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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "fact" accompanied by statements or clauses containing more specific information

    oai_token-act-pair · gpt-3.5-turbo

    statements presenting factual information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TPPStreamerBot
    -0.71
    interstitial
    -0.70
    XY
    -0.68
    mens
    -0.67
     throat
    -0.63
     recip
    -0.59
    CI
    -0.57
    usable
    -0.56
    åĨ
    -0.55
    kie
    -0.55
    POSITIVE LOGITS
    ually
    0.98
    uality
    0.91
    ional
    0.85
    orial
    0.83
    oids
    0.82
    oid
    0.81
    itious
    0.77
    uated
    0.72
    ual
    0.71
    uring
    0.71
    Act Density 0.037%

    No Known Activations