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

    Neuronpedia

    INDEX
    Explanations

    academic phrases indicating purpose or aims of studies and articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.82
     שוליים
    -0.82
     يتيمه
    -0.81
    ThroughAttribute
    -0.81
    parsedMessage
    -0.81
     ModelExpression
    -0.78
    出版年
    -0.78
    InputBorder
    -0.77
    Sucesor
    -0.76
    ScopeManager
    -0.75
    POSITIVE LOGITS
     sam
    0.48
    harp
    0.46
    Segue
    0.42
    ここでは
    0.41
     clavier
    0.41
    usty
    0.40
    STATION
    0.40
     condensed
    0.40
    setContentType
    0.40
     پز
    0.40
    Act Density 0.762%

    No Known Activations