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

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in sentences

    oai_token-act-pair · gpt-3.5-turbo

    sentences or clauses that conclude thoughts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     constantly
    -0.72
     everyday
    -0.70
     bully
    -0.69
     jugg
    -0.66
     utter
    -0.65
     extinct
    -0.64
    roph
    -0.63
     kid
    -0.62
     royalty
    -0.62
     loving
    -0.61
    POSITIVE LOGITS
     Asked
    1.06
    Asked
    0.96
     Previously
    0.95
     Sources
    0.94
     Officials
    0.88
     Among
    0.88
     Presumably
    0.88
     He
    0.86
     Meanwhile
    0.86
     Specifically
    0.85
    Act Density 0.413%

    No Known Activations