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

    Neuronpedia

    INDEX
    Explanations

    mentions of dates or numerical values within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.80
     ModelExpression
    -0.76
     betweenstory
    -0.75
     يتيمه
    -0.73
     nakalista
    -0.73
    fromnode
    -0.72
    )');
    -0.70
    getitem
    -0.69
     Chriftian
    -0.68
     Saltar
    -0.68
    POSITIVE LOGITS
    ScopeManager
    0.80
    enderror
    0.63
    ternos
    0.51
     is
    0.45
     etc
    0.45
     to
    0.43
    kabel
    0.42
     وسلم
    0.42
    onto
    0.42
    waffe
    0.42
    Act Density 0.531%

    No Known Activations