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

    Neuronpedia

    INDEX
    Explanations

    numerical data and its significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.56
    makeConstraints
    -0.53
     ModelExpression
    -0.51
     الاطلاع
    -0.48
     @"/
    -0.47
    plotly
    -0.47
    Gweler
    -0.45
    kloped
    -0.44
    rds
    -0.43
    Portale
    -0.42
    POSITIVE LOGITS
     likewise
    0.80
     similarly
    0.76
     ditto
    0.71
     correspondingly
    0.66
     тоже
    0.65
     ebenfalls
    0.65
    Likewise
    0.64
     alſo
    0.63
    Similarly
    0.62
     Similarly
    0.61
    Act Density 0.293%

    No Known Activations