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

    Neuronpedia

    INDEX
    Explanations

    the negation of statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing negation or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ounters
    -0.73
     Parenthood
    -0.69
    ò
    -0.67
     pione
    -0.66
    ñ
    -0.66
     Compass
    -0.61
    footed
    -0.61
     Gap
    -0.61
     Passage
    -0.61
    emetery
    -0.60
    POSITIVE LOGITS
     kidding
    1.08
     personally
    1.01
     myself
    0.95
     believe
    0.88
     ashamed
    0.87
     sure
    0.86
     hesitate
    0.83
     joking
    0.82
     doubt
    0.82
     necessarily
    0.81
    Act Density 0.124%

    No Known Activations