Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods, in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Datuak
    -0.94
     дописавши
    -0.90
    脚注の使い方
    -0.87
    IndentedString
    -0.85
    例文帳に追加
    -0.84
     ModelExpression
    -0.80
     mergeFrom
    -0.80
     digress
    -0.78
    __()
    -0.77
    RenderAtEndOf
    -0.77
    POSITIVE LOGITS
     real
    0.50
    gg
    0.45
    shutil
    0.45
     I
    0.45
     both
    0.45
    SizeF
    0.44
    ,
    0.42
     col
    0.42
    ars
    0.42
     section
    0.42
    Act Density 0.002%

    No Known Activations