INDEX
Explanations
proper nouns related to individuals
references to specific individuals, particularly those with the surname "Woodward" and related contexts
New Auto-Interp
Negative Logits
utral
-0.78
istant
-0.76
srfAttach
-0.76
amic
-0.73
UT
-0.71
ICAN
-0.70
hof
-0.70
Nun
-0.70
ELY
-0.69
ICA
-0.69
POSITIVE LOGITS
iculty
0.78
ulla
0.78
Parenthood
0.76
rador
0.75
rods
0.75
inx
0.73
undai
0.71
artif
0.70
omething
0.70
gem
0.70
Activations Density 0.028%