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

    Neuronpedia

    INDEX
    Explanations

    references to fatal incidents or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "fatal" in various contexts of incidents or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    here
    -0.83
    orthy
    -0.80
     Remastered
    -0.79
    annis
    -0.75
    arte
    -0.74
    erous
    -0.74
    berman
    -0.72
    enda
    -0.70
    hovah
    -0.68
    aday
    -0.68
    POSITIVE LOGITS
    ities
    1.11
    istically
    1.03
     accidents
    1.02
     shootings
    1.02
     gunshot
    1.00
     flaw
    1.00
    istic
    0.99
    ized
    0.97
     overdoses
    0.95
     fatal
    0.94
    Act Density 0.045%

    No Known Activations