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

    Neuronpedia

    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of quotation marks and related punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aque
    -0.83
    ilyn
    -0.82
    ouver
    -0.79
    enzie
    -0.78
    ible
    -0.77
    rikes
    -0.77
    atted
    -0.75
    oid
    -0.75
    eele
    -0.72
    AGES
    -0.71
    POSITIVE LOGITS
    cipled
    0.73
    !--
    0.68
    Page
    0.67
     Zoro
    0.65
     indec
    0.62
    mington
    0.60
    oti
    0.59
    ysis
    0.59
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.58
    ````
    0.58
    Act Density 0.022%

    No Known Activations