INDEX
Explanations
specific mentions related to places or organizations
references to scientific and political frameworks
New Auto-Interp
Negative Logits
Canaver
-0.66
utenberg
-0.64
Falk
-0.61
Solitaire
-0.60
FANTASY
-0.55
CoC
-0.55
Nanto
-0.55
Wem
-0.54
Kamp
-0.53
Aberdeen
-0.52
POSITIVE LOGITS
}.
1.06
.).
0.97
.�
0.97
.''.
0.96
).[
0.95
]."
0.93
].
0.93
`.
0.87
.''
0.87
).
0.86
Activations Density 1.044%