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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Once" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "once" indicating a repeated action or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.84
    rug
    -0.76
    ================================================================
    -0.71
    ãĤ®
    -0.70
    orts
    -0.68
    ista
    -0.66
    oco
    -0.65
    urtle
    -0.65
    going
    -0.64
    æ©
    -0.63
    POSITIVE LOGITS
     again
    1.39
     Upon
    1.04
     upon
    1.00
     bitten
    0.97
     mastered
    0.93
     Again
    0.86
     completed
    0.83
    soever
    0.81
     you
    0.79
    again
    0.78
    Act Density 0.043%

    No Known Activations