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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "tobacco"

    oai_token-act-pair · gpt-3.5-turbo

    references to tobacco and its associated health impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ithmetic
    -0.76
     Wynne
    -0.75
     Lazarus
    -0.70
    infeld
    -0.69
     Zup
    -0.68
     Gamergate
    -0.68
     Ake
    -0.68
     Defenders
    -0.68
    variable
    -0.68
    olon
    -0.67
    POSITIVE LOGITS
     cigarettes
    1.11
     smoking
    0.98
     smoke
    0.96
     cessation
    0.93
     cigarette
    0.91
     smoked
    0.85
     cig
    0.84
     tobacco
    0.84
    arette
    0.82
     puff
    0.81
    Act Density 0.012%

    No Known Activations