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

    Neuronpedia

    INDEX
    Explanations

    dates or time-referenced events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "has" and its variations indicating possession or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reference
    -0.73
     Kills
    -0.68
     Errors
    -0.66
    evil
    -0.64
     Conversation
    -0.63
    entary
    -0.62
     Would
    -0.61
    ieth
    -0.61
     Explan
    -0.61
     respects
    -0.60
    POSITIVE LOGITS
     begun
    1.36
     emerged
    1.20
     resur
    1.16
     resorted
    1.15
     embarked
    1.13
     become
    1.09
     risen
    1.05
     stepped
    1.05
     quietly
    1.02
     shifted
    1.02
    Act Density 0.272%

    No Known Activations