INDEX
Explanations
punctuation marks at the end of sentences
New Auto-Interp
Negative Logits
}}$}
-0.76
ujednoznacz
-0.71
']
-0.71
QRST
-0.69
}}">
-0.69
"]
-0.68
nicio
-0.67
"])
-0.67
akces
-0.66
]
-0.66
POSITIVE LOGITS
.”
0.64
."
0.63
._
0.61
.*
0.60
.’
0.60
.)
0.59
.?
0.58
.**
0.56
.[
0.56
.•
0.54
Activations Density 0.326%