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

    Neuronpedia

    INDEX
    Explanations

    phrases related to smoking and cigarettes

    oai_token-act-pair · gpt-3.5-turbo

    references to cigarettes and related smoking terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.83
    herty
    -0.77
    */(
    -0.75
    ithmetic
    -0.74
    UFC
    -0.72
    ede
    -0.70
    alon
    -0.69
    icter
    -0.68
    imon
    -0.67
    variable
    -0.67
    POSITIVE LOGITS
    arette
    1.31
    arettes
    1.21
     cigarettes
    1.13
     smoking
    1.09
     smoker
    1.07
     cig
    1.03
     smokers
    1.03
     smoked
    1.03
     cigarette
    1.00
     smoke
    0.97
    Act Density 0.018%

    No Known Activations