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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to smoking and tobacco use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugi
    -0.16
    loat
    -0.15
    yme
    -0.15
    ãĥ¼ãĥ
    -0.15
     è¾
    -0.15
     Dexter
    -0.15
    andex
    -0.15
    emoc
    -0.15
    resar
    -0.14
    öz
    -0.14
    POSITIVE LOGITS
     tobacco
    0.50
     cigarettes
    0.47
     smoking
    0.45
     nicotine
    0.44
     cigarette
    0.44
     Smoking
    0.42
     Tobacco
    0.42
     smokers
    0.40
     smoker
    0.38
     smoke
    0.35
    Act Density 0.058%

    No Known Activations