INDEX
Explanations
proper names and locations
the mention of the name "Lena" in various contexts
New Auto-Interp
Negative Logits
icultural
-0.90
rary
-0.86
direction
-0.85
ername
-0.84
tery
-0.81
matically
-0.79
ty
-0.79
mallow
-0.77
milo
-0.76
rarily
-0.76
POSITIVE LOGITS
issance
1.22
Vista
0.99
Dunham
0.84
emon
0.79
Lans
0.75
emia
0.74
Gomez
0.73
zzo
0.73
Nieto
0.70
uthor
0.69
Activations Density 0.027%