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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or dismissal

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "at all."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.70
    ptions
    -0.67
    pez
    -0.65
    izo
    -0.61
    Magn
    -0.59
     Converted
    -0.59
    éĹĺ
    -0.59
    ascript
    -0.59
     Ahead
    -0.59
    liness
    -0.58
    POSITIVE LOGITS
     least
    1.01
    yp
    0.90
     anytime
    0.89
     anymore
    0.89
    onement
    0.88
     slightest
    0.85
     any
    0.84
     present
    0.76
     all
    0.76
    ogether
    0.76
    Act Density 0.096%

    No Known Activations