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

    Neuronpedia

    INDEX
    Explanations

    mentions of fatal events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to fatal incidents or deaths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.80
    here
    -0.73
    annis
    -0.73
    arta
    -0.71
    arte
    -0.69
    arity
    -0.69
    atters
    -0.69
    adr
    -0.68
    enda
    -0.68
     Remastered
    -0.67
    POSITIVE LOGITS
    istically
    1.13
    istic
    1.09
    ities
    1.02
     fatal
    0.99
     flaw
    0.98
    ized
    0.97
    ist
    0.95
    ism
    0.91
    izes
    0.89
     overdose
    0.86
    Act Density 0.016%

    No Known Activations