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

    Neuronpedia

    INDEX
    Explanations

    keywords related to cigarettes and smoking

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cigarette and tobacco products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiz
    -0.72
    herty
    -0.72
    alon
    -0.70
    ithmetic
    -0.68
    ansson
    -0.67
    peak
    -0.64
    raised
    -0.64
    alan
    -0.64
     guiActiveUnfocused
    -0.63
    hem
    -0.63
    POSITIVE LOGITS
     cigarettes
    1.41
     cessation
    1.40
     smoking
    1.39
    arette
    1.35
     smoker
    1.30
     cig
    1.26
    arettes
    1.24
     cigarette
    1.24
     smokers
    1.23
     smoked
    1.21
    Act Density 0.052%

    No Known Activations