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

    Neuronpedia

    INDEX
    Explanations

    phrases related to smoking

    oai_token-act-pair · gpt-3.5-turbo

    terms related to smoking and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assian
    -0.88
    UFC
    -0.70
    ousse
    -0.70
     ILCS
    -0.70
    translation
    -0.69
    oteric
    -0.69
    dylib
    -0.67
    ngth
    -0.67
     Vector
    -0.67
    ensional
    -0.66
    POSITIVE LOGITS
     cessation
    1.40
     cigarettes
    1.14
     smoking
    1.06
     smoker
    1.03
     smoked
    1.00
    creen
    0.93
     habits
    0.93
     cigars
    0.92
     cig
    0.91
     smoke
    0.90
    Act Density 0.018%

    No Known Activations