INDEX
Explanations
names or references related to 'Irvin'
references to individuals, particularly names and related nouns, associated with actions or identities
New Auto-Interp
Negative Logits
wcs
-0.83
å§
-0.79
Nanto
-0.66
arnaev
-0.64
ulhu
-0.64
minster
-0.64
ecause
-0.63
merce
-0.62
emporary
-0.62
Tokens
-0.61
POSITIVE LOGITS
XM
0.70
ANCE
0.67
Conan
0.67
Strauss
0.64
ueller
0.62
ña
0.62
ELY
0.61
istant
0.61
heim
0.60
omal
0.60
Activations Density 0.143%