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

    Neuronpedia

    INDEX
    Explanations

    references to fires and fire-related incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to fire-related incidents or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atem
    -0.79
     Proud
    -0.76
    berra
    -0.72
     Vide
    -0.72
    xus
    -0.71
    ĸļ
    -0.68
     Virtue
    -0.66
    Tok
    -0.66
    ËĪ
    -0.65
    Birth
    -0.64
    POSITIVE LOGITS
    flies
    1.06
    proof
    1.03
     exting
    0.95
    storm
    0.88
     brig
    0.84
     brigade
    0.83
     retard
    0.82
    onica
    0.81
    fighter
    0.81
    storms
    0.80
    Act Density 0.022%

    No Known Activations