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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning specific durations or time periods

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a minimum or threshold requirement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceutical
    -0.64
    FTWARE
    -0.61
     kindly
    -0.61
     Carmen
    -0.60
    Reviewer
    -0.56
     Giul
    -0.55
     Marian
    -0.54
     drums
    -0.54
     disliked
    -0.53
    Berry
    -0.53
    POSITIVE LOGITS
     least
    1.56
    onement
    1.31
    roph
    1.13
    yp
    0.99
    rial
    0.97
    hens
    0.95
    olls
    0.89
    rophic
    0.89
    abase
    0.88
    las
    0.87
    Act Density 0.094%

    No Known Activations