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

    Neuronpedia

    INDEX
    Explanations

    verbs related to quitting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quit" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inen
    -0.79
    Catalog
    -0.76
    arov
    -0.69
    ANS
    -0.69
    Herm
    -0.67
    Grant
    -0.62
     ancest
    -0.62
    arthy
    -0.62
    ---------------
    -0.62
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.60
    POSITIVE LOGITS
     smoking
    1.13
    ters
    0.99
     Smoking
    0.92
    ting
    0.92
     Quit
    0.87
     quitting
    0.82
     whining
    0.76
    smoking
    0.75
     eating
    0.69
    terness
    0.67
    Act Density 0.009%

    No Known Activations