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

    Neuronpedia

    INDEX
    Explanations

    mentions of quitting something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quit" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Catalog
    -0.76
    inen
    -0.69
    HOU
    -0.67
    arov
    -0.66
    arthy
    -0.65
    acqu
    -0.64
     ancest
    -0.64
    Herm
    -0.63
    è¯
    -0.63
     intric
    -0.63
    POSITIVE LOGITS
     smoking
    1.08
    ters
    1.00
     Quit
    0.92
     quitting
    0.89
     Smoking
    0.88
    ting
    0.88
     quit
    0.74
    smoking
    0.68
     eating
    0.67
     breathing
    0.67
    Act Density 0.013%

    No Known Activations