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

    Neuronpedia

    INDEX
    Explanations

    abbreviations with punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.61
    uble
    -0.60
     [|
    -0.60
    tenance
    -0.59
    collar
    -0.59
    JUST
    -0.57
    ITED
    -0.57
    catentry
    -0.57
    NetMessage
    -0.57
    forcement
    -0.54
    POSITIVE LOGITS
    a
    1.86
    ahs
    1.06
    Ãł
    0.98
    ah
    0.96
    aa
    0.95
    aan
    0.95
    ae
    0.88
    aic
    0.85
    aq
    0.84
    as
    0.82
    Act Density 0.204%

    No Known Activations