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

    Neuronpedia

    INDEX
    Explanations

    proper nouns with the special character 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    references to alarming or serious events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tradable
    -0.89
    SourceFile
    -0.82
    viation
    -0.73
    oca
    -0.72
    rodu
    -0.70
    rette
    -0.70
     thous
    -0.68
    cules
    -0.68
    isphere
    -0.68
    proc
    -0.67
    POSITIVE LOGITS
    [/
    0.67
    Adds
    0.66
    Wilson
    0.62
    Bay
    0.62
    SPONSORED
    0.61
     deadliest
    0.61
    cutting
    0.60
     Kaine
    0.57
    CDC
    0.57
    Weak
    0.57
    Act Density 0.053%

    No Known Activations