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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms in texts

    oai_token-act-pair · gpt-3.5-turbo

    unusual or non-standard punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogical
    -0.70
    agos
    -0.70
    oresc
    -0.66
    anguages
    -0.66
    ipel
    -0.65
    omore
    -0.65
    assetsadobe
    -0.64
    onyms
    -0.62
    ensical
    -0.62
    engu
    -0.62
    POSITIVE LOGITS
    s
    1.28
    ll
    0.94
    ses
    0.89
    LL
    0.83
    ve
    0.78
    thens
    0.78
    S
    0.77
    ves
    0.76
    si
    0.75
    itates
    0.75
    Act Density 0.113%

    No Known Activations