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

    Neuronpedia

    INDEX
    Explanations

    mentions of fatal incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to fatal incidents or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.84
    orthy
    -0.79
    arte
    -0.69
    ledge
    -0.68
    arity
    -0.68
    erous
    -0.67
    berman
    -0.67
    ebook
    -0.66
    liga
    -0.65
     Remastered
    -0.65
    POSITIVE LOGITS
    istically
    1.12
    istic
    1.06
     fatal
    1.05
     flaw
    0.90
    ism
    0.87
    ities
    0.86
    ãĥ¥
    0.83
     accidents
    0.83
     overdose
    0.82
     gunshot
    0.82
    Act Density 0.006%

    No Known Activations