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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the capability or ability to perform actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NewRow
    -0.65
    titleMargin
    -0.65
    hloromethane
    -0.64
    apunov
    -0.63
    TypedDataSet
    -0.63
    tiftung
    -0.61
    nodejs
    -0.61
     MwSt
    -0.60
    renda
    -0.60
    TagMode
    -0.60
    POSITIVE LOGITS
    toxicity
    0.56
     admit
    0.53
     fleste
    0.53
     flesta
    0.52
    ComponentModel
    0.50
    initState
    0.50
    زال
    0.49
    DotNetBar
    0.49
    améli
    0.48
    
    0.48
    Act Density 0.087%

    No Known Activations