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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "proper" followed by a noun

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "proper."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.73
    ritch
    -0.70
    _>
    -0.67
    âĹı
    -0.66
    hyde
    -0.66
    ---------
    -0.65
    leton
    -0.63
    Graham
    -0.62
    qt
    -0.62
    planes
    -0.62
    POSITIVE LOGITS
    tarian
    1.28
     functioning
    0.93
     noun
    0.90
    tarians
    0.88
     guiActiveUn
    0.85
     etiquette
    0.83
    bred
    0.82
     disclaim
    0.78
     disposal
    0.77
     spelling
    0.77
    Act Density 0.013%

    No Known Activations