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

    Neuronpedia

    INDEX
    Explanations

    phrases that imply a correlation or relationship between two variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avigation
    -0.51
    něte
    -0.48
    UrlEncoded
    -0.47
     हू
    -0.46
    スタム
    -0.46
    .}~\
    -0.46
     prosz
    -0.45
    XmlType
    -0.45
    aptation
    -0.44
    レスレット
    -0.44
    POSITIVE LOGITS
    越大
    0.71
    越高
    0.68
    tagHelperRunner
    0.67
    越多
    0.64
    Чем
    0.64
    越是
    0.63
     càng
    0.63
     чем
    0.58
     richer
    0.57
     @"/
    0.57
    Act Density 0.102%

    No Known Activations