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

    Neuronpedia

    INDEX
    Explanations

    mentions of substance abuse

    oai_token-act-pair · gpt-3.5-turbo

    references to substance abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blazers
    -0.80
     Slate
    -0.75
    rium
    -0.69
    DIR
    -0.68
    aldi
    -0.67
     Pratt
    -0.65
    doms
    -0.64
    ersen
    -0.64
    OY
    -0.64
    estamp
    -0.64
    POSITIVE LOGITS
    abuse
    1.06
     abusers
    0.96
     Abuse
    0.95
     abuser
    0.90
     abuse
    0.88
    fulness
    0.88
     substances
    0.88
    amphetamine
    0.84
    itute
    0.83
    uality
    0.82
    Act Density 0.024%

    No Known Activations