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

    Neuronpedia

    INDEX
    Explanations

    the word "resist" and variations of it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resist" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.76
    weekly
    -0.71
    Dub
    -0.70
     Bohem
    -0.70
     Roads
    -0.70
    ammy
    -0.69
     Referred
    -0.68
    Day
    -0.67
    day
    -0.67
    WHERE
    -0.65
    POSITIVE LOGITS
     resist
    1.31
     resistance
    1.05
     resisted
    1.02
    resist
    0.99
     Resist
    0.99
    ances
    0.98
     resists
    0.97
     resisting
    0.94
    ency
    0.93
    ences
    0.91
    Act Density 0.005%

    No Known Activations