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

    Neuronpedia

    INDEX
    Explanations

    the word "yet" before a subsequent action or occurrence

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases indicating recurrence or accumulation of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.81
    rities
    -0.78
    urated
    -0.72
    mop
    -0.71
    ogens
    -0.66
    uration
    -0.66
    otaur
    -0.63
    tein
    -0.62
     powd
    -0.61
    ured
    -0.60
    POSITIVE LOGITS
     again
    0.87
    another
    0.79
     unborn
    0.78
     another
    0.76
    OTHER
    0.73
    Another
    0.72
    NESS
    0.70
     Another
    0.70
    unin
    0.70
     Again
    0.69
    Act Density 0.026%

    No Known Activations