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

    Neuronpedia

    INDEX
    Explanations

    mentions of dangerous or potentially lethal situations or substances

    oai_token-act-pair · gpt-3.5-turbo

    references to lethal situations or substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourced
    -0.88
    erous
    -0.83
    ership
    -0.82
    adra
    -0.81
    arity
    -0.79
    agate
    -0.77
     CLIENT
    -0.76
    acular
    -0.75
     Username
    -0.75
    orers
    -0.74
    POSITIVE LOGITS
     poisonous
    0.91
     poison
    0.91
     wounding
    0.88
     dose
    0.88
     assault
    0.87
     lethal
    0.85
     deadly
    0.81
     weapon
    0.81
    ãĥ¥
    0.81
     overdose
    0.78
    Act Density 0.014%

    No Known Activations