INDEX
Explanations
instances of dialogue and reporting speech
Attribution or speech act
quotes followed by names
New Auto-Interp
Negative Logits
تانيه
-0.63
ddelweddau
-0.56
Esau
-0.56
ệc
-0.54
extremity
-0.54
Loreto
-0.54
cât
-0.54
itſelf
-0.53
typelib
-0.53
chert
-0.52
POSITIVE LOGITS
])):
0.77
])).
0.77
]))
0.69
]]:
0.67
]));
0.65
]),
0.65
)]);
0.64
})));
0.64
))));
0.63
)]:
0.63
Activations Density 0.032%