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

    Neuronpedia

    INDEX
    Explanations

    phrases related to explosives or dangerous situations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of explosive devices or descriptions of explosive situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cedented
    -0.88
    aird
    -0.86
    SEA
    -0.78
    krit
    -0.77
    pai
    -0.77
    wright
    -0.77
    heit
    -0.76
    atche
    -0.75
    alian
    -0.75
    ournal
    -0.74
    POSITIVE LOGITS
     explosive
    1.09
     decomp
    0.89
     eru
    0.88
     incendiary
    0.85
     bursts
    0.78
     darts
    0.78
    onite
    0.77
     deton
    0.75
     explodes
    0.74
     flares
    0.73
    Act Density 0.011%

    No Known Activations