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

    Neuronpedia

    INDEX
    Explanations

    sequences of underscores or blank spaces within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.86
    parsedMessage
    -0.78
    脚注の使い方
    -0.78
    Дереккөздер
    -0.75
    таратура
    -0.74
    tagHelperRunner
    -0.74
     okuyayım
    -0.71
    Autoritní
    -0.70
    rungsseite
    -0.69
     ModelExpression
    -0.68
    POSITIVE LOGITS
     hers
    0.49
    num
    0.48
    usermodel
    0.48
    .
    0.46
     rocz
    0.45
     affatto
    0.44
     Abteilung
    0.44
     cavo
    0.43
    <>("
    0.43
     issuing
    0.43
    Act Density 1.356%

    No Known Activations