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

    Neuronpedia

    INDEX
    Explanations

    words related to tobacco and smoking

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tobacco and cigarettes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    herty
    -0.73
    ithmetic
    -0.73
    assian
    -0.71
     Ake
    -0.70
    alon
    -0.70
     Wynne
    -0.70
    Ü
    -0.70
    ansson
    -0.69
     Yates
    -0.68
    variable
    -0.67
    POSITIVE LOGITS
     cigarettes
    1.34
     smoking
    1.27
     cessation
    1.26
    arette
    1.20
     cig
    1.19
     cigarette
    1.19
     smoker
    1.11
    arettes
    1.10
     smoke
    1.09
     smokers
    1.07
    Act Density 0.059%

    No Known Activations