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

    Neuronpedia

    INDEX
    Explanations

    variables or labels likely related to data classification or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帖最后由
    -1.18
    providedIn
    -1.02
     HasFactory
    -0.91
    CloseOperation
    -0.84
    awtextra
    -0.82
    principalColumn
    -0.80
    }));
    -0.80
    '},
    -0.79
    DoubleQuotes
    -0.78
    styleType
    -0.78
    POSITIVE LOGITS
    xx
    1.68
     xx
    1.68
    XX
    1.52
     XX
    1.46
     YY
    1.31
    YY
    1.21
     yy
    1.20
    xxx
    1.17
     xxx
    1.13
    XXX
    1.10
    Act Density 0.240%

    No Known Activations