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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "proper" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "proper" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _>
    -0.73
    è¦ļéĨĴ
    -0.73
    âĹı
    -0.71
    ritch
    -0.67
     Lilly
    -0.66
    hyde
    -0.65
    ula
    -0.64
    qt
    -0.62
    yrs
    -0.62
     Barkley
    -0.61
    POSITIVE LOGITS
    tarian
    1.30
     functioning
    0.94
     noun
    0.90
    bred
    0.87
    tarians
    0.87
    iciary
    0.83
     etiquette
    0.82
     guiActiveUn
    0.81
    nsic
    0.79
    lly
    0.76
    Act Density 0.018%

    No Known Activations