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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparative standards and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.92
     ModelExpression
    -0.85
    NameInMap
    -0.73
     Lightboxes
    -0.73
     kaarangay
    -0.65
    principalColumn
    -0.62
    titleMargin
    -0.60
    oa̍t
    -0.59
    LookAnd
    -0.59
    IndentedString
    -0.58
    POSITIVE LOGITS
     part
    0.58
    getContentPane
    0.54
    wend
    0.52
    openqa
    0.52
    inflater
    0.52
     portion
    0.50
    endorff
    0.48
     direct
    0.47
    part
    0.47
    حياته
    0.44
    Act Density 0.825%

    No Known Activations