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

    Neuronpedia

    INDEX
    Explanations

    mentions of lethal or dangerous items, actions, or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to lethal substances or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oard
    -0.83
    ilage
    -0.81
    aliation
    -0.76
    resses
    -0.75
    bed
    -0.72
    æĦ
    -0.72
    roller
    -0.72
    roll
    -0.72
    baby
    -0.71
    acular
    -0.69
    POSITIVE LOGITS
    cious
    0.94
    istics
    0.93
    uania
    0.84
    cius
    0.80
    lihood
    0.75
    SPONSORED
    0.74
     Luthor
    0.74
    istically
    0.73
     injection
    0.72
     ANGEL
    0.71
    Act Density 0.035%

    No Known Activations