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

    Neuronpedia

    INDEX
    Explanations

    examples and instances used in explanations or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whoſe
    -0.60
     Monfieur
    -0.56
     beſt
    -0.54
    fml
    -0.54
    busch
    -0.54
     Pringle
    -0.52
    下载附件
    -0.52
     WHICH
    -0.51
    readdir
    -0.51
    ciun
    -0.51
    POSITIVE LOGITS
     example
    1.59
    example
    1.42
    EXAMPLE
    1.34
    Example
    1.34
     Example
    1.34
     EXAMPLE
    1.30
     ejemplo
    1.30
     المثال
    1.25
     esempio
    1.24
     exemplo
    1.24
    Act Density 0.492%

    No Known Activations