag+0.010
ages+0.010
tr+0.009
ained+0.009
ometer+0.008
Neg logit contributions
 en-0.015
 unatt-0.014
 My-0.014
ivated-0.014
 I-0.014
Token.
Token ID13
Feature activation+1.13e+00

Pos logit contributions
zag+0.067
ages+0.065
tr+0.064
ained+0.062
ccoli+0.062
Neg logit contributions
 I-0.028
 alone-0.027
 unatt-0.026
 My-0.026
 en-0.025
Token They
Token ID1119
Feature activation+1.15e+00

Pos logit contributions
zag+0.045
ages+0.043
tails+0.039
tr+0.038
ahs+0.038
Neg logit contributions
 I-0.042
 My-0.042
 en-0.041
 Int-0.038
 alone-0.037
Token never
Token ID1239
Feature activation-1.23e+00

Pos logit contributions
ivated+0.026
 unatt+0.025
 My+0.025
ternally+0.025
 en+0.024
Neg logit contributions
zag-0.028
ages-0.026
tr-0.024
ine-0.024
ained-0.023
Token wanted
Token ID2227
Feature activation-1.86e+00

Pos logit contributions
ternally+0.048
 My+0.047
ivated+0.047
 unatt+0.044
 en+0.043
Neg logit contributions
zag-0.042
ages-0.039
tr-0.036
ies-0.036
ained-0.036
Token to
Token ID284
Feature activation-1.14e+00

Pos logit contributions
ivated+0.085
ternally+0.083
 unatt+0.078
 Int+0.075
 My+0.073
Neg logit contributions
zag-0.049
ages-0.048
 lesson-0.046
 common-0.045
ment-0.045
Token leave
Token ID2666
Feature activation-1.59e+00

Pos logit contributions
ternally+0.039
 My+0.037
ivated+0.037
 unatt+0.037
 Int+0.037
Neg logit contributions
zag-0.046
ages-0.041
tails-0.041
tr-0.039
ine-0.038
Token the
Token ID262
Feature activation-1.14e+00

Pos logit contributions
ivated+0.061
ternally+0.059
 Int+0.059
 My+0.058
 en+0.054
Neg logit contributions
zag-0.052
ages-0.050
 common-0.049
ment-0.048
ained-0.048
Token group
Token ID1448
Feature activation-3.95e+00

Pos logit contributions
 My+0.036
ternally+0.035
ivated+0.034
 Int+0.033
 unatt+0.031
Neg logit contributions
zag-0.049
ages-0.046
tr-0.045
ained-0.044
tails-0.042
Token again
Token ID757
Feature activation-4.15e-01

Pos logit contributions
ternally+0.164
 Int+0.163
ivated+0.153
 My+0.152
Gu+0.145
Neg logit contributions
zag-0.114
ages-0.096
packs-0.089
ies-0.087
ward-0.087
Token.
Token ID13
Feature activation-1.08e-02

Pos logit contributions
ternally+0.014
ivated+0.014
 My+0.014
 en+0.014
 unatt+0.014
Neg logit contributions
zag-0.016
ages-0.016
ained-0.014
tr-0.014
ine-0.014
Token They
Token ID1119
Feature activation+1.26e-01

Pos logit contributions
ivated+0.000
 unatt+0.000
ternally+0.000
 en+0.000
 My+0.000
Neg logit contributions
ages-0.000
zag-0.000
tr-0.000
ained-0.000
ometer-0.000
Token were
Token ID547
Feature activation-1.14e-01

Pos logit contributions
ages+0.005
zag+0.005
tr+0.005
ained+0.005
ometer+0.004
Neg logit contributions
ivated-0.004
 unatt-0.004
 en-0.004
 My-0.004
ternally-0.004
Token so
Token ID523
Feature activation-4.45e-01

Pos logit contributions
ivated+0.003
 My+0.003
 unatt+0.003
ternally+0.003
 en+0.003
Neg logit contributions
zag-0.005
ages-0.005
ained-0.005
tr-0.005
ometer-0.005
Token and
Token ID290
Feature activation+1.03e+00

Pos logit contributions
ternally+0.027
 unatt+0.026
ivated+0.026
 My+0.026
 Int+0.025
Neg logit contributions
zag-0.025
ages-0.024
ained-0.022
tr-0.021
olving-0.021
Token the
Token ID262
Feature activation-2.60e-02

Pos logit contributions
zag+0.044
ages+0.044
tr+0.042
aj+0.042
ained+0.041
Neg logit contributions
 en-0.032
 alone-0.030
 I-0.030
 My-0.029
 cheer-0.029
Token deer
Token ID20096
Feature activation-1.20e-01

Pos logit contributions
ivated+0.001
 My+0.001
 unatt+0.001
ternally+0.001
 en+0.001
Neg logit contributions
zag-0.001
ages-0.001
tr-0.001
ained-0.001
ometer-0.001
Token was
Token ID373
Feature activation-2.59e-01

Pos logit contributions
ivated+0.004
 My+0.004
 unatt+0.004
ternally+0.004
 en+0.004
Neg logit contributions
zag-0.004
ages-0.004
tr-0.004
ained-0.004
ometer-0.004
Token never
Token ID1239
Feature activation-1.20e+00

Pos logit contributions
ivated+0.008
ternally+0.008
 unatt+0.008
 My+0.008
 Int+0.008
Neg logit contributions
zag-0.010
ages-0.010
ained-0.010
tr-0.009
ine-0.009
Token bored
Token ID17533
Feature activation-3.83e+00

Pos logit contributions
ternally+0.035
 My+0.034
ivated+0.033
 Int+0.030
Give+0.029
Neg logit contributions
ages-0.051
ained-0.050
zag-0.050
olving-0.046
ies-0.045
Token again
Token ID757
Feature activation+1.31e-02

Pos logit contributions
ternally+0.175
 Int+0.152
ivated+0.144
 My+0.140
chie+0.138
Neg logit contributions
olving-0.111
 ending-0.107
 lesson-0.101
ained-0.100
zag-0.098
Token.
Token ID13
Feature activation+3.13e-01

Pos logit contributions
zag+0.001
ages+0.001
tr+0.000
ained+0.000
ometer+0.000
Neg logit contributions
ivated-0.000
ternally-0.000
 My-0.000
 unatt-0.000
 en-0.000
Token<|endoftext|>
Token ID50256
Feature activation-2.18e-01

Pos logit contributions
zag+0.013
ages+0.013
tr+0.012
ained+0.012
ometer+0.012
Neg logit contributions
 My-0.009
 en-0.009
ivated-0.009
 unatt-0.009
 I-0.009
TokenOne
Token ID3198
Feature activation-3.71e-02

Pos logit contributions
ivated+0.007
ternally+0.007
 unatt+0.007
 en+0.007
 My+0.007
Neg logit contributions
zag-0.008
ages-0.008
ained-0.008
tr-0.008
ometer-0.007
Token day
Token ID1110
Feature activation+8.20e-01

Pos logit contributions
ivated+0.002
ternally+0.002
 unatt+0.002
 My+0.002
 en+0.002
Neg logit contributions
zag-0.001
ages-0.001
ained-0.001
tr-0.001
ometer-0.001
Token extra
Token ID3131
Feature activation+4.98e-03

Pos logit contributions
ivated+0.010
 My+0.010
ternally+0.010
 unatt+0.009
 Int+0.009
Neg logit contributions
ages-0.014
zag-0.014
ained-0.013
tr-0.013
tails-0.012
Token careful
Token ID8161
Feature activation-4.35e-01

Pos logit contributions
ages+0.000
zag+0.000
tr+0.000
ained+0.000
ometer+0.000
Neg logit contributions
ivated-0.000
 My-0.000
 unatt-0.000
 en-0.000
ternally-0.000
Token and
Token ID290
Feature activation+9.73e-01

Pos logit contributions
ivated+0.015
ternally+0.015
 My+0.014
 unatt+0.014
 en+0.014
Neg logit contributions
ages-0.017
zag-0.017
ained-0.015
tr-0.015
ometer-0.015
Token never
Token ID1239
Feature activation-4.23e-01

Pos logit contributions
zag+0.042
ages+0.041
ained+0.039
tr+0.039
ometer+0.038
Neg logit contributions
 I-0.030
 en-0.029
 alone-0.029
 unatt-0.028
 My-0.028
Token leave
Token ID2666
Feature activation-1.17e+00

Pos logit contributions
ternally+0.012
ivated+0.012
 My+0.011
 unatt+0.011
 en+0.011
Neg logit contributions
zag-0.019
ages-0.019
tr-0.018
ained-0.017
tails-0.017
Token anyone
Token ID2687
Feature activation-3.40e+00

Pos logit contributions
ivated+0.038
ternally+0.036
 Int+0.036
 My+0.035
 en+0.034
Neg logit contributions
ages-0.047
zag-0.046
ained-0.044
tr-0.043
ine-0.042
Token behind
Token ID2157
Feature activation-2.25e+00

Pos logit contributions
ternally+0.105
 Int+0.104
 My+0.093
ivated+0.092
Hall+0.087
Neg logit contributions
packs-0.130
zag-0.129
ages-0.127
ies-0.125
ends-0.113
Token.
Token ID13
Feature activation+2.04e-01

Pos logit contributions
ivated+0.092
ternally+0.090
 Int+0.086
 en+0.083
 My+0.082
Neg logit contributions
ained-0.068
zag-0.068
packs-0.067
ages-0.061
tr-0.059
Token<|endoftext|>
Token ID50256
Feature activation+1.45e-02

Pos logit contributions
zag+0.009
ages+0.009
tr+0.009
ained+0.009
ometer+0.008
Neg logit contributions
 My-0.005
ivated-0.005
 en-0.005
 unatt-0.005
ternally-0.005
TokenOnce
Token ID7454
Feature activation+3.86e-01

Pos logit contributions
zag+0.001
ages+0.001
tr+0.001
ained+0.001
ometer+0.001
Neg logit contributions
ivated-0.000
 unatt-0.000
ternally-0.000
 en-0.000
 My-0.000
Token upon
Token ID2402
Feature activation+1.16e-01

Pos logit contributions
ages+0.009
zag+0.009
tr+0.008
ained+0.008
ometer+0.007
Neg logit contributions
 en-0.019
ivated-0.019
 My-0.018
 unatt-0.018
ternally-0.018
Token she
Token ID673
Feature activation-8.58e-03

Pos logit contributions
ages+0.019
zag+0.019
tr+0.018
ained+0.018
ometer+0.018
Neg logit contributions
 My-0.010
 en-0.010
ivated-0.010
 unatt-0.010
 I-0.010
Token had
Token ID550
Feature activation-3.62e-01

Pos logit contributions
ivated+0.000
 unatt+0.000
 en+0.000
 My+0.000
ternally+0.000
Neg logit contributions
zag-0.000
ages-0.000
tr-0.000
ained-0.000
ometer-0.000
Token never
Token ID1239
Feature activation+5.44e-02

Pos logit contributions
ivated+0.012
ternally+0.012
 unatt+0.012
 My+0.012
 en+0.012
Neg logit contributions
ages-0.014
zag-0.014
tr-0.013
ained-0.013
tails-0.012
Token sung
Token ID23568
Feature activation-8.08e-01

Pos logit contributions
zag+0.002
ages+0.002
tr+0.002
ained+0.002
ometer+0.002
Neg logit contributions
ivated-0.002
 unatt-0.002
 My-0.002
 en-0.002
ternally-0.002
Token in
Token ID287
Feature activation-4.49e-01

Pos logit contributions
ivated+0.028
ternally+0.027
 unatt+0.027
 en+0.026
 My+0.026
Neg logit contributions
zag-0.031
ages-0.030
ained-0.028
tr-0.028
ine-0.027
Token front
Token ID2166
Feature activation-3.36e+00

Pos logit contributions
ivated+0.013
ternally+0.013
 unatt+0.013
 My+0.012
 en+0.012
Neg logit contributions
zag-0.019
ages-0.019
ained-0.018
tr-0.018
ine-0.018
Token of
Token ID286
Feature activation-6.58e-01

Pos logit contributions
ternally+0.150
ivated+0.143
 Int+0.133
Bruce+0.128
 Nem+0.127
Neg logit contributions
tr-0.086
ment-0.081
zag-0.081
ained-0.078
packs-0.074
Token anyone
Token ID2687
Feature activation-2.33e+00

Pos logit contributions
ivated+0.019
ternally+0.019
 unatt+0.018
 en+0.018
 My+0.018
Neg logit contributions
zag-0.027
ages-0.027
tr-0.026
ained-0.026
tails-0.025
Token before
Token ID878
Feature activation+4.88e-02

Pos logit contributions
ternally+0.101
ivated+0.092
 Int+0.091
Leave+0.091
 sidelines+0.085
Neg logit contributions
zag-0.070
ages-0.064
ine-0.062
tr-0.060
ccoli-0.060
Token.
Token ID13
Feature activation+3.91e-01

Pos logit contributions
zag+0.002
ages+0.002
tr+0.002
ained+0.002
ometer+0.002
Neg logit contributions
ivated-0.001
ternally-0.001
 unatt-0.001
 en-0.001
 My-0.001
Token But
Token ID887
Feature activation+8.63e-01

Pos logit contributions
zag+0.019
ages+0.019
ained+0.017
tr+0.017
ccoli+0.017
Neg logit contributions
 My-0.010
 en-0.009
ivated-0.009
 I-0.009
 unatt-0.009
Token sail
Token ID14936
Feature activation-6.52e-02

Pos logit contributions
 unatt+0.006
ivated+0.006
ternally+0.006
 My+0.006
 en+0.006
Neg logit contributions
zag-0.008
ages-0.008
tr-0.008
ained-0.007
tails-0.007
Token his
Token ID465
Feature activation-1.28e+00

Pos logit contributions
ivated+0.002
 My+0.002
ternally+0.002
 en+0.002
 unatt+0.002
Neg logit contributions
ages-0.002
zag-0.002
tr-0.002
ained-0.002
ometer-0.002
Token boat
Token ID8848
Feature activation-3.50e-01

Pos logit contributions
ivated+0.048
 My+0.045
 Int+0.043
 unatt+0.042
 en+0.041
Neg logit contributions
zag-0.050
ages-0.049
ometer-0.044
ies-0.043
tr-0.042
Token in
Token ID287
Feature activation-1.12e+00

Pos logit contributions
ivated+0.011
 My+0.011
ternally+0.011
 en+0.011
 unatt+0.011
Neg logit contributions
zag-0.014
ages-0.014
tr-0.013
ained-0.013
ometer-0.012
Token the
Token ID262
Feature activation-1.73e+00

Pos logit contributions
ivated+0.041
ternally+0.040
 My+0.038
 unatt+0.038
 Int+0.035
Neg logit contributions
 common-0.039
packs-0.039
zag-0.038
ine-0.037
ained-0.037
Token big
Token ID1263
Feature activation-3.33e+00

Pos logit contributions
ivated+0.070
 My+0.066
ternally+0.065
 cheer+0.060
 unatt+0.060
Neg logit contributions
ained-0.056
zag-0.054
tr-0.052
ages-0.051
w-0.047
Token blue
Token ID4171
Feature activation-1.25e+00

Pos logit contributions
ivated+0.165
 My+0.151
ternally+0.146
ivating+0.142
My+0.141
Neg logit contributions
packs-0.093
ossible-0.083
ies-0.079
 tent-0.075
agons-0.074
Token sea
Token ID5417
Feature activation-1.77e-01

Pos logit contributions
ivated+0.044
 en+0.040
ternally+0.040
 unatt+0.040
 My+0.039
Neg logit contributions
zag-0.050
ages-0.049
packs-0.047
ained-0.047
tr-0.045
Token.
Token ID13
Feature activation-3.30e-01

Pos logit contributions
ivated+0.006
ternally+0.006
 My+0.006
 unatt+0.006
 en+0.006
Neg logit contributions
ages-0.007
zag-0.007
tr-0.006
ained-0.006
ometer-0.006
Token One
Token ID1881
Feature activation+1.53e-01

Pos logit contributions
ivated+0.012
 unatt+0.012
ternally+0.012
 en+0.011
 My+0.011
Neg logit contributions
zag-0.013
ages-0.012
tr-0.012
ained-0.012
ometer-0.011
Token day
Token ID1110
Feature activation+1.39e+00

Pos logit contributions
ages+0.004
zag+0.004
tr+0.004
ained+0.004
ometer+0.003
Neg logit contributions
ivated-0.007
 en-0.007
 unatt-0.007
 My-0.007
ternally-0.007
Token the
Token ID262
Feature activation+7.94e-02

Pos logit contributions
zag+0.024
ages+0.023
ained+0.022
tr+0.022
ometer+0.021
Neg logit contributions
 en-0.012
 unatt-0.011
 My-0.011
ivated-0.011
 alone-0.011
Token old
Token ID1468
Feature activation+2.40e-01

Pos logit contributions
zag+0.003
ages+0.003
tr+0.003
ained+0.003
ometer+0.003
Neg logit contributions
ivated-0.002
 unatt-0.002
ternally-0.002
 My-0.002
 en-0.002
Token cat
Token ID3797
Feature activation-3.12e-01

Pos logit contributions
ages+0.010
zag+0.010
ained+0.010
tr+0.010
ometer+0.009
Neg logit contributions
 en-0.007
 My-0.007
ivated-0.007
 unatt-0.007
ternally-0.007
Token was
Token ID373
Feature activation-4.58e-01

Pos logit contributions
ivated+0.011
 My+0.011
ternally+0.011
 unatt+0.011
 en+0.011
Neg logit contributions
ages-0.012
zag-0.012
tr-0.011
ained-0.010
ometer-0.010
Token never
Token ID1239
Feature activation-1.28e+00

Pos logit contributions
ivated+0.014
ternally+0.014
 My+0.014
 Int+0.013
 unatt+0.013
Neg logit contributions
zag-0.019
ages-0.019
ained-0.018
tr-0.018
tails-0.017
Token seen
Token ID1775
Feature activation-3.33e+00

Pos logit contributions
ivated+0.043
ternally+0.043
 My+0.042
folk+0.039
 Int+0.038
Neg logit contributions
ages-0.050
zag-0.048
ained-0.046
ies-0.045
tails-0.043
Token again
Token ID757
Feature activation-9.18e-02

Pos logit contributions
ivated+0.141
ternally+0.139
folk+0.136
chie+0.127
 Int+0.125
Neg logit contributions
ained-0.081
 for-0.080
tr-0.080
 lesson-0.076
olving-0.075
Token.
Token ID13
Feature activation+8.56e-02

Pos logit contributions
ternally+0.003
ivated+0.003
 My+0.003
 unatt+0.003
 en+0.003
Neg logit contributions
ages-0.004
zag-0.004
ained-0.003
tr-0.003
ometer-0.003
Token<|endoftext|>
Token ID50256
Feature activation-6.72e-02

Pos logit contributions
ages+0.004
zag+0.004
tr+0.004
ained+0.003
ometer+0.003
Neg logit contributions
ivated-0.002
 unatt-0.002
 en-0.002
ternally-0.002
 My-0.002
TokenOnce
Token ID7454
Feature activation-7.73e-02

Pos logit contributions
ivated+0.002
ternally+0.002
 unatt+0.002
 en+0.002
 My+0.002
Neg logit contributions
zag-0.003
ages-0.003
tr-0.002
ained-0.002
ometer-0.002
Token upon
Token ID2402
Feature activation+2.06e-01

Pos logit contributions
ivated+0.004
 unatt+0.004
ternally+0.004
 My+0.004
 en+0.004
Neg logit contributions
zag-0.002
ages-0.002
ained-0.002
tr-0.002
ometer-0.001
TokenL
Token ID43
Feature activation-1.03e-01

Pos logit contributions
ages+0.007
zag+0.007
tr+0.006
ained+0.006
ometer+0.006
Neg logit contributions
ivated-0.012
 My-0.012
 unatt-0.011
 en-0.011
ternally-0.011
Tokenily
Token ID813
Feature activation-5.02e-01

Pos logit contributions
ivated+0.004
 unatt+0.004
 en+0.004
ternally+0.004
 My+0.004
Neg logit contributions
zag-0.004
ages-0.003
ained-0.003
tr-0.003
ometer-0.003
Token and
Token ID290
Feature activation+1.93e-01

Pos logit contributions
ivated+0.017
ternally+0.017
 unatt+0.017
 My+0.017
 en+0.016
Neg logit contributions
ages-0.019
zag-0.019
tr-0.018
ained-0.018
ccoli-0.017
Token Ben
Token ID3932
Feature activation-5.10e-01

Pos logit contributions
zag+0.008
ages+0.008
tr+0.008
ained+0.008
ometer+0.008
Neg logit contributions
ivated-0.006
 en-0.006
 My-0.006
 unatt-0.006
ternally-0.005
Token were
Token ID547
Feature activation+2.67e-01

Pos logit contributions
ivated+0.017
ternally+0.017
 My+0.017
 unatt+0.017
 en+0.017
Neg logit contributions
ages-0.020
zag-0.019
tr-0.018
ained-0.018
ccoli-0.017
Token twins
Token ID20345
Feature activation-3.32e+00

Pos logit contributions
zag+0.010
ages+0.010
tr+0.009
ained+0.009
ometer+0.009
Neg logit contributions
 en-0.009
ivated-0.009
 unatt-0.009
 My-0.009
ternally-0.009
Token who
Token ID508
Feature activation+1.05e+00

Pos logit contributions
 Int+0.171
ternally+0.170
vious+0.166
ivated+0.162
Leave+0.158
Neg logit contributions
ages-0.067
ine-0.059
zag-0.056
ward-0.053
tr-0.051
Token liked
Token ID8288
Feature activation-2.60e-01

Pos logit contributions
zag+0.049
ages+0.048
tr+0.046
ometer+0.046
ained+0.045
Neg logit contributions
 en-0.028
 alone-0.027
 I-0.026
ivated-0.026
 My-0.025
Token to
Token ID284
Feature activation+2.11e-01

Pos logit contributions
ivated+0.008
ternally+0.008
 unatt+0.007
 My+0.007
 en+0.007
Neg logit contributions
ages-0.011
zag-0.011
tr-0.010
ained-0.010
ometer-0.010
Token play
Token ID711
Feature activation-2.51e-01

Pos logit contributions
ages+0.010
zag+0.010
tr+0.010
ained+0.010
ometer+0.010
Neg logit contributions
ivated-0.005
 en-0.005
 My-0.005
 unatt-0.005
ternally-0.005
Token outside
Token ID2354
Feature activation-5.40e-01

Pos logit contributions
ivated+0.007
ternally+0.007
 unatt+0.007
 My+0.007
 en+0.007
Neg logit contributions
zag-0.011
ages-0.011
tr-0.010
ained-0.010
ometer-0.010
Token said
Token ID531
Feature activation-1.32e+00

Pos logit contributions
 unatt+0.009
ivated+0.009
ternally+0.008
 My+0.008
 en+0.008
Neg logit contributions
zag-0.013
ages-0.013
tr-0.012
ine-0.011
ained-0.011
Token,
Token ID11
Feature activation-5.77e-01

Pos logit contributions
 unatt+0.061
ivated+0.061
ternally+0.060
 Int+0.056
 alone+0.055
Neg logit contributions
ages-0.035
zag-0.032
ometer-0.030
tr-0.029
ccoli-0.029
Token "
Token ID366
Feature activation-1.52e+00

Pos logit contributions
 unatt+0.020
ternally+0.020
ivated+0.019
 en+0.018
 alone+0.018
Neg logit contributions
ages-0.022
zag-0.022
tr-0.021
ometer-0.021
ccoli-0.020
TokenHi
Token ID17250
Feature activation-4.73e-01

Pos logit contributions
 en+0.049
ivated+0.046
 alone+0.046
ternally+0.044
 unatt+0.044
Neg logit contributions
tr-0.062
After-0.060
ages-0.059
w-0.058
Before-0.057
Token,
Token ID11
Feature activation-8.81e-01

Pos logit contributions
ivated+0.019
ternally+0.019
 unatt+0.019
 en+0.018
 alone+0.017
Neg logit contributions
zag-0.015
ages-0.015
tr-0.014
ained-0.013
ometer-0.013
Token can
Token ID460
Feature activation-3.30e+00

Pos logit contributions
ivated+0.023
 unatt+0.023
ternally+0.023
 en+0.021
 alone+0.020
Neg logit contributions
zag-0.039
tr-0.037
ages-0.037
ometer-0.036
ccoli-0.036
Token I
Token ID314
Feature activation-1.48e+00

Pos logit contributions
 unatt+0.106
vious+0.105
ivated+0.104
 outsider+0.101
lier+0.099
Neg logit contributions
w-0.112
ages-0.112
ves-0.110
zag-0.110
uffy-0.109
Token play
Token ID711
Feature activation-1.68e+00

Pos logit contributions
ivated+0.058
 unatt+0.057
ternally+0.056
folk+0.055
 Int+0.054
Neg logit contributions
zag-0.053
tr-0.047
ine-0.046
ages-0.043
tails-0.043
Token with
Token ID351
Feature activation-1.73e+00

Pos logit contributions
folk+0.066
ternally+0.065
ivated+0.065
 Int+0.062
 unatt+0.061
Neg logit contributions
zag-0.056
tr-0.050
ages-0.049
ends-0.048
ained-0.047
Token you
Token ID345
Feature activation-3.82e-01

Pos logit contributions
ivated+0.054
 Int+0.048
 unatt+0.048
ternally+0.047
 en+0.047
Neg logit contributions
w-0.068
ages-0.067
zag-0.064
tails-0.063
ward-0.062
Token?"
Token ID1701
Feature activation-8.00e-01

Pos logit contributions
ivated+0.014
ternally+0.014
 en+0.014
 unatt+0.013
 My+0.013
Neg logit contributions
zag-0.014
ages-0.013
tr-0.013
ained-0.013
ccoli-0.012
Token on
Token ID319
Feature activation+8.27e-01

Pos logit contributions
ages+0.050
zag+0.048
ccoli+0.048
tr+0.046
ometer+0.045
Neg logit contributions
 I-0.051
 alone-0.051
 My-0.050
 en-0.050
 me-0.048
Token,
Token ID11
Feature activation+7.88e-01

Pos logit contributions
ages+0.036
zag+0.035
tr+0.033
ained+0.033
ometer+0.032
Neg logit contributions
 My-0.025
 I-0.025
 alone-0.024
 en-0.024
ternally-0.024
Token Jane
Token ID12091
Feature activation+1.04e-01

Pos logit contributions
ages+0.038
zag+0.038
ained+0.036
tr+0.036
ometer+0.035
Neg logit contributions
 My-0.019
 en-0.019
 I-0.019
 unatt-0.018
ivated-0.018
Token was
Token ID373
Feature activation-2.26e-01

Pos logit contributions
zag+0.004
ages+0.004
tr+0.004
ained+0.004
ometer+0.004
Neg logit contributions
ivated-0.003
 unatt-0.003
 en-0.003
 My-0.003
ternally-0.003
Token never
Token ID1239
Feature activation-1.04e+00

Pos logit contributions
ivated+0.007
 My+0.007
ternally+0.007
 unatt+0.007
 en+0.007
Neg logit contributions
zag-0.010
ages-0.009
ained-0.009
tr-0.009
ine-0.008
Token bored
Token ID17533
Feature activation-3.30e+00

Pos logit contributions
ternally+0.028
 My+0.028
ivated+0.028
 Int+0.025
 unatt+0.025
Neg logit contributions
ages-0.045
zag-0.045
ained-0.043
tr-0.041
olving-0.041
Token.
Token ID13
Feature activation-8.29e-01

Pos logit contributions
ternally+0.134
 Int+0.115
ivated+0.112
 My+0.107
Hall+0.104
Neg logit contributions
olving-0.106
zag-0.103
ained-0.098
tr-0.095
 lesson-0.092
Token She
Token ID1375
Feature activation-2.25e-01

Pos logit contributions
ivated+0.028
 unatt+0.028
ternally+0.027
 en+0.026
 alone+0.025
Neg logit contributions
zag-0.032
ages-0.032
tr-0.031
ained-0.030
ometer-0.030
Token had
Token ID550
Feature activation-6.34e-01

Pos logit contributions
ivated+0.008
 unatt+0.008
 My+0.008
ternally+0.008
 en+0.008
Neg logit contributions
zag-0.008
ages-0.008
tr-0.008
ained-0.008
ine-0.007
Token many
Token ID867
Feature activation-1.08e+00

Pos logit contributions
ivated+0.023
ternally+0.022
 unatt+0.022
 My+0.022
 en+0.021
Neg logit contributions
ages-0.024
zag-0.023
ained-0.022
tr-0.021
ine-0.021
Token smooth
Token ID7209
Feature activation+2.72e-01

Pos logit contributions
ivated+0.046
 My+0.046
 unatt+0.044
ternally+0.043
 Int+0.042
Neg logit contributions
ages-0.032
zag-0.030
packs-0.029
ained-0.028
ira-0.028
Token away
Token ID1497
Feature activation+4.01e-01

Pos logit contributions
ternally+0.009
ivated+0.009
 My+0.009
 unatt+0.009
 en+0.009
Neg logit contributions
zag-0.015
ages-0.014
tr-0.014
ained-0.013
ometer-0.013
Token,
Token ID11
Feature activation-9.15e-01

Pos logit contributions
ages+0.018
zag+0.017
tr+0.017
ained+0.016
ometer+0.016
Neg logit contributions
 en-0.012
ivated-0.011
 unatt-0.011
 alone-0.011
 My-0.011
Token never
Token ID1239
Feature activation-9.93e-01

Pos logit contributions
ternally+0.029
ivated+0.028
 My+0.027
 unatt+0.027
 Int+0.026
Neg logit contributions
zag-0.037
ages-0.036
tr-0.034
ained-0.033
ccoli-0.032
Token to
Token ID284
Feature activation-1.05e+00

Pos logit contributions
ternally+0.034
ivated+0.033
 My+0.031
 Int+0.030
 unatt+0.029
Neg logit contributions
zag-0.038
ages-0.038
tr-0.036
ained-0.034
olving-0.034
Token be
Token ID307
Feature activation-1.35e+00

Pos logit contributions
ternally+0.035
ivated+0.034
 Int+0.033
 My+0.033
 unatt+0.031
Neg logit contributions
zag-0.040
ages-0.038
ine-0.038
tr-0.038
tails-0.037
Token seen
Token ID1775
Feature activation-3.30e+00

Pos logit contributions
ternally+0.044
ivated+0.043
 My+0.041
 Int+0.041
folk+0.037
Neg logit contributions
ages-0.055
ained-0.050
ine-0.049
zag-0.049
ends-0.046
Token again
Token ID757
Feature activation-1.51e-01

Pos logit contributions
ivated+0.145
ternally+0.139
 Int+0.137
chie+0.130
folk+0.128
Neg logit contributions
 for-0.077
olving-0.076
tr-0.072
ment-0.071
ained-0.071
Token.
Token ID13
Feature activation-4.64e-01

Pos logit contributions
ternally+0.005
ivated+0.005
 My+0.005
 unatt+0.005
 en+0.005
Neg logit contributions
zag-0.006
ages-0.006
ained-0.006
tr-0.005
ometer-0.005
Token
Token ID198
Feature activation+6.83e-01

Pos logit contributions
ivated+0.017
 unatt+0.017
ternally+0.017
 en+0.016
 My+0.015
Neg logit contributions
ages-0.017
zag-0.017
tr-0.015
ained-0.015
ometer-0.015
Token
Token ID198
Feature activation+3.13e-01

Pos logit contributions
ages+0.025
zag+0.025
tr+0.023
ained+0.023
ometer+0.022
Neg logit contributions
 en-0.024
ivated-0.024
 My-0.024
 alone-0.024
 unatt-0.023
TokenThe
Token ID464
Feature activation+1.41e-01

Pos logit contributions
ages+0.017
zag+0.017
tr+0.016
ained+0.016
ometer+0.016
Neg logit contributions
ivated-0.006
ternally-0.006
 en-0.006
 My-0.006
 unatt-0.006
Token,
Token ID11
Feature activation+3.98e-01

Pos logit contributions
 unatt+0.012
ivated+0.012
ternally+0.012
 en+0.012
 My+0.011
Neg logit contributions
ages-0.011
zag-0.011
tr-0.010
ometer-0.010
tails-0.009
Token "
Token ID366
Feature activation-1.28e+00

Pos logit contributions
zag+0.019
ages+0.019
ained+0.017
tr+0.017
ometer+0.017
Neg logit contributions
 My-0.010
 en-0.010
ivated-0.010
 unatt-0.010
ternally-0.010
TokenHi
Token ID17250
Feature activation-6.64e-01

Pos logit contributions
 unatt+0.039
 alone+0.037
 en+0.036
ivated+0.035
ternally+0.035
Neg logit contributions
zag-0.053
ages-0.053
w-0.051
tails-0.051
ained-0.050
Token Pedro
Token ID28855
Feature activation+7.17e-01

Pos logit contributions
 unatt+0.026
ivated+0.026
ternally+0.025
 en+0.025
 alone+0.024
Neg logit contributions
zag-0.023
ages-0.022
tails-0.020
ometer-0.020
ine-0.020
Token,
Token ID11
Feature activation-1.20e+00

Pos logit contributions
zag+0.031
ages+0.031
ained+0.030
tr+0.030
ometer+0.028
Neg logit contributions
 My-0.020
 en-0.020
 I-0.020
ternally-0.020
 unatt-0.019
Token can
Token ID460
Feature activation-3.29e+00

Pos logit contributions
ivated+0.038
 unatt+0.037
ternally+0.036
 en+0.033
 alone+0.032
Neg logit contributions
zag-0.049
tr-0.046
ages-0.045
ometer-0.044
ccoli-0.044
Token I
Token ID314
Feature activation-1.86e+00

Pos logit contributions
 unatt+0.112
ivated+0.099
vious+0.095
lier+0.092
 outsider+0.090
Neg logit contributions
zag-0.124
tails-0.120
ages-0.117
w-0.114
ves-0.113
Token ride
Token ID6594
Feature activation-9.10e-01

Pos logit contributions
ivated+0.066
 unatt+0.065
 en+0.062
ternally+0.062
 Int+0.060
Neg logit contributions
zag-0.076
tr-0.064
ages-0.061
tails-0.059
ine-0.058
Token you
Token ID345
Feature activation-7.40e-01

Pos logit contributions
ivated+0.025
 en+0.024
ternally+0.023
 unatt+0.023
 Int+0.023
Neg logit contributions
zag-0.042
ages-0.040
tr-0.038
ained-0.038
tails-0.037
Token?"
Token ID1701
Feature activation+3.15e-01

Pos logit contributions
ivated+0.025
 en+0.025
ternally+0.025
 My+0.024
 unatt+0.024
Neg logit contributions
zag-0.030
ages-0.027
tr-0.026
ained-0.026
ometer-0.024
Token Pedro
Token ID28855
Feature activation-8.24e-01

Pos logit contributions
zag+0.013
ages+0.013
tr+0.013
ained+0.012
ometer+0.012
Neg logit contributions
ivated-0.009
 en-0.009
 My-0.009
ternally-0.009
 unatt-0.009
Token.
Token ID13
Feature activation-8.79e-01

Pos logit contributions
ternally+0.031
ivated+0.030
 unatt+0.030
 My+0.028
 en+0.028
Neg logit contributions
zag-0.030
ages-0.030
tr-0.028
ometer-0.028
ccoli-0.027
Token "
Token ID366
Feature activation-1.14e+00

Pos logit contributions
 unatt+0.034
ternally+0.033
ivated+0.032
Leave+0.030
 en+0.029
Neg logit contributions
ages-0.031
zag-0.031
ometer-0.029
ccoli-0.028
tr-0.028
TokenM
Token ID44
Feature activation+6.11e-01

Pos logit contributions
ternally+0.034
 unatt+0.032
ivated+0.032
 en+0.032
 alone+0.031
Neg logit contributions
tr-0.046
ages-0.045
ained-0.045
zag-0.045
After-0.043
Tokenummy
Token ID13513
Feature activation+1.98e-01

Pos logit contributions
ages+0.020
zag+0.020
tr+0.019
ccoli+0.018
ained+0.018
Neg logit contributions
 My-0.024
 I-0.024
 en-0.024
 unatt-0.024
ivated-0.024
Token,
Token ID11
Feature activation-1.17e+00

Pos logit contributions
ages+0.008
zag+0.008
tr+0.007
ained+0.007
ometer+0.007
Neg logit contributions
ivated-0.007
 My-0.007
 unatt-0.007
 en-0.007
ternally-0.007
Token can
Token ID460
Feature activation-3.29e+00

Pos logit contributions
ivated+0.039
ternally+0.038
 unatt+0.037
 en+0.036
 Int+0.035
Neg logit contributions
zag-0.042
tr-0.042
ccoli-0.041
ages-0.041
ometer-0.039
Token I
Token ID314
Feature activation-1.49e+00

Pos logit contributions
lier+0.104
 unatt+0.101
ivated+0.096
vious+0.090
and+0.089
Neg logit contributions
zag-0.120
w-0.117
ages-0.116
ves-0.111
tails-0.109
Token ride
Token ID6594
Feature activation-8.05e-01

Pos logit contributions
 unatt+0.055
ivated+0.053
 en+0.051
ternally+0.051
 Int+0.049
Neg logit contributions
zag-0.059
tr-0.051
ages-0.048
ine-0.047
tails-0.047
Token in
Token ID287
Feature activation-1.90e+00

Pos logit contributions
ivated+0.022
ternally+0.021
 en+0.021
 unatt+0.021
 Int+0.020
Neg logit contributions
zag-0.036
ages-0.035
tr-0.033
ained-0.033
ometer-0.032
Token it
Token ID340
Feature activation-5.54e-01

Pos logit contributions
ivated+0.067
ternally+0.066
 Int+0.062
 unatt+0.062
 en+0.061
Neg logit contributions
zag-0.065
packs-0.061
ine-0.059
ained-0.059
After-0.056
Token?"
Token ID1701
Feature activation-1.96e+00

Pos logit contributions
ternally+0.020
ivated+0.020
 en+0.020
 My+0.019
 unatt+0.019
Neg logit contributions
zag-0.020
tr-0.019
ages-0.019
ained-0.018
ometer-0.017
Token said
Token ID531
Feature activation-6.32e-01

Pos logit contributions
 unatt+0.044
ternally+0.044
ivated+0.043
 My+0.040
Leave+0.040
Neg logit contributions
ages-0.033
zag-0.032
tails-0.029
ine-0.029
ccoli-0.029
Token,
Token ID11
Feature activation-2.48e-01

Pos logit contributions
 unatt+0.026
ivated+0.026
ternally+0.026
 en+0.025
 alone+0.024
Neg logit contributions
ages-0.019
zag-0.019
ometer-0.017
tr-0.017
ccoli-0.017
Token "
Token ID366
Feature activation-1.44e+00

Pos logit contributions
 unatt+0.008
ternally+0.008
ivated+0.007
 en+0.007
 My+0.007
Neg logit contributions
zag-0.010
ages-0.010
tr-0.010
ometer-0.009
ained-0.009
TokenHi
Token ID17250
Feature activation-1.06e+00

Pos logit contributions
 en+0.048
ivated+0.047
 alone+0.046
ternally+0.045
 unatt+0.044
Neg logit contributions
tr-0.058
w-0.054
After-0.053
ages-0.052
Before-0.051
Token,
Token ID11
Feature activation-1.42e+00

Pos logit contributions
ivated+0.049
ternally+0.048
 unatt+0.047
Leave+0.046
 en+0.045
Neg logit contributions
zag-0.028
uffy-0.026
ages-0.025
ccoli-0.025
tr-0.025
Token can
Token ID460
Feature activation-3.28e+00

Pos logit contributions
ivated+0.047
ternally+0.046
 unatt+0.046
folk+0.043
 Int+0.041
Neg logit contributions
tr-0.052
zag-0.052
ccoli-0.050
ometer-0.049
uffy-0.047
Token I
Token ID314
Feature activation-1.50e+00

Pos logit contributions
 unatt+0.103
ivated+0.102
vious+0.101
lier+0.099
 outsider+0.099
Neg logit contributions
w-0.116
zag-0.112
uffy-0.110
ccoli-0.110
oof-0.110
Token play
Token ID711
Feature activation-1.88e+00

Pos logit contributions
ivated+0.060
 unatt+0.059
ternally+0.058
folk+0.057
 Int+0.055
Neg logit contributions
zag-0.054
tr-0.047
ine-0.046
 common-0.043
tails-0.042
Token with
Token ID351
Feature activation-2.18e+00

Pos logit contributions
folk+0.076
ternally+0.074
ivated+0.074
 Int+0.071
 outsider+0.071
Neg logit contributions
zag-0.060
tr-0.053
ages-0.052
ends-0.051
ained-0.051
Token you
Token ID345
Feature activation-4.50e-01

Pos logit contributions
ivated+0.083
 outsider+0.078
 Int+0.075
ternally+0.072
 unatt+0.072
Neg logit contributions
w-0.077
oof-0.067
After-0.064
ages-0.064
 lunch-0.063
Token?"
Token ID1701
Feature activation-1.02e+00

Pos logit contributions
ivated+0.017
ternally+0.017
 en+0.016
 unatt+0.016
 My+0.016
Neg logit contributions
zag-0.016
ages-0.015
tr-0.015
ained-0.015
ccoli-0.014
Token "
Token ID366
Feature activation-1.34e+00

Pos logit contributions
 unatt+0.013
ternally+0.013
ivated+0.013
 en+0.012
 My+0.012
Neg logit contributions
ages-0.016
zag-0.016
tr-0.015
ometer-0.015
ccoli-0.015
TokenHello
Token ID15496
Feature activation-7.01e-01

Pos logit contributions
 unatt+0.038
ivated+0.036
 en+0.034
 alone+0.034
ternally+0.034
Neg logit contributions
zag-0.056
w-0.056
tr-0.056
ages-0.055
After-0.055
Token little
Token ID1310
Feature activation-1.23e+00

Pos logit contributions
ivated+0.028
ternally+0.027
 unatt+0.027
 en+0.026
Leave+0.026
Neg logit contributions
zag-0.023
ages-0.022
tr-0.021
ometer-0.020
ccoli-0.020
Token bird
Token ID6512
Feature activation-1.05e-01

Pos logit contributions
ivated+0.037
 unatt+0.032
ternally+0.031
 My+0.030
 en+0.030
Neg logit contributions
zag-0.053
ages-0.052
tr-0.052
tails-0.051
ies-0.051
Token,
Token ID11
Feature activation-1.33e+00

Pos logit contributions
ivated+0.004
 unatt+0.003
ternally+0.003
 en+0.003
 My+0.003
Neg logit contributions
zag-0.004
ages-0.004
tr-0.004
ained-0.004
ometer-0.004
Token can
Token ID460
Feature activation-3.27e+00

Pos logit contributions
ivated+0.044
 unatt+0.043
ternally+0.043
 Int+0.040
folk+0.039
Neg logit contributions
tr-0.048
zag-0.048
ccoli-0.045
olving-0.044
ometer-0.044
Token you
Token ID345
Feature activation-2.16e+00

Pos logit contributions
 unatt+0.111
lier+0.105
ivated+0.103
liest+0.100
ement+0.098
Neg logit contributions
w-0.108
zag-0.105
ages-0.100
tails-0.098
ves-0.097
Token pass
Token ID1208
Feature activation-1.29e+00

Pos logit contributions
folk+0.077
 unatt+0.075
 Int+0.073
ternally+0.073
ople+0.072
Neg logit contributions
zag-0.084
tr-0.067
tails-0.065
ine-0.065
ast-0.065
Token me
Token ID502
Feature activation+1.67e-02

Pos logit contributions
ivated+0.031
 en+0.028
ternally+0.027
 unatt+0.027
 Int+0.027
Neg logit contributions
zag-0.061
ained-0.060
ages-0.059
w-0.058
tr-0.058
Token a
Token ID257
Feature activation-4.11e-01

Pos logit contributions
zag+0.001
ages+0.001
tr+0.001
ained+0.001
ometer+0.001
Neg logit contributions
ivated-0.000
 en-0.000
 unatt-0.000
ternally-0.000
 My-0.000
Token tw
Token ID665
Feature activation-7.40e-01

Pos logit contributions
ivated+0.013
ternally+0.013
 unatt+0.013
 My+0.013
 en+0.013
Neg logit contributions
zag-0.017
ages-0.016
tr-0.016
ometer-0.015
ained-0.015
Token the
Token ID262
Feature activation-9.17e-01

Pos logit contributions
zag+0.010
ages+0.010
tr+0.010
ained+0.010
ometer+0.010
Neg logit contributions
 unatt-0.006
 en-0.006
ivated-0.006
 My-0.006
ternally-0.006
Token small
Token ID1402
Feature activation-5.53e-01

Pos logit contributions
ivated+0.031
ternally+0.030
 My+0.029
 unatt+0.029
 Int+0.028
Neg logit contributions
zag-0.036
ages-0.035
tr-0.033
 lesson-0.031
ira-0.031
Token gorilla
Token ID45314
Feature activation-6.50e-01

Pos logit contributions
ivated+0.021
 unatt+0.020
ternally+0.020
 My+0.019
 Int+0.019
Neg logit contributions
zag-0.021
ages-0.020
tr-0.018
ometer-0.018
ira-0.018
Token was
Token ID373
Feature activation-8.29e-01

Pos logit contributions
ivated+0.024
 My+0.023
ternally+0.023
 unatt+0.022
 en+0.022
Neg logit contributions
ages-0.025
zag-0.024
tr-0.022
tails-0.021
ometer-0.021
Token never
Token ID1239
Feature activation-1.66e+00

Pos logit contributions
ternally+0.026
 My+0.026
ivated+0.025
 Int+0.025
 I+0.024
Neg logit contributions
zag-0.035
ages-0.034
ained-0.032
tr-0.031
ends-0.030
Token seen
Token ID1775
Feature activation-3.26e+00

Pos logit contributions
ternally+0.060
 My+0.058
ivated+0.058
Give+0.053
yle+0.053
Neg logit contributions
ages-0.058
zag-0.057
ained-0.054
ies-0.052
ends-0.051
Token again
Token ID757
Feature activation-1.95e-01

Pos logit contributions
ivated+0.142
ternally+0.141
folk+0.130
 Int+0.124
Leave+0.123
Neg logit contributions
ained-0.075
olving-0.074
 for-0.073
 fault-0.073
ward-0.072
Token.
Token ID13
Feature activation+1.21e-01

Pos logit contributions
ternally+0.006
ivated+0.006
 My+0.006
 unatt+0.006
 en+0.006
Neg logit contributions
zag-0.008
ages-0.008
ained-0.007
tr-0.007
ine-0.007
Token<|endoftext|>
Token ID50256
Feature activation+8.81e-03

Pos logit contributions
zag+0.006
ages+0.006
tr+0.006
ained+0.006
ometer+0.006
Neg logit contributions
ivated-0.002
 en-0.002
 unatt-0.002
 My-0.002
ternally-0.002
TokenOnce
Token ID7454
Feature activation-1.80e-02

Pos logit contributions
zag+0.000
ages+0.000
tr+0.000
ained+0.000
ometer+0.000
Neg logit contributions
ivated-0.000
 unatt-0.000
ternally-0.000
 en-0.000
 My-0.000
Token upon
Token ID2402
Feature activation+2.31e-01

Pos logit contributions
ivated+0.001
 unatt+0.001
ternally+0.001
 en+0.001
 My+0.001
Neg logit contributions
zag-0.000
ages-0.000
tr-0.000
ained-0.000
ometer-0.000
Token The
Token ID383
Feature activation+9.26e-02

Pos logit contributions
zag+0.007
ages+0.007
tr+0.007
ained+0.006
ometer+0.006
Neg logit contributions
ivated-0.005
 en-0.005
 My-0.005
 unatt-0.005
ternally-0.005
Token original
Token ID2656
Feature activation+1.58e-01

Pos logit contributions
zag+0.004
ages+0.004
tr+0.004
ained+0.004
ometer+0.004
Neg logit contributions
ivated-0.003
 unatt-0.003
 en-0.003
 My-0.003
ternally-0.003
Token city
Token ID1748
Feature activation-5.28e-01

Pos logit contributions
ages+0.007
zag+0.007
tr+0.006
ained+0.006
ometer+0.006
Neg logit contributions
ivated-0.005
 en-0.005
 unatt-0.005
 My-0.005
ternally-0.005
Token was
Token ID373
Feature activation-2.29e-01

Pos logit contributions
ivated+0.018
 My+0.018
ternally+0.018
 unatt+0.018
 en+0.018
Neg logit contributions
zag-0.020
ages-0.020
tr-0.018
ained-0.018
ometer-0.017
Token never
Token ID1239
Feature activation-9.95e-01

Pos logit contributions
ivated+0.007
 My+0.007
ternally+0.007
 unatt+0.007
 en+0.007
Neg logit contributions
zag-0.010
ages-0.010
ained-0.009
tr-0.009
ometer-0.009
Token seen
Token ID1775
Feature activation-3.25e+00

Pos logit contributions
 My+0.030
ternally+0.029
ivated+0.029
 Int+0.027
 en+0.026
Neg logit contributions
zag-0.041
ages-0.041
ained-0.040
tr-0.038
olving-0.037
Token again
Token ID757
Feature activation+4.24e-02

Pos logit contributions
ivated+0.130
ternally+0.127
 Int+0.123
Give+0.115
Leave+0.114
Neg logit contributions
olving-0.102
zag-0.091
 lesson-0.087
ained-0.085
 ending-0.085
Token.
Token ID13
Feature activation-3.08e-02

Pos logit contributions
zag+0.002
ages+0.002
tr+0.002
ained+0.002
ometer+0.002
Neg logit contributions
ivated-0.001
ternally-0.001
 My-0.001
 unatt-0.001
 en-0.001
Token<|endoftext|>
Token ID50256
Feature activation+4.48e-01

Pos logit contributions
ivated+0.001
 unatt+0.001
ternally+0.001
 en+0.001
 My+0.001
Neg logit contributions
zag-0.001
ages-0.001
tr-0.001
ained-0.001
ometer-0.001
TokenOnce
Token ID7454
Feature activation+6.60e-02

Pos logit contributions
ages+0.014
zag+0.014
tr+0.013
ained+0.012
ometer+0.012
Neg logit contributions
 My-0.018
ivated-0.018
 en-0.018
 unatt-0.018
ternally-0.018
Token upon
Token ID2402
Feature activation+6.44e-01

Pos logit contributions
zag+0.001
ages+0.001
tr+0.001
ained+0.001
ometer+0.001
Neg logit contributions
ivated-0.003
 unatt-0.003
 en-0.003
 My-0.003
ternally-0.003
Token They
Token ID1119
Feature activation-7.80e-02

Pos logit contributions
 unatt+0.033
ivated+0.032
ternally+0.032
 cheer+0.029
 en+0.029
Neg logit contributions
ages-0.032
tr-0.031
zag-0.031
ometer-0.031
ained-0.030
Token thought
Token ID1807
Feature activation-3.57e-01

Pos logit contributions
 My+0.003
ternally+0.003
ivated+0.003
 unatt+0.003
 en+0.002
Neg logit contributions
ages-0.003
zag-0.003
tr-0.003
ained-0.003
ometer-0.003
Token,
Token ID11
Feature activation-1.13e-01

Pos logit contributions
ternally+0.013
ivated+0.013
 unatt+0.013
 My+0.013
 en+0.012
Neg logit contributions
zag-0.013
ages-0.012
ained-0.011
tr-0.011
ometer-0.011
Token "
Token ID366
Feature activation-9.53e-01

Pos logit contributions
 unatt+0.003
ivated+0.003
ternally+0.003
 My+0.003
 en+0.003
Neg logit contributions
ages-0.005
zag-0.005
tr-0.005
ained-0.005
ometer-0.005
TokenHow
Token ID2437
Feature activation+7.49e-01

Pos logit contributions
ivated+0.024
 unatt+0.024
 My+0.024
ternally+0.024
 en+0.023
Neg logit contributions
ages-0.044
zag-0.043
tr-0.043
ained-0.042
After-0.039
Token can
Token ID460
Feature activation-3.24e+00

Pos logit contributions
ages+0.031
zag+0.031
tails+0.029
ained+0.028
tr+0.028
Neg logit contributions
 I-0.024
 en-0.023
 My-0.023
 unatt-0.022
 alone-0.022
Token I
Token ID314
Feature activation-1.28e+00

Pos logit contributions
 unatt+0.138
ivated+0.130
ternally+0.120
lier+0.119
vious+0.115
Neg logit contributions
zag-0.103
ves-0.098
ages-0.092
 lesson-0.082
ira-0.082
Token make
Token ID787
Feature activation-1.41e+00

Pos logit contributions
ternally+0.043
ivated+0.043
 Int+0.043
 unatt+0.042
 My+0.041
Neg logit contributions
zag-0.052
tr-0.046
ages-0.046
olving-0.042
ine-0.042
Token the
Token ID262
Feature activation-1.64e+00

Pos logit contributions
 unatt+0.050
ivated+0.050
ternally+0.048
Leave+0.047
 Int+0.046
Neg logit contributions
zag-0.049
ages-0.049
ained-0.046
ward-0.043
ine-0.043
Token boats
Token ID16659
Feature activation-1.04e+00

Pos logit contributions
ternally+0.067
 My+0.066
 Int+0.066
ivated+0.064
 unatt+0.062
Neg logit contributions
zag-0.053
ained-0.051
 common-0.050
 lesson-0.048
ages-0.047
Token go
Token ID467
Feature activation-6.76e-01

Pos logit contributions
 My+0.031
ternally+0.030
 Int+0.029
ivated+0.029
 unatt+0.028
Neg logit contributions
zag-0.045
ages-0.043
ained-0.041
tr-0.040
olving-0.038
Token.
Token ID13
Feature activation-2.63e-01

Pos logit contributions
ivated+0.013
ternally+0.013
 My+0.012
 unatt+0.012
 en+0.012
Neg logit contributions
zag-0.018
ages-0.018
ained-0.017
ometer-0.017
tr-0.017
Token
Token ID198
Feature activation+3.91e-01

Pos logit contributions
 unatt+0.010
ternally+0.010
ivated+0.010
 en+0.009
 My+0.009
Neg logit contributions
ages-0.009
zag-0.009
tr-0.009
ained-0.009
ometer-0.008
Token
Token ID198
Feature activation+5.00e-01

Pos logit contributions
ages+0.017
zag+0.017
tr+0.016
ained+0.016
ometer+0.016
Neg logit contributions
 My-0.011
 en-0.011
ivated-0.011
 unatt-0.011
 I-0.011
Token"
Token ID1
Feature activation-7.33e-01

Pos logit contributions
zag+0.020
ages+0.019
tr+0.018
ained+0.018
ometer+0.018
Neg logit contributions
ivated-0.017
 My-0.017
 en-0.017
 I-0.017
 unatt-0.016
TokenHow
Token ID2437
Feature activation+1.21e+00

Pos logit contributions
 unatt+0.026
ivated+0.026
ternally+0.025
 alone+0.025
 en+0.025
Neg logit contributions
tr-0.026
zag-0.026
ages-0.026
ained-0.025
After-0.024
Token can
Token ID460
Feature activation-3.24e+00

Pos logit contributions
ages+0.052
zag+0.049
tails+0.049
igi+0.045
ained+0.044
Neg logit contributions
 I-0.040
 en-0.038
 My-0.038
 alone-0.035
 Int-0.034
Token we
Token ID356
Feature activation-1.24e+00

Pos logit contributions
 unatt+0.152
ivated+0.145
lier+0.137
vious+0.136
ternally+0.136
Neg logit contributions
ves-0.084
zag-0.080
ira-0.072
 common-0.070
ages-0.068
Token get
Token ID651
Feature activation-1.04e+00

Pos logit contributions
ternally+0.042
 My+0.042
 unatt+0.041
 Int+0.041
 en+0.040
Neg logit contributions
zag-0.048
tr-0.043
ages-0.042
tails-0.040
olving-0.040
Token the
Token ID262
Feature activation-6.19e-01

Pos logit contributions
ternally+0.035
 Int+0.034
 My+0.034
ivated+0.033
 unatt+0.032
Neg logit contributions
ages-0.037
ained-0.037
zag-0.037
w-0.035
ometer-0.034
Token jet
Token ID12644
Feature activation-4.44e-01

Pos logit contributions
ivated+0.018
 My+0.018
ternally+0.017
 unatt+0.017
 Int+0.017
Neg logit contributions
zag-0.027
ages-0.026
tr-0.026
ained-0.025
ometer-0.024
Token back
Token ID736
Feature activation+3.20e-01

Pos logit contributions
ivated+0.013
 My+0.013
 en+0.013
ternally+0.013
 unatt+0.013
Neg logit contributions
zag-0.019
ages-0.018
tr-0.018
ained-0.017
ometer-0.017
Token."
Token ID526
Feature activation-4.55e-01

Pos logit contributions
zag+0.002
ages+0.002
tr+0.002
ained+0.002
ometer+0.002
Neg logit contributions
ivated-0.001
 unatt-0.001
ternally-0.001
 en-0.001
 My-0.001
Token
Token ID198
Feature activation-4.74e-01

Pos logit contributions
 unatt+0.018
ternally+0.017
ivated+0.017
 en+0.016
 My+0.016
Neg logit contributions
zag-0.016
ages-0.016
ained-0.015
tr-0.014
tails-0.014
Token
Token ID198
Feature activation-2.56e-01

Pos logit contributions
 unatt+0.018
ivated+0.018
ternally+0.018
 en+0.017
 My+0.017
Neg logit contributions
zag-0.017
ages-0.016
tr-0.015
ained-0.015
ometer-0.015
Token"
Token ID1
Feature activation-1.42e+00

Pos logit contributions
 unatt+0.010
ivated+0.010
ternally+0.010
 en+0.010
 My+0.009
Neg logit contributions
zag-0.009
ages-0.009
tr-0.008
ained-0.008
tails-0.008
TokenHow
Token ID2437
Feature activation+9.81e-01

Pos logit contributions
 unatt+0.051
 alone+0.047
ternally+0.047
ivated+0.044
ople+0.042
Neg logit contributions
tr-0.053
zag-0.052
After-0.052
ages-0.051
Before-0.049
Token can
Token ID460
Feature activation-3.22e+00

Pos logit contributions
ages+0.042
zag+0.040
ained+0.037
tails+0.037
tr+0.036
Neg logit contributions
 I-0.032
 My-0.031
 en-0.030
ternally-0.028
 alone-0.028
Token you
Token ID345
Feature activation-8.18e-01

Pos logit contributions
 unatt+0.111
ivated+0.098
ternally+0.091
lier+0.083
 sidelines+0.081
Neg logit contributions
ves-0.126
ira-0.124
ages-0.123
zag-0.123
tails-0.121
Token talk
Token ID1561
Feature activation-6.14e-01

Pos logit contributions
 unatt+0.027
ternally+0.027
 My+0.026
ivated+0.026
 en+0.025
Neg logit contributions
zag-0.033
ages-0.031
tr-0.029
tails-0.029
ine-0.029
Token to
Token ID284
Feature activation-1.92e+00

Pos logit contributions
ivated+0.022
ternally+0.022
 unatt+0.021
 en+0.021
 My+0.021
Neg logit contributions
zag-0.023
ages-0.022
tr-0.021
ained-0.020
ometer-0.020
Token a
Token ID257
Feature activation-8.84e-01

Pos logit contributions
ivated+0.062
ternally+0.058
 unatt+0.056
 Int+0.056
 en+0.054
Neg logit contributions
zag-0.073
tails-0.069
tr-0.069
ages-0.068
ine-0.066
Token bird
Token ID6512
Feature activation-9.14e-02

Pos logit contributions
ivated+0.021
ternally+0.020
 unatt+0.020
 Int+0.018
 My+0.018
Neg logit contributions
zag-0.045
tr-0.042
ages-0.042
ometer-0.041
ira-0.040
Token to
Token ID284
Feature activation-7.86e-01

Pos logit contributions
ternally+0.024
ivated+0.023
 unatt+0.023
 My+0.022
 I+0.021
Neg logit contributions
zag-0.028
ages-0.026
ained-0.025
tr-0.024
ometer-0.023
Token think
Token ID892
Feature activation-7.93e-01

Pos logit contributions
 My+0.025
ternally+0.024
 unatt+0.024
ivated+0.023
folk+0.022
Neg logit contributions
zag-0.034
tr-0.030
ained-0.029
ages-0.029
tails-0.029
Token.
Token ID13
Feature activation-4.38e-01

Pos logit contributions
ivated+0.030
ternally+0.029
 unatt+0.028
 My+0.027
 en+0.026
Neg logit contributions
zag-0.029
ages-0.028
tr-0.026
ained-0.026
ine-0.026
Token "
Token ID366
Feature activation-7.74e-01

Pos logit contributions
 unatt+0.015
ternally+0.014
ivated+0.014
 en+0.013
 alone+0.013
Neg logit contributions
ages-0.018
zag-0.018
ometer-0.017
tr-0.016
ained-0.016
TokenHow
Token ID2437
Feature activation+3.07e-01

Pos logit contributions
 unatt+0.020
ivated+0.020
ternally+0.020
 en+0.019
 My+0.019
Neg logit contributions
tr-0.035
ages-0.035
zag-0.035
ained-0.034
ine-0.032
Token can
Token ID460
Feature activation-3.21e+00

Pos logit contributions
ages+0.012
zag+0.012
tr+0.011
ained+0.011
ometer+0.011
Neg logit contributions
 My-0.010
 en-0.010
ivated-0.010
 unatt-0.010
ternally-0.010
Token I
Token ID314
Feature activation-1.76e+00

Pos logit contributions
 unatt+0.107
ivated+0.100
lier+0.090
ternally+0.089
joy+0.084
Neg logit contributions
zag-0.130
ages-0.126
ves-0.125
tails-0.120
w-0.113
Token roll
Token ID4836
Feature activation-9.44e-01

Pos logit contributions
 unatt+0.069
ternally+0.068
ivated+0.067
folk+0.065
 Int+0.065
Neg logit contributions
zag-0.065
tr-0.051
ages-0.050
tails-0.048
ained-0.048
Token like
Token ID588
Feature activation-2.12e+00

Pos logit contributions
ivated+0.028
ternally+0.028
 unatt+0.027
 Int+0.027
 en+0.027
Neg logit contributions
zag-0.039
ained-0.037
ages-0.036
tr-0.036
w-0.035
Token the
Token ID262
Feature activation-1.27e+00

Pos logit contributions
ivated+0.080
ternally+0.077
 outsider+0.076
 unatt+0.075
 en+0.071
Neg logit contributions
zag-0.067
tr-0.065
ward-0.064
After-0.063
ained-0.061
Token ball
Token ID2613
Feature activation-1.26e+00

Pos logit contributions
ternally+0.053
 unatt+0.053
ivated+0.052
 Int+0.049
 My+0.047
Neg logit contributions
zag-0.042
ained-0.039
ages-0.036
tr-0.035
 lesson-0.035
Token,
Token ID11
Feature activation+1.48e-01

Pos logit contributions
 unatt+0.008
ivated+0.008
ternally+0.008
 My+0.008
 en+0.008
Neg logit contributions
zag-0.011
ages-0.011
tr-0.010
ained-0.010
ometer-0.010
Token gru
Token ID22848
Feature activation+6.64e-02

Pos logit contributions
zag+0.007
ages+0.007
tr+0.006
ained+0.006
ometer+0.006
Neg logit contributions
ivated-0.004
 en-0.004
 unatt-0.004
 My-0.004
ternally-0.004
Tokenff
Token ID487
Feature activation+1.09e-01

Pos logit contributions
zag+0.003
ages+0.003
tr+0.003
ained+0.003
ometer+0.002
Neg logit contributions
ivated-0.002
 unatt-0.002
 en-0.002
 My-0.002
ternally-0.002
Token voice
Token ID3809
Feature activation-1.87e-01

Pos logit contributions
zag+0.006
ages+0.006
tr+0.006
ained+0.006
ometer+0.006
Neg logit contributions
ivated-0.002
 unatt-0.002
 en-0.002
 My-0.002
ternally-0.002
Token calling
Token ID4585
Feature activation+5.46e-01

Pos logit contributions
ternally+0.006
 My+0.006
ivated+0.006
 unatt+0.006
 en+0.006
Neg logit contributions
zag-0.008
ages-0.008
tr-0.007
ained-0.007
tails-0.007
Token her
Token ID607
Feature activation+2.51e+00

Pos logit contributions
ages+0.026
zag+0.026
ained+0.025
tr+0.024
ccoli+0.024
Neg logit contributions
ivated-0.013
 My-0.013
 en-0.013
 unatt-0.013
ternally-0.013
Token name
Token ID1438
Feature activation-4.64e-01

Pos logit contributions
ained+0.109
ages+0.107
live+0.106
w+0.105
wl+0.098
Neg logit contributions
 back-0.087
 I-0.078
 alone-0.076
 me-0.073
 cheer-0.071
Token.
Token ID13
Feature activation-4.56e-02

Pos logit contributions
ivated+0.016
 en+0.016
ternally+0.016
 unatt+0.015
 My+0.015
Neg logit contributions
zag-0.018
ages-0.017
tr-0.017
ained-0.016
ometer-0.016
Token She
Token ID1375
Feature activation+6.12e-01

Pos logit contributions
 unatt+0.001
ivated+0.001
ternally+0.001
 en+0.001
 My+0.001
Neg logit contributions
ages-0.002
zag-0.002
tr-0.002
ained-0.002
ometer-0.002
Token looked
Token ID3114
Feature activation-2.08e-01

Pos logit contributions
ages+0.029
zag+0.028
ained+0.028
tr+0.026
ometer+0.026
Neg logit contributions
 en-0.016
 My-0.016
ternally-0.015
ivated-0.015
 me-0.015
Token up
Token ID510
Feature activation-7.08e-01

Pos logit contributions
 My+0.005
 unatt+0.005
ternally+0.005
ivated+0.005
 en+0.005
Neg logit contributions
zag-0.010
ages-0.010
tr-0.009
ained-0.009
ometer-0.009
Token in
Token ID287
Feature activation+8.88e-01

Pos logit contributions
ages+0.011
zag+0.011
tr+0.011
ained+0.011
ometer+0.010
Neg logit contributions
ivated-0.006
 en-0.006
 unatt-0.006
ternally-0.006
 My-0.006
Token the
Token ID262
Feature activation+5.69e-01

Pos logit contributions
zag+0.039
ages+0.038
ained+0.035
tr+0.035
ometer+0.034
Neg logit contributions
 en-0.028
 me-0.026
 My-0.026
 alone-0.026
 unatt-0.026
Token blankets
Token ID34794
Feature activation+4.08e-02

Pos logit contributions
zag+0.020
ages+0.020
ained+0.019
tr+0.018
ometer+0.018
Neg logit contributions
 unatt-0.021
ternally-0.021
 en-0.021
 My-0.021
 alone-0.020
Token and
Token ID290
Feature activation+1.96e+00

Pos logit contributions
zag+0.002
ages+0.002
tr+0.002
ained+0.001
ometer+0.001
Neg logit contributions
ivated-0.001
 unatt-0.001
 en-0.001
 My-0.001
ternally-0.001
Token made
Token ID925
Feature activation+7.22e-01

Pos logit contributions
zag+0.097
ained+0.091
ometer+0.087
oral+0.087
ogo+0.086
Neg logit contributions
 alone-0.050
 cheer-0.048
 I-0.048
 en-0.048
 unatt-0.047
Token a
Token ID257
Feature activation+2.32e+00

Pos logit contributions
zag+0.031
ages+0.030
tr+0.029
ained+0.029
ometer+0.028
Neg logit contributions
 en-0.021
ternally-0.021
 My-0.020
ivated-0.020
 unatt-0.020
Token tent
Token ID11105
Feature activation+1.06e+00

Pos logit contributions
ained+0.116
ages+0.109
zag+0.106
live+0.105
ometers+0.102
Neg logit contributions
 cheer-0.069
 me-0.064
 back-0.061
 en-0.058
 g-0.058
Token on
Token ID319
Feature activation+7.84e-01

Pos logit contributions
ages+0.048
zag+0.046
ained+0.045
ometer+0.043
ccoli+0.043
Neg logit contributions
 unatt-0.029
 alone-0.029
 en-0.028
 I-0.027
ivated-0.027
Token the
Token ID262
Feature activation-2.08e-01

Pos logit contributions
ages+0.042
zag+0.041
ained+0.039
tr+0.038
ometer+0.038
Neg logit contributions
 en-0.016
 unatt-0.016
 My-0.015
 alone-0.015
 I-0.015
Token floor
Token ID4314
Feature activation+5.63e-01

Pos logit contributions
ivated+0.008
 en+0.008
ternally+0.008
 My+0.008
 unatt+0.007
Neg logit contributions
zag-0.007
ages-0.007
tr-0.007
ained-0.006
ometer-0.006
Token.
Token ID13
Feature activation+9.95e-01

Pos logit contributions
ages+0.025
zag+0.025
tr+0.023
ained+0.023
ometer+0.023
Neg logit contributions
 unatt-0.016
 en-0.016
ivated-0.015
 My-0.015
 alone-0.015
Token and
Token ID290
Feature activation+2.18e-02

Pos logit contributions
ternally+0.011
ivated+0.010
 unatt+0.010
 My+0.010
 en+0.010
Neg logit contributions
ages-0.011
zag-0.011
ained-0.010
tr-0.010
ometer-0.010
Token scared
Token ID12008
Feature activation-1.01e+00

Pos logit contributions
ages+0.001
zag+0.001
tr+0.001
ained+0.001
ometer+0.001
Neg logit contributions
ivated-0.001
 unatt-0.001
ternally-0.001
 My-0.001
 en-0.001
Token.
Token ID13
Feature activation+9.09e-02

Pos logit contributions
ivated+0.043
ternally+0.042
 unatt+0.040
 My+0.039
 Int+0.039
Neg logit contributions
ages-0.030
ained-0.027
zag-0.027
ment-0.026
ies-0.026
Token They
Token ID1119
Feature activation+6.60e-01

Pos logit contributions
ages+0.003
zag+0.003
tr+0.002
ained+0.002
ometer+0.002
Neg logit contributions
ivated-0.004
 unatt-0.004
 en-0.004
ternally-0.004
 My-0.004
Token worked
Token ID3111
Feature activation+2.07e+00

Pos logit contributions
zag+0.029
ages+0.029
ained+0.027
tr+0.027
ometer+0.027
Neg logit contributions
 en-0.019
ivated-0.019
 alone-0.018
 unatt-0.018
ternally-0.018
Token hard
Token ID1327
Feature activation+2.35e+00

Pos logit contributions
ages+0.089
ira+0.088
tr+0.087
tails+0.086
ccoli+0.086
Neg logit contributions
 alone-0.067
 back-0.066
 so-0.065
 en-0.063
 unatt-0.056
Token to
Token ID284
Feature activation+9.43e-02

Pos logit contributions
ccoli+0.128
tr+0.125
omo+0.125
live+0.123
ages+0.122
Neg logit contributions
 alone-0.050
 so-0.041
 en-0.039
ivated-0.038
 unatt-0.038
Token find
Token ID1064
Feature activation-5.34e-01

Pos logit contributions
zag+0.005
ages+0.005
tr+0.004
ained+0.004
ometer+0.004
Neg logit contributions
ivated-0.002
 unatt-0.002
 en-0.002
 My-0.002
ternally-0.002
Token food
Token ID2057
Feature activation+4.40e-01

Pos logit contributions
ivated+0.019
 unatt+0.019
 My+0.018
ternally+0.018
 en+0.018
Neg logit contributions
ages-0.020
zag-0.019
tr-0.018
ained-0.018
ometer-0.017
Token and
Token ID290
Feature activation+1.53e+00

Pos logit contributions
zag+0.018
ages+0.018
tr+0.017
ained+0.017
ometer+0.017
Neg logit contributions
 unatt-0.013
 en-0.013
ivated-0.013
 My-0.013
ternally-0.013
Token help
Token ID1037
Feature activation-9.75e-01

Pos logit contributions
zag+0.069
ained+0.065
ages+0.063
ometer+0.062
tr+0.061
Neg logit contributions
 en-0.044
 I-0.044
 unatt-0.043
 alone-0.043
 cheer-0.042
Token Spot
Token ID15899
Feature activation+5.65e-01

Pos logit contributions
ivated+0.020
 unatt+0.020
ternally+0.019
 en+0.019
 alone+0.018
Neg logit contributions
zag-0.019
ages-0.019
tr-0.018
tails-0.017
ained-0.017
Token.
Token ID13
Feature activation+7.84e-02

Pos logit contributions
zag+0.026
ages+0.026
ained+0.025
tr+0.025
ometer+0.024
Neg logit contributions
 alone-0.014
 My-0.014
 en-0.014
 unatt-0.014
 I-0.014
Token Spot
Token ID15899
Feature activation+1.65e-01

Pos logit contributions
zag+0.003
ages+0.003
tr+0.003
ained+0.003
ometer+0.003
Neg logit contributions
ivated-0.003
 unatt-0.003
 en-0.003
ternally-0.003
 My-0.003
Token had
Token ID550
Feature activation+1.77e-01

Pos logit contributions
zag+0.007
ages+0.007
tr+0.006
ained+0.006
ometer+0.006
Neg logit contributions
ivated-0.005
 en-0.005
 My-0.005
 unatt-0.005
ternally-0.005
Token a
Token ID257
Feature activation+1.01e+00

Pos logit contributions
zag+0.007
ages+0.007
tr+0.006
ained+0.006
ometer+0.006
Neg logit contributions
 en-0.006
 My-0.006
ivated-0.006
 unatt-0.006
ternally-0.006
Token long
Token ID890
Feature activation+2.39e+00

Pos logit contributions
ages+0.050
zag+0.048
ained+0.048
ment+0.047
ometers+0.045
Neg logit contributions
 en-0.025
 My-0.023
 alone-0.022
 I-0.022
 me-0.022
Token tail
Token ID7894
Feature activation-4.68e-01

Pos logit contributions
ometers+0.110
ages+0.109
ment+0.103
ccoli+0.103
ained+0.102
Neg logit contributions
 me-0.064
 alone-0.063
 en-0.062
 back-0.055
 I-0.054
Token that
Token ID326
Feature activation-7.03e-01

Pos logit contributions
ternally+0.017
ivated+0.017
 unatt+0.016
 My+0.016
 en+0.015
Neg logit contributions
zag-0.018
ages-0.017
tr-0.017
ained-0.016
ometer-0.015
Token w
Token ID266
Feature activation+4.53e-01

Pos logit contributions
ivated+0.027
ternally+0.026
 unatt+0.025
 en+0.023
 My+0.023
Neg logit contributions
ages-0.026
zag-0.026
tr-0.025
ometer-0.023
ained-0.023
Tokenagged
Token ID14655
Feature activation+1.78e+00

Pos logit contributions
zag+0.017
ages+0.017
tr+0.016
ccoli+0.016
ometer+0.015
Neg logit contributions
ternally-0.015
 en-0.015
ivated-0.015
 unatt-0.015
 My-0.015
Token when
Token ID618
Feature activation+1.59e-01

Pos logit contributions
oral+0.098
ccoli+0.094
ages+0.092
aj+0.092
uffy+0.092
Neg logit contributions
 alone-0.040
 en-0.037
 back-0.031
 me-0.029
 so-0.029
Token.
Token ID13
Feature activation-3.60e-01

Pos logit contributions
ivated+0.024
ternally+0.024
 en+0.023
 My+0.023
 unatt+0.023
Neg logit contributions
zag-0.026
ages-0.026
tr-0.024
ometer-0.024
ained-0.023
Token She
Token ID1375
Feature activation+1.42e-01

Pos logit contributions
ivated+0.012
 unatt+0.012
ternally+0.012
 en+0.012
 My+0.011
Neg logit contributions
ages-0.014
zag-0.013
ained-0.013
tr-0.013
ometer-0.013
Token learned
Token ID4499
Feature activation+1.10e+00

Pos logit contributions
zag+0.006
ages+0.006
tr+0.006
ained+0.006
ometer+0.006
Neg logit contributions
ivated-0.004
 en-0.004
 unatt-0.004
 My-0.004
ternally-0.004
Token that
Token ID326
Feature activation+9.22e-02

Pos logit contributions
zag+0.059
ages+0.057
tr+0.054
ccoli+0.054
ometer+0.053
Neg logit contributions
 en-0.025
 me-0.024
 I-0.024
 My-0.024
 alone-0.022
Token it
Token ID340
Feature activation-3.92e-01

Pos logit contributions
ages+0.004
zag+0.004
tr+0.004
ained+0.004
ometer+0.004
Neg logit contributions
ivated-0.002
 unatt-0.002
 en-0.002
ternally-0.002
 My-0.002
Token's
Token ID338
Feature activation+2.49e+00

Pos logit contributions
ivated+0.009
 unatt+0.009
ternally+0.008
 My+0.008
 en+0.008
Neg logit contributions
zag-0.020
ages-0.020
tr-0.018
ained-0.018
ometer-0.018
Token important
Token ID1593
Feature activation+1.40e+00

Pos logit contributions
zag+0.139
ops+0.132
ages+0.130
ometer+0.129
ira+0.126
Neg logit contributions
 en-0.067
 alone-0.067
 me-0.065
 so-0.064
 especially-0.062
Token to
Token ID284
Feature activation+1.12e+00

Pos logit contributions
zag+0.083
tr+0.081
aj+0.081
ogo+0.080
ages+0.079
Neg logit contributions
 I-0.021
 alone-0.017
 me-0.017
 My-0.016
 back-0.015
Token help
Token ID1037
Feature activation-8.33e-01

Pos logit contributions
ages+0.056
zag+0.055
tr+0.054
ometer+0.053
ained+0.053
Neg logit contributions
 I-0.027
 me-0.027
 en-0.027
 cheer-0.026
 alone-0.025
Token others
Token ID1854
Feature activation+9.36e-02

Pos logit contributions
ivated+0.024
 Int+0.023
 unatt+0.023
ternally+0.022
 en+0.022
Neg logit contributions
ages-0.038
zag-0.035
ine-0.034
ained-0.033
tails-0.033
Token and
Token ID290
Feature activation+7.74e-01

Pos logit contributions
ages+0.004
zag+0.004
tr+0.003
ained+0.003
ometer+0.003
Neg logit contributions
ivated-0.003
 unatt-0.003
 en-0.003
 My-0.003
ternally-0.003
Token unknown
Token ID6439
Feature activation+1.54e-01

Pos logit contributions
 My+0.045
ternally+0.045
 Int+0.043
 unatt+0.042
ivated+0.042
Neg logit contributions
zag-0.046
ages-0.046
ine-0.046
ained-0.046
 lesson-0.042
Token adventure
Token ID8855
Feature activation-4.50e-01

Pos logit contributions
ages+0.006
zag+0.006
tr+0.006
ained+0.006
ometer+0.006
Neg logit contributions
ivated-0.005
 unatt-0.005
 en-0.005
 My-0.005
ternally-0.005
Token.
Token ID13
Feature activation-6.68e-01

Pos logit contributions
ivated+0.015
ternally+0.015
 en+0.015
 My+0.015
 unatt+0.015
Neg logit contributions
zag-0.018
ages-0.018
tr-0.016
ained-0.016
ometer-0.016
Token
Token ID198
Feature activation+4.79e-01

Pos logit contributions
 unatt+0.022
ivated+0.021
ternally+0.021
 en+0.020
 alone+0.020
Neg logit contributions
ages-0.026
zag-0.026
ained-0.025
tr-0.025
ometer-0.024
Token
Token ID198
Feature activation+2.41e-01

Pos logit contributions
ages+0.021
zag+0.021
tr+0.020
ained+0.019
ccoli+0.019
Neg logit contributions
 en-0.014
 My-0.013
ivated-0.013
ternally-0.013
 unatt-0.013
TokenWhen
Token ID2215
Feature activation+1.06e+00

Pos logit contributions
ages+0.010
zag+0.010
tr+0.009
ained+0.009
ometer+0.009
Neg logit contributions
ivated-0.008
 en-0.008
 My-0.008
ternally-0.007
 unatt-0.007
Token they
Token ID484
Feature activation+5.48e-02

Pos logit contributions
ages+0.061
zag+0.060
tr+0.057
ccoli+0.056
ained+0.055
Neg logit contributions
 I-0.021
 My-0.020
 en-0.019
 me-0.018
ivated-0.018
Token arrived
Token ID5284
Feature activation+4.87e-01

Pos logit contributions
zag+0.003
ages+0.003
tr+0.002
ained+0.002
ometer+0.002
Neg logit contributions
ivated-0.001
 unatt-0.001
 en-0.001
 My-0.001
ternally-0.001
Token at
Token ID379
Feature activation+4.00e-01

Pos logit contributions
ages+0.021
zag+0.021
tr+0.020
ained+0.019
ccoli+0.019
Neg logit contributions
ivated-0.014
 en-0.014
 unatt-0.014
 My-0.014
 alone-0.014
Token the
Token ID262
Feature activation-2.04e-01

Pos logit contributions
ages+0.022
zag+0.022
tr+0.020
ained+0.020
ometer+0.020
Neg logit contributions
 en-0.007
 unatt-0.007
ivated-0.007
 My-0.007
ternally-0.007
Token park
Token ID3952
Feature activation+4.79e-03

Pos logit contributions
ivated+0.006
ternally+0.006
 My+0.006
 unatt+0.006
 en+0.006
Neg logit contributions
zag-0.009
ages-0.008
tr-0.008
ained-0.008
ometer-0.008
Token.
Token ID13
Feature activation-2.07e-01

Pos logit contributions
zag+0.007
ages+0.007
tr+0.006
ained+0.006
ometer+0.006
Neg logit contributions
ivated-0.005
 en-0.005
 unatt-0.005
ternally-0.005
 My-0.005
Token Her
Token ID2332
Feature activation+5.11e-01

Pos logit contributions
ivated+0.006
 unatt+0.006
ternally+0.006
 en+0.006
 My+0.006
Neg logit contributions
zag-0.009
ages-0.009
tr-0.008
ained-0.008
ometer-0.008
Token mom
Token ID1995
Feature activation+1.92e-01

Pos logit contributions
zag+0.021
ages+0.021
ained+0.020
tr+0.019
ometer+0.019
Neg logit contributions
 en-0.016
 My-0.016
ternally-0.015
 unatt-0.015
ivated-0.015
Token listened
Token ID16399
Feature activation+7.42e-01

Pos logit contributions
zag+0.008
ages+0.008
tr+0.007
ained+0.007
ometer+0.007
Neg logit contributions
ivated-0.006
 en-0.006
 unatt-0.006
 My-0.006
ternally-0.006
Token and
Token ID290
Feature activation-3.10e-01

Pos logit contributions
zag+0.034
ages+0.034
ained+0.032
tr+0.032
ometer+0.030
Neg logit contributions
 en-0.020
ivated-0.019
 My-0.019
ternally-0.019
 unatt-0.019
Token put
Token ID1234
Feature activation+6.12e-01

Pos logit contributions
 My+0.009
ivated+0.009
 en+0.009
ternally+0.009
 unatt+0.009
Neg logit contributions
ages-0.013
zag-0.013
tr-0.012
ained-0.012
ccoli-0.012
Token some
Token ID617
Feature activation+9.99e-02

Pos logit contributions
zag+0.032
ages+0.031
tr+0.029
ained+0.029
ometer+0.029
Neg logit contributions
 unatt-0.013
ternally-0.013
 en-0.013
 alone-0.013
ivated-0.012
Token ice
Token ID4771
Feature activation+1.30e+00

Pos logit contributions
ages+0.003
zag+0.003
tr+0.003
ained+0.003
ometer+0.003
Neg logit contributions
ivated-0.004
 unatt-0.004
 en-0.004
 My-0.004
ternally-0.004
Token in
Token ID287
Feature activation+8.05e-01

Pos logit contributions
zag+0.050
ages+0.046
ccoli+0.046
tails+0.046
ained+0.046
Neg logit contributions
 unatt-0.044
 alone-0.042
 back-0.041
ternally-0.041
 en-0.041
Token the
Token ID262
Feature activation-3.45e-01

Pos logit contributions
ages+0.043
zag+0.043
tr+0.040
ained+0.040
ometer+0.039
Neg logit contributions
 en-0.016
 alone-0.016
 My-0.016
 unatt-0.016
 I-0.016
Token lemon
Token ID18873
Feature activation+6.98e-02

Pos logit contributions
ivated+0.012
ternally+0.011
 My+0.011
 unatt+0.011
 en+0.011
Neg logit contributions
ages-0.014
zag-0.013
tr-0.013
ained-0.012
ometer-0.012
TokenM
Token ID44
Feature activation+1.23e+00

Pos logit contributions
zag+0.111
ages+0.108
ccoli+0.105
ogo+0.104
aj+0.102
Neg logit contributions
My-0.041
I-0.038
 I-0.038
 My-0.037
 en-0.036
Tokenummy
Token ID13513
Feature activation+5.64e-01

Pos logit contributions
ages+0.029
ccoli+0.026
zag+0.025
tr+0.023
packs+0.023
Neg logit contributions
ternally-0.061
 My-0.060
 I-0.059
 me-0.059
 en-0.058
Token!
Token ID0
Feature activation-2.01e-01

Pos logit contributions
ages+0.023
zag+0.023
ained+0.021
tr+0.021
ometer+0.021
Neg logit contributions
 en-0.018
 My-0.018
 I-0.017
ivated-0.017
ternally-0.017
Token Look
Token ID6803
Feature activation-3.53e-01

Pos logit contributions
 unatt+0.006
ivated+0.006
ternally+0.006
 en+0.005
 My+0.005
Neg logit contributions
ages-0.009
zag-0.009
tr-0.008
ained-0.008
ometer-0.008
Token at
Token ID379
Feature activation+5.74e-01

Pos logit contributions
ivated+0.012
 unatt+0.012
 en+0.012
ternally+0.012
 My+0.012
Neg logit contributions
ages-0.013
zag-0.013
tr-0.012
ccoli-0.012
ometer-0.012
Token me
Token ID502
Feature activation+6.51e-01

Pos logit contributions
ages+0.030
zag+0.030
tr+0.028
ained+0.027
ometer+0.027
Neg logit contributions
 en-0.012
 My-0.012
 I-0.012
ternally-0.012
ivated-0.012
Token!
Token ID0
Feature activation-1.10e-01

Pos logit contributions
ages+0.028
zag+0.026
tr+0.026
ained+0.025
ometer+0.025
Neg logit contributions
ivated-0.020
 My-0.020
 en-0.019
 I-0.019
 unatt-0.019
Tokenâ
Token ID22940
Feature activation-9.49e-02

Pos logit contributions
 unatt+0.003
ivated+0.003
ternally+0.003
 en+0.003
 My+0.003
Neg logit contributions
ages-0.005
zag-0.005
tr-0.005
ained-0.005
ometer-0.005
Token€
Token ID26391
Feature activation+2.08e-01

Pos logit contributions
ivated+0.003
 en+0.003
 unatt+0.003
 My+0.003
ternally+0.003
Neg logit contributions
zag-0.004
ages-0.004
tr-0.003
ained-0.003
ometer-0.003
Token Beth
Token ID19223
Feature activation-2.30e-01

Pos logit contributions
zag+0.008
ages+0.008
tr+0.007
ained+0.007
ometer+0.007
Neg logit contributions
ivated-0.007
 My-0.007
 unatt-0.007
 en-0.007
ternally-0.007
Token exclaimed
Token ID33552
Feature activation-5.76e-01

Pos logit contributions
 unatt+0.008
ivated+0.008
ternally+0.007
 My+0.007
 en+0.007
Neg logit contributions
zag-0.009
ages-0.009
tr-0.008
ained-0.008
ometer-0.008
Token day
Token ID1110
Feature activation-1.08e+00

Pos logit contributions
ages+0.004
zag+0.004
tr+0.003
ained+0.003
ometer+0.003
Neg logit contributions
ivated-0.006
 unatt-0.006
 en-0.006
 My-0.006
ternally-0.006
Token.
Token ID13
Feature activation+9.55e-01

Pos logit contributions
ternally+0.044
ivated+0.043
 Int+0.041
 My+0.041
 en+0.040
Neg logit contributions
ages-0.038
zag-0.035
tr-0.032
ine-0.031
ained-0.031
Token They
Token ID1119
Feature activation+1.14e+00

Pos logit contributions
zag+0.038
ages+0.038
ine+0.034
ained+0.034
tr+0.034
Neg logit contributions
 I-0.033
 My-0.033
 en-0.031
 Int-0.030
 alone-0.029
Token were
Token ID547
Feature activation+3.86e-01

Pos logit contributions
zag+0.049
ages+0.049
ained+0.047
ometer+0.045
tr+0.044
Neg logit contributions
 en-0.033
 alone-0.033
 cheer-0.032
 unatt-0.032
ivated-0.031
Token the
Token ID262
Feature activation-4.16e-01

Pos logit contributions
zag+0.018
ages+0.018
tr+0.017
ometer+0.017
ained+0.017
Neg logit contributions
 en-0.010
ivated-0.010
 My-0.010
 unatt-0.010
 alone-0.010
Token best
Token ID1266
Feature activation+4.47e-01

Pos logit contributions
ivated+0.020
 My+0.019
ternally+0.019
 unatt+0.019
 Int+0.019
Neg logit contributions
zag-0.010
ages-0.010
tr-0.010
ained-0.009
tails-0.008
Token of
Token ID286
Feature activation+2.92e-01

Pos logit contributions
ages+0.022
zag+0.021
ained+0.020
tr+0.020
ccoli+0.020
Neg logit contributions
 en-0.011
 My-0.011
 alone-0.010
 unatt-0.010
 I-0.010
Token friends
Token ID2460
Feature activation-7.37e-01

Pos logit contributions
zag+0.010
ages+0.010
tr+0.009
ometer+0.009
ained+0.009
Neg logit contributions
 en-0.012
ivated-0.011
 unatt-0.011
ternally-0.011
 My-0.011
Token.
Token ID13
Feature activation+5.84e-01

Pos logit contributions
ivated+0.029
ternally+0.028
 Int+0.027
 en+0.027
 My+0.027
Neg logit contributions
ages-0.026
zag-0.025
tr-0.023
ained-0.022
ometer-0.022
Token<|endoftext|>
Token ID50256
Feature activation-5.49e-01

Pos logit contributions
zag+0.025
ages+0.025
ometer+0.023
ained+0.022
tr+0.022
Neg logit contributions
 My-0.018
 I-0.017
 en-0.017
ivated-0.017
 unatt-0.016
TokenOne
Token ID3198
Feature activation+4.68e-01

Pos logit contributions
ivated+0.020
ternally+0.020
 unatt+0.020
 en+0.020
 My+0.020
Neg logit contributions
zag-0.020
ages-0.019
ained-0.018
tr-0.018
ometer-0.017
Token
Token ID220
Feature activation+3.84e-01

Pos logit contributions
 unatt+0.016
ternally+0.016
ivated+0.015
 en+0.015
 alone+0.014
Neg logit contributions
ages-0.018
zag-0.018
tr-0.017
ometer-0.016
ained-0.016
Token
Token ID198
Feature activation-2.30e-01

Pos logit contributions
ages+0.017
zag+0.017
tr+0.015
ained+0.015
ometer+0.015
Neg logit contributions
ivated-0.011
 My-0.011
 en-0.011
 unatt-0.011
ternally-0.011
Token
Token ID198
Feature activation-4.65e-02

Pos logit contributions
 unatt+0.008
ternally+0.008
ivated+0.008
 en+0.008
 My+0.008
Neg logit contributions
zag-0.009
ages-0.009
tr-0.008
ained-0.008
ometer-0.008
TokenLu
Token ID25596
Feature activation+3.15e-01

Pos logit contributions
 unatt+0.002
ivated+0.002
 en+0.002
ternally+0.002
 My+0.002
Neg logit contributions
zag-0.002
ages-0.002
tr-0.001
ained-0.001
ometer-0.001
Tokency
Token ID948
Feature activation+1.19e-01

Pos logit contributions
zag+0.014
ages+0.014
ained+0.013
tr+0.012
ometer+0.012
Neg logit contributions
ternally-0.009
ivated-0.009
 unatt-0.009
 My-0.009
 en-0.009
Token walked
Token ID6807
Feature activation+8.23e-01

Pos logit contributions
zag+0.005
ages+0.005
tr+0.005
ained+0.005
ometer+0.005
Neg logit contributions
ivated-0.003
 unatt-0.003
 en-0.003
 My-0.003
ternally-0.003
Token around
Token ID1088
Feature activation-1.27e-01

Pos logit contributions
ages+0.046
zag+0.044
ccoli+0.043
tr+0.043
ained+0.042
Neg logit contributions
 alone-0.016
ivated-0.016
 back-0.015
 en-0.015
 me-0.014
Token the
Token ID262
Feature activation-5.33e-01

Pos logit contributions
ternally+0.003
ivated+0.003
 unatt+0.003
 My+0.003
 en+0.003
Neg logit contributions
zag-0.006
ages-0.006
tr-0.005
ained-0.005
ometer-0.005
Token attic
Token ID46113
Feature activation-1.30e-01

Pos logit contributions
ivated+0.021
ternally+0.021
 en+0.021
 unatt+0.021
 My+0.021
Neg logit contributions
zag-0.017
ages-0.017
tr-0.016
ained-0.015
ometer-0.015
Token and
Token ID290
Feature activation+4.98e-01

Pos logit contributions
ivated+0.004
ternally+0.004
 My+0.004
 unatt+0.004
 en+0.004
Neg logit contributions
zag-0.005
ages-0.005
tr-0.005
ained-0.005
ometer-0.004
Token noticed
Token ID6810
Feature activation+1.14e-01

Pos logit contributions
ages+0.026
zag+0.026
tr+0.024
ained+0.024
ometer+0.024
Neg logit contributions
ivated-0.011
 en-0.010
 unatt-0.010
 My-0.010
 alone-0.010
Token wanted
Token ID2227
Feature activation-3.59e-01

Pos logit contributions
ivated+0.004
ternally+0.004
 My+0.004
 unatt+0.004
 en+0.004
Neg logit contributions
ages-0.005
zag-0.005
tr-0.005
ained-0.005
ometer-0.005
Token to
Token ID284
Feature activation-1.13e+00

Pos logit contributions
ivated+0.012
ternally+0.011
 unatt+0.011
 en+0.011
 My+0.011
Neg logit contributions
ages-0.015
zag-0.015
tr-0.014
ained-0.013
ometer-0.013
Token take
Token ID1011
Feature activation+6.73e-01

Pos logit contributions
 unatt+0.042
ternally+0.041
ivated+0.040
 My+0.037
 en+0.037
Neg logit contributions
zag-0.043
ages-0.041
tails-0.039
tr-0.038
ine-0.036
Token a
Token ID257
Feature activation-8.92e-01

Pos logit contributions
zag+0.029
ages+0.028
tr+0.028
ometer+0.027
ained+0.027
Neg logit contributions
 en-0.020
 My-0.020
 alone-0.019
 unatt-0.019
ivated-0.019
Token big
Token ID1263
Feature activation-9.27e-01

Pos logit contributions
ivated+0.031
ternally+0.031
 en+0.030
 My+0.030
 unatt+0.030
Neg logit contributions
zag-0.035
tr-0.032
ages-0.031
ometer-0.030
tails-0.028
Token challenge
Token ID4427
Feature activation-7.79e-02

Pos logit contributions
ivated+0.033
 My+0.032
ternally+0.032
 en+0.032
 unatt+0.031
Neg logit contributions
zag-0.035
ages-0.033
tr-0.032
ometer-0.030
tails-0.030
Token and
Token ID290
Feature activation+8.57e-01

Pos logit contributions
ivated+0.003
ternally+0.002
 en+0.002
 unatt+0.002
 My+0.002
Neg logit contributions
zag-0.003
ages-0.003
tr-0.003
ained-0.003
ometer-0.003
Token he
Token ID339
Feature activation+2.45e-01

Pos logit contributions
zag+0.041
ages+0.041
ained+0.040
tr+0.039
ccoli+0.038
Neg logit contributions
 en-0.021
 I-0.021
 unatt-0.021
 alone-0.021
 My-0.020
Token decided
Token ID3066
Feature activation-2.94e-01

Pos logit contributions
zag+0.011
ages+0.011
ained+0.010
tr+0.010
ometer+0.010
Neg logit contributions
 en-0.007
ivated-0.007
 unatt-0.007
 My-0.007
ternally-0.007
Token to
Token ID284
Feature activation-1.96e-01

Pos logit contributions
ivated+0.009
ternally+0.009
 unatt+0.009
 en+0.008
 My+0.008
Neg logit contributions
ages-0.013
zag-0.013
tr-0.011
ometer-0.011
ained-0.011
Token catch
Token ID4929
Feature activation-5.51e-01

Pos logit contributions
 unatt+0.006
ivated+0.006
ternally+0.006
 My+0.005
 en+0.005
Neg logit contributions
zag-0.009
ages-0.009
tr-0.008
ained-0.008
ometer-0.008
Token it
Token ID340
Feature activation-6.73e-01

Pos logit contributions
zag+0.005
ages+0.005
tr+0.005
ained+0.005
ometer+0.004
Neg logit contributions
ivated-0.003
 unatt-0.003
 en-0.003
 My-0.003
ternally-0.003
Token and
Token ID290
Feature activation-3.35e-01

Pos logit contributions
ivated+0.022
ternally+0.022
 unatt+0.022
 My+0.022
 en+0.021
Neg logit contributions
zag-0.028
ages-0.026
ained-0.024
tr-0.024
tails-0.022
Token I
Token ID314
Feature activation+6.19e-01

Pos logit contributions
ivated+0.008
ternally+0.008
 unatt+0.008
 en+0.008
 My+0.008
Neg logit contributions
zag-0.016
ages-0.016
tr-0.015
ained-0.014
ometer-0.014
Token just
Token ID655
Feature activation-6.92e-01

Pos logit contributions
ages+0.024
zag+0.023
tr+0.022
ained+0.022
ometer+0.021
Neg logit contributions
 en-0.021
ivated-0.020
 My-0.020
ternally-0.020
 I-0.020
Token keep
Token ID1394
Feature activation-8.38e-01

Pos logit contributions
ivated+0.023
 unatt+0.022
ternally+0.022
 My+0.022
 en+0.021
Neg logit contributions
zag-0.027
ages-0.027
ained-0.025
tr-0.025
ccoli-0.024
Token trying
Token ID2111
Feature activation-2.21e-01

Pos logit contributions
ivated+0.025
ternally+0.024
 unatt+0.024
 My+0.024
 Int+0.023
Neg logit contributions
ages-0.035
zag-0.035
ained-0.033
tails-0.032
ine-0.031
Token."
Token ID526
Feature activation+6.46e-02

Pos logit contributions
ivated+0.006
ternally+0.006
 unatt+0.006
 en+0.006
 My+0.006
Neg logit contributions
zag-0.010
ages-0.010
ained-0.009
tr-0.009
ometer-0.009
Token
Token ID198
Feature activation-5.09e-01

Pos logit contributions
ages+0.003
zag+0.003
tr+0.003
ained+0.003
ometer+0.003
Neg logit contributions
ivated-0.002
 unatt-0.002
 en-0.002
ternally-0.002
 My-0.002
Token
Token ID198
Feature activation-4.59e-01

Pos logit contributions
 unatt+0.019
ivated+0.018
ternally+0.018
 en+0.018
 My+0.018
Neg logit contributions
zag-0.019
ages-0.018
tr-0.017
ained-0.017
ometer-0.016
TokenBlue
Token ID14573
Feature activation+1.14e+00

Pos logit contributions
 unatt+0.015
ivated+0.015
 en+0.014
ternally+0.014
 My+0.014
Neg logit contributions
zag-0.018
ages-0.018
tr-0.017
ained-0.016
After-0.016
Token thought
Token ID1807
Feature activation-2.22e-01

Pos logit contributions
ages+0.051
ained+0.050
zag+0.050
tr+0.049
ometers+0.049
Neg logit contributions
 en-0.031
ternally-0.030
 me-0.030
ivated-0.029
 alone-0.029
Token one
Token ID530
Feature activation+4.62e-01

Pos logit contributions
zag+0.014
ages+0.013
tr+0.013
ained+0.013
ometer+0.012
Neg logit contributions
 My-0.009
 unatt-0.009
 en-0.009
ternally-0.009
ivated-0.009
Token of
Token ID286
Feature activation+4.03e-01

Pos logit contributions
ages+0.019
zag+0.019
ained+0.018
tr+0.017
tails+0.017
Neg logit contributions
 My-0.015
 unatt-0.014
 en-0.014
 I-0.014
ternally-0.014
Token your
Token ID534
Feature activation+2.18e-01

Pos logit contributions
zag+0.021
ages+0.021
tr+0.019
ained+0.019
ometer+0.019
Neg logit contributions
 My-0.009
 en-0.008
 unatt-0.008
ternally-0.008
ivated-0.008
Token toys
Token ID14958
Feature activation+4.71e-01

Pos logit contributions
zag+0.009
ages+0.009
tr+0.008
ained+0.008
ometer+0.008
Neg logit contributions
 en-0.007
ivated-0.007
 unatt-0.007
 My-0.007
ternally-0.007
Token or
Token ID393
Feature activation+2.73e-01

Pos logit contributions
zag+0.021
ages+0.021
tr+0.020
ained+0.020
ometer+0.019
Neg logit contributions
 unatt-0.013
 My-0.013
 en-0.012
ivated-0.012
 I-0.012
Token books
Token ID3835
Feature activation+8.49e-02

Pos logit contributions
zag+0.012
ages+0.012
ained+0.011
tr+0.011
ometer+0.011
Neg logit contributions
 My-0.008
 en-0.008
 unatt-0.008
ivated-0.008
ternally-0.008
Token."
Token ID526
Feature activation+1.38e-03

Pos logit contributions
zag+0.004
ages+0.004
tr+0.004
ained+0.003
ometer+0.003
Neg logit contributions
ivated-0.002
 en-0.002
 unatt-0.002
ternally-0.002
 My-0.002
Token Ben
Token ID3932
Feature activation-3.20e-01

Pos logit contributions
ages+0.000
zag+0.000
tr+0.000
ained+0.000
ometer+0.000
Neg logit contributions
ivated-0.000
 unatt-0.000
ternally-0.000
 en-0.000
 My-0.000
Token thinks
Token ID6834
Feature activation-3.95e-02

Pos logit contributions
 unatt+0.014
ivated+0.013
 My+0.013
ternally+0.013
 en+0.013
Neg logit contributions
ages-0.010
zag-0.010
tr-0.009
ccoli-0.008
ained-0.008
Token for
Token ID329
Feature activation+9.81e-01

Pos logit contributions
ivated+0.001
ternally+0.001
 unatt+0.001
 My+0.001
 en+0.001
Neg logit contributions
zag-0.001
ages-0.001
ained-0.001
tr-0.001
ometer-0.001
Token a
Token ID257
Feature activation+1.04e+00

Pos logit contributions
zag+0.046
ages+0.046
ometer+0.042
ained+0.042
tr+0.041
Neg logit contributions
 My-0.027
 I-0.027
 en-0.027
 me-0.025
 unatt-0.025
Token she
Token ID673
Feature activation-4.30e-01

Pos logit contributions
zag+0.039
ages+0.039
tr+0.037
ained+0.037
ometer+0.035
Neg logit contributions
 I-0.019
 en-0.019
 My-0.019
 alone-0.018
 unatt-0.018
Token was
Token ID373
Feature activation-3.41e-01

Pos logit contributions
ivated+0.015
ternally+0.015
 unatt+0.015
 My+0.015
 en+0.015
Neg logit contributions
zag-0.016
ages-0.016
tr-0.015
ained-0.014
ccoli-0.014
Token there
Token ID612
Feature activation+3.32e-01

Pos logit contributions
ternally+0.009
 My+0.008
ivated+0.008
 unatt+0.008
 Int+0.008
Neg logit contributions
zag-0.016
ages-0.016
ained-0.015
tr-0.015
ometer-0.014
Token and
Token ID290
Feature activation-1.29e-01

Pos logit contributions
ages+0.014
zag+0.014
tr+0.013
ained+0.013
ometer+0.012
Neg logit contributions
 unatt-0.010
 en-0.010
 My-0.010
ivated-0.010
ternally-0.010
Token she
Token ID673
Feature activation+4.58e-01

Pos logit contributions
ivated+0.004
 unatt+0.004
ternally+0.003
 My+0.003
 en+0.003
Neg logit contributions
ages-0.006
zag-0.006
tr-0.005
ained-0.005
ometer-0.005
Token said
Token ID531
Feature activation-5.91e-01

Pos logit contributions
ages+0.018
zag+0.018
ained+0.017
tr+0.017
ometer+0.016
Neg logit contributions
 en-0.015
ivated-0.015
 My-0.015
ternally-0.015
 unatt-0.014
Token she
Token ID673
Feature activation+8.47e-01

Pos logit contributions
ivated+0.020
ternally+0.020
 unatt+0.020
 en+0.019
 My+0.019
Neg logit contributions
ages-0.022
zag-0.022
tr-0.020
ometer-0.020
ccoli-0.020
Token just
Token ID655
Feature activation+3.47e-01

Pos logit contributions
zag+0.037
ages+0.037
ained+0.035
tr+0.034
olving+0.033
Neg logit contributions
 en-0.024
 I-0.023
 My-0.023
ternally-0.022
 alone-0.022
Token wanted
Token ID2227
Feature activation-9.97e-01

Pos logit contributions
zag+0.016
ages+0.016
ained+0.015
tr+0.015
ometer+0.015
Neg logit contributions
 en-0.009
 My-0.009
 unatt-0.009
ivated-0.009
ternally-0.009
Token to
Token ID284
Feature activation-3.61e-01

Pos logit contributions
ivated+0.038
ternally+0.036
 en+0.034
 unatt+0.033
 Int+0.033
Neg logit contributions
ages-0.037
zag-0.034
tr-0.033
ine-0.033
ccoli-0.032
Token stay
Token ID2652
Feature activation-5.40e-02

Pos logit contributions
ivated+0.010
 unatt+0.010
ternally+0.010
 en+0.010
 My+0.010
Neg logit contributions
zag-0.016
ages-0.016
tr-0.015
ained-0.014
tails-0.014
Token Jill
Token ID22772
Feature activation-5.04e-01

Pos logit contributions
ages+0.010
zag+0.010
tr+0.009
ained+0.009
ometer+0.009
Neg logit contributions
ivated-0.006
 en-0.006
 unatt-0.006
 My-0.006
ternally-0.006
Token was
Token ID373
Feature activation-7.32e-01

Pos logit contributions
ivated+0.017
 unatt+0.017
ternally+0.017
 My+0.017
 en+0.016
Neg logit contributions
zag-0.020
ages-0.019
tr-0.018
ained-0.017
ine-0.017
Token counting
Token ID14143
Feature activation+4.81e-01

Pos logit contributions
ternally+0.025
 My+0.024
 unatt+0.024
ivated+0.024
 Int+0.023
Neg logit contributions
zag-0.028
ages-0.027
ained-0.026
ends-0.025
ine-0.025
Token slowly
Token ID6364
Feature activation+7.66e-01

Pos logit contributions
ages+0.021
zag+0.021
tr+0.020
ained+0.019
ometer+0.019
Neg logit contributions
 en-0.014
ivated-0.014
 unatt-0.013
 My-0.013
ternally-0.013
Token.
Token ID13
Feature activation-1.03e-01

Pos logit contributions
ages+0.034
zag+0.033
ained+0.031
tr+0.031
ometer+0.031
Neg logit contributions
 en-0.022
ivated-0.021
 unatt-0.021
 My-0.021
 alone-0.021
Token She
Token ID1375
Feature activation+1.20e-01

Pos logit contributions
 unatt+0.003
ternally+0.003
ivated+0.003
 My+0.003
 en+0.003
Neg logit contributions
zag-0.004
ages-0.004
tr-0.004
ained-0.004
ometer-0.004
Token looked
Token ID3114
Feature activation-7.71e-01

Pos logit contributions
zag+0.005
ages+0.005
tr+0.005
ained+0.005
ometer+0.004
Neg logit contributions
ivated-0.004
 unatt-0.004
 en-0.004
 My-0.004
ternally-0.004
Token around
Token ID1088
Feature activation-7.28e-01

Pos logit contributions
 My+0.024
ternally+0.024
 unatt+0.024
ivated+0.023
 I+0.022
Neg logit contributions
zag-0.030
ages-0.030
ained-0.028
tr-0.028
ometer-0.027
Token and
Token ID290
Feature activation-7.22e-01

Pos logit contributions
ternally+0.026
 My+0.026
 unatt+0.026
ivated+0.026
 en+0.025
Neg logit contributions
zag-0.025
ages-0.024
tr-0.023
ained-0.022
olving-0.022
Token saw
Token ID2497
Feature activation-2.65e-01

Pos logit contributions
ternally+0.022
 My+0.021
 unatt+0.021
ivated+0.020
 en+0.020
Neg logit contributions
zag-0.030
ages-0.030
tr-0.028
ained-0.027
ine-0.027
Token a
Token ID257
Feature activation+2.62e-01

Pos logit contributions
 unatt+0.010
ivated+0.010
ternally+0.009
 My+0.009
 en+0.009
Neg logit contributions
ages-0.009
zag-0.009
tr-0.009
ained-0.009
ometer-0.008
TokenHey
Token ID10814
Feature activation-9.55e-01

Pos logit contributions
ternally+0.033
 alone+0.033
 en+0.033
ivated+0.033
 unatt+0.033
Neg logit contributions
ained-0.034
w-0.034
ages-0.033
tr-0.033
After-0.032
Token,
Token ID11
Feature activation-9.63e-01

Pos logit contributions
ternally+0.038
ivated+0.037
 unatt+0.037
 My+0.036
 en+0.035
Neg logit contributions
zag-0.029
ages-0.029
ies-0.027
uffy-0.027
tr-0.026
Token that
Token ID326
Feature activation-1.38e+00

Pos logit contributions
ternally+0.033
 unatt+0.032
ivated+0.032
 Int+0.030
 en+0.030
Neg logit contributions
zag-0.033
ages-0.033
tr-0.032
oys-0.031
ained-0.031
Token's
Token ID338
Feature activation+5.56e-01

Pos logit contributions
ivated+0.045
 unatt+0.042
ternally+0.042
folk+0.039
 en+0.037
Neg logit contributions
zag-0.059
ages-0.055
tr-0.055
ained-0.054
w-0.051
Token my
Token ID616
Feature activation-3.60e-01

Pos logit contributions
ages+0.030
zag+0.029
ometer+0.027
tr+0.027
ained+0.027
Neg logit contributions
 en-0.011
 My-0.011
 unatt-0.011
 I-0.011
ivated-0.011
Token ball
Token ID2613
Feature activation-2.02e+00

Pos logit contributions
ivated+0.012
ternally+0.012
 unatt+0.012
 My+0.011
 en+0.011
Neg logit contributions
zag-0.015
ages-0.014
tr-0.014
ained-0.013
ometer-0.013
Token!
Token ID0
Feature activation-1.14e+00

Pos logit contributions
ivated+0.094
ternally+0.088
 Int+0.085
Leave+0.085
folk+0.084
Neg logit contributions
zag-0.067
tr-0.060
ages-0.055
ained-0.051
uffy-0.050
Token Why
Token ID4162
Feature activation+6.04e-01

Pos logit contributions
 unatt+0.033
ternally+0.033
ivated+0.032
 alone+0.029
 en+0.029
Neg logit contributions
tr-0.050
ages-0.050
ometer-0.049
zag-0.049
ccoli-0.047
Token did
Token ID750
Feature activation-1.01e+00

Pos logit contributions
ages+0.025
zag+0.025
tr+0.023
ained+0.023
ometer+0.022
Neg logit contributions
 I-0.019
 en-0.019
 My-0.019
ternally-0.018
 unatt-0.018
Token you
Token ID345
Feature activation-7.35e-01

Pos logit contributions
 unatt+0.020
ivated+0.020
ternally+0.020
 en+0.017
 Int+0.016
Neg logit contributions
ages-0.053
zag-0.052
tails-0.049
tr-0.048
ometer-0.047
Token kick
Token ID4829
Feature activation-1.06e+00

Pos logit contributions
ternally+0.023
 unatt+0.023
 My+0.022
 Int+0.022
ivated+0.021
Neg logit contributions
zag-0.031
ages-0.029
tr-0.027
ained-0.027
ine-0.027
Token dog
Token ID3290
Feature activation-9.04e-01

Pos logit contributions
zag+0.021
ages+0.021
ained+0.020
tr+0.020
ccoli+0.019
Neg logit contributions
 en-0.013
 unatt-0.012
 alone-0.012
ivated-0.012
 My-0.012
Token was
Token ID373
Feature activation-7.07e-01

Pos logit contributions
ivated+0.033
ternally+0.032
 unatt+0.031
 My+0.031
 en+0.030
Neg logit contributions
zag-0.034
ages-0.033
tr-0.031
ine-0.029
tails-0.029
Token gone
Token ID3750
Feature activation+3.29e-01

Pos logit contributions
ternally+0.022
 My+0.022
ivated+0.021
 I+0.020
 Int+0.020
Neg logit contributions
zag-0.030
ages-0.029
ained-0.028
tr-0.027
ine-0.026
Token and
Token ID290
Feature activation-4.63e-01

Pos logit contributions
ages+0.015
zag+0.014
tr+0.014
ained+0.013
ometer+0.013
Neg logit contributions
 unatt-0.009
ivated-0.009
 en-0.009
ternally-0.009
 My-0.009
Token he
Token ID339
Feature activation-7.97e-01

Pos logit contributions
ivated+0.015
ternally+0.015
 My+0.014
 unatt+0.014
 en+0.013
Neg logit contributions
ages-0.018
zag-0.018
tr-0.017
ained-0.017
tails-0.016
Token felt
Token ID2936
Feature activation-1.92e+00

Pos logit contributions
ivated+0.032
 My+0.031
ternally+0.030
 unatt+0.030
 en+0.029
Neg logit contributions
ages-0.027
zag-0.027
tr-0.024
ine-0.024
tails-0.023
Token much
Token ID881
Feature activation-1.34e+00

Pos logit contributions
ternally+0.080
ople+0.079
folk+0.078
ican+0.078
ard+0.076
Neg logit contributions
ages-0.054
ained-0.053
 lesson-0.048
ends-0.047
ment-0.044
Token better
Token ID1365
Feature activation+7.70e-01

Pos logit contributions
 My+0.058
ternally+0.054
ivated+0.053
yle+0.052
folk+0.052
Neg logit contributions
ages-0.038
ained-0.034
 lesson-0.034
tr-0.033
zag-0.033
Token.
Token ID13
Feature activation+7.44e-02

Pos logit contributions
zag+0.037
ages+0.037
tr+0.036
ained+0.035
ccoli+0.035
Neg logit contributions
 unatt-0.020
 alone-0.020
 en-0.018
 I-0.018
ivated-0.018
Token He
Token ID679
Feature activation-4.06e-02

Pos logit contributions
ages+0.003
zag+0.003
tr+0.003
ained+0.003
ometer+0.003
Neg logit contributions
ivated-0.002
 unatt-0.002
ternally-0.002
 en-0.002
 My-0.002
Token played
Token ID2826
Feature activation-1.41e-01

Pos logit contributions
ivated+0.001
 unatt+0.001
 My+0.001
ternally+0.001
 en+0.001
Neg logit contributions
zag-0.002
ages-0.002
tr-0.001
ained-0.001
ometer-0.001
TokenThe
Token ID464
Feature activation-1.88e-01

Pos logit contributions
 unatt+0.044
ternally+0.041
 en+0.040
 anybody+0.039
ivated+0.039
Neg logit contributions
ages-0.037
After-0.035
zag-0.035
tr-0.031
tails-0.031
Token ghost
Token ID10905
Feature activation+3.80e-02

Pos logit contributions
ivated+0.004
 unatt+0.004
 My+0.004
ternally+0.004
 en+0.004
Neg logit contributions
zag-0.009
ages-0.009
tr-0.009
ained-0.008
ometer-0.008
Token said
Token ID531
Feature activation-5.53e-01

Pos logit contributions
zag+0.002
ages+0.002
tr+0.001
ained+0.001
ometer+0.001
Neg logit contributions
ivated-0.001
 unatt-0.001
 en-0.001
ternally-0.001
 My-0.001
Token,
Token ID11
Feature activation-5.94e-02

Pos logit contributions
 unatt+0.022
ivated+0.022
ternally+0.022
 en+0.021
 My+0.020
Neg logit contributions
ages-0.018
zag-0.018
tr-0.016
ometer-0.016
ccoli-0.015
Token "
Token ID366
Feature activation-1.38e+00

Pos logit contributions
 unatt+0.002
ivated+0.002
ternally+0.002
 en+0.002
 My+0.002
Neg logit contributions
zag-0.003
ages-0.003
tr-0.002
ained-0.002
ometer-0.002
TokenLet
Token ID5756
Feature activation-2.05e+00

Pos logit contributions
 unatt+0.037
 en+0.037
ivated+0.036
 alone+0.034
ternally+0.032
Neg logit contributions
zag-0.059
tr-0.058
ages-0.058
w-0.058
After-0.056
Token me
Token ID502
Feature activation-1.61e-01

Pos logit contributions
 unatt+0.064
ivated+0.064
 en+0.059
folk+0.058
years+0.056
Neg logit contributions
w-0.084
ages-0.081
ine-0.078
tails-0.078
ies-0.077
Token help
Token ID1037
Feature activation-1.60e+00

Pos logit contributions
ivated+0.004
 unatt+0.004
 en+0.004
ternally+0.004
 My+0.004
Neg logit contributions
zag-0.008
ages-0.008
tr-0.007
ained-0.007
ometer-0.007
Token you
Token ID345
Feature activation-1.16e-01

Pos logit contributions
ivated+0.041
 Int+0.040
 en+0.040
 unatt+0.039
ternally+0.036
Neg logit contributions
ages-0.071
tails-0.070
zag-0.069
ies-0.068
ine-0.066
Token un
Token ID555
Feature activation-1.14e-01

Pos logit contributions
ivated+0.003
 unatt+0.003
 en+0.003
ternally+0.003
 My+0.003
Neg logit contributions
zag-0.005
ages-0.005
tr-0.005
ained-0.005
ometer-0.005
Tokenpack
Token ID8002
Feature activation-2.16e-01

Pos logit contributions
 en+0.004
 My+0.004
ivated+0.004
 unatt+0.004
ternally+0.004
Neg logit contributions
zag-0.004
ages-0.004
tr-0.004
ained-0.004
ometer-0.003
Token Will
Token ID2561
Feature activation-3.29e-01

Pos logit contributions
ivated+0.009
 unatt+0.009
ternally+0.009
 en+0.009
 My+0.009
Neg logit contributions
zag-0.015
ages-0.015
tr-0.014
ometer-0.014
ained-0.014
Token you
Token ID345
Feature activation+2.97e-01

Pos logit contributions
ivated+0.009
 unatt+0.009
ternally+0.009
 en+0.008
 My+0.008
Neg logit contributions
ages-0.015
zag-0.015
tr-0.014
ained-0.014
ometer-0.014
Token swing
Token ID9628
Feature activation-4.81e-01

Pos logit contributions
ages+0.012
zag+0.012
tr+0.011
ained+0.011
ometer+0.011
Neg logit contributions
ivated-0.009
 en-0.009
 My-0.009
ternally-0.009
 unatt-0.009
Token me
Token ID502
Feature activation+2.28e-01

Pos logit contributions
ivated+0.015
ternally+0.014
 en+0.014
 unatt+0.014
 My+0.014
Neg logit contributions
zag-0.020
ages-0.020
tr-0.019
ained-0.018
ometer-0.018
Token too
Token ID1165
Feature activation+5.95e-02

Pos logit contributions
ages+0.009
zag+0.009
tr+0.009
ained+0.009
ometer+0.009
Neg logit contributions
ivated-0.007
 unatt-0.007
 en-0.007
 My-0.007
ternally-0.007
Token?"
Token ID1701
Feature activation-1.93e+00

Pos logit contributions
zag+0.002
ages+0.002
tr+0.002
ained+0.002
ometer+0.002
Neg logit contributions
ivated-0.002
 unatt-0.002
ternally-0.002
 My-0.002
 en-0.002
Token
Token ID198
Feature activation-1.74e+00

Pos logit contributions
 unatt+0.081
ternally+0.079
ivated+0.071
chie+0.071
 upper+0.067
Neg logit contributions
ages-0.058
After-0.053
ira-0.052
ometer-0.050
ment-0.049
Token
Token ID198
Feature activation-2.08e+00

Pos logit contributions
 unatt+0.087
ivated+0.085
ternally+0.083
 en+0.082
 happiest+0.080
Neg logit contributions
ages-0.040
zag-0.036
After-0.034
ira-0.034
tails-0.032
TokenThe
Token ID464
Feature activation-4.47e-01

Pos logit contributions
 unatt+0.086
ivated+0.080
 en+0.079
 anybody+0.079
ternally+0.076
Neg logit contributions
ages-0.066
After-0.063
Before-0.054
zag-0.054
tails-0.053
Token man
Token ID582
Feature activation-6.37e-01

Pos logit contributions
ternally+0.013
 unatt+0.013
ivated+0.013
 My+0.012
 I+0.012
Neg logit contributions
ages-0.020
zag-0.019
ometer-0.018
tr-0.018
ira-0.018
Token laughed
Token ID13818
Feature activation-1.73e+00

Pos logit contributions
 unatt+0.018
ivated+0.018
 My+0.017
ternally+0.017
 en+0.016
Neg logit contributions
zag-0.029
ages-0.028
tr-0.027
ine-0.026
ometer-0.025
Token skip
Token ID14267
Feature activation-1.19e+00

Pos logit contributions
 unatt+0.012
ternally+0.012
ivated+0.011
 en+0.011
 My+0.011
Neg logit contributions
zag-0.018
ages-0.017
tr-0.017
tails-0.016
ccoli-0.016
Token.
Token ID13
Feature activation-5.02e-01

Pos logit contributions
ternally+0.048
ivated+0.048
 My+0.046
 unatt+0.045
 en+0.044
Neg logit contributions
ained-0.039
zag-0.038
tr-0.035
ages-0.034
packs-0.033
Token She
Token ID1375
Feature activation-1.18e+00

Pos logit contributions
 unatt+0.018
ivated+0.018
ternally+0.018
 en+0.016
 alone+0.016
Neg logit contributions
zag-0.019
tr-0.019
ages-0.018
ained-0.018
ometer-0.018
Token skipped
Token ID26684
Feature activation+1.08e-01

Pos logit contributions
 unatt+0.050
ternally+0.049
ivated+0.049
 My+0.047
 en+0.045
Neg logit contributions
zag-0.038
ages-0.035
ained-0.034
ine-0.034
tr-0.033
Token everywhere
Token ID8347
Feature activation-7.92e-01

Pos logit contributions
ages+0.005
zag+0.005
tr+0.005
ained+0.005
ometer+0.005
Neg logit contributions
ivated-0.003
 unatt-0.003
 en-0.003
 My-0.003
ternally-0.003
Token she
Token ID673
Feature activation-2.73e+00

Pos logit contributions
ternally+0.031
ivated+0.030
 unatt+0.030
 en+0.029
 My+0.028
Neg logit contributions
zag-0.028
ages-0.025
tr-0.024
ained-0.024
ine-0.022
Token went
Token ID1816
Feature activation-4.16e-01

Pos logit contributions
ternally+0.122
ivated+0.113
 unatt+0.110
igator+0.110
 My+0.108
Neg logit contributions
tr-0.078
zag-0.077
ained-0.075
ine-0.070
packs-0.068
Token,
Token ID11
Feature activation-2.34e+00

Pos logit contributions
ternally+0.016
ivated+0.015
 unatt+0.015
 My+0.015
 en+0.015
Neg logit contributions
zag-0.015
ages-0.014
ained-0.014
tr-0.013
tails-0.012
Token even
Token ID772
Feature activation-3.56e-01

Pos logit contributions
ternally+0.103
lier+0.093
ement+0.092
 My+0.092
liest+0.091
Neg logit contributions
zag-0.073
ained-0.065
ends-0.061
tr-0.059
ages-0.058
Token to
Token ID284
Feature activation-8.03e-01

Pos logit contributions
ternally+0.011
ivated+0.011
 My+0.011
 unatt+0.011
 en+0.011
Neg logit contributions
zag-0.014
ages-0.014
ained-0.014
tr-0.013
olving-0.012
Token the
Token ID262
Feature activation-4.07e-01

Pos logit contributions
ternally+0.026
 My+0.026
 unatt+0.026
ivated+0.025
ard+0.024
Neg logit contributions
zag-0.032
ained-0.030
ages-0.029
ine-0.028
olving-0.028