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

    Neuronpedia

    INDEX
    Explanations

    words related to mortality and lethal events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "death."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Avg
    -0.77
    Available
    -0.75
    æ©Ł
    -0.74
    Cola
    -0.73
    arity
    -0.73
    Export
    -0.72
    ĸļ
    -0.71
    Ĭ±
    -0.70
     Monthly
    -0.69
    Alpha
    -0.69
    POSITIVE LOGITS
    blow
    0.94
    stroke
    0.87
    bed
    0.85
    lier
    0.85
    guards
    0.84
    claw
    0.84
    touch
    0.83
     toll
    0.82
    mur
    0.82
    match
    0.81
    Act Density 0.027%

    No Known Activations