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

    Neuronpedia

    INDEX
    Explanations

    words related to cigarettes and smoking

    oai_token-act-pair · gpt-3.5-turbo

    references to cigarettes and smoking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ede
    -0.76
    Ü
    -0.71
    herty
    -0.69
     MacDonald
    -0.68
    Jean
    -0.68
    ansson
    -0.66
     Ake
    -0.66
     mathematic
    -0.65
    pmwiki
    -0.65
    assian
    -0.62
    POSITIVE LOGITS
    arette
    1.36
    arettes
    1.25
     cigarettes
    1.14
     cig
    1.10
     smoked
    1.09
     smoking
    1.09
     smoker
    1.07
     cigarette
    1.07
     smokers
    1.05
     smoke
    1.03
    Act Density 0.040%

    No Known Activations