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

    Neuronpedia

    INDEX
    Explanations

    mentions of cigarettes

    oai_token-act-pair · gpt-3.5-turbo

    references to cigarettes and their various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hip
    -1.13
    hips
    -1.13
    paces
    -1.03
    ourcing
    -1.00
    ourced
    -0.92
    ettings
    -0.88
    cale
    -0.83
    olving
    -0.80
    peak
    -0.80
    terday
    -0.79
    POSITIVE LOGITS
    holder
    0.95
    holders
    0.88
    brush
    0.83
     Worker
    0.74
     holder
    0.73
     bott
    0.73
    pole
    0.69
     coaster
    0.69
     belt
    0.69
     peel
    0.65
    Act Density 0.023%

    No Known Activations