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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sequence of events

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "Then."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ties
    -0.69
    ische
    -0.61
    orum
    -0.61
     otherwise
    -0.60
    cv
    -0.60
    making
    -0.60
    ded
    -0.57
    toe
    -0.57
    maker
    -0.56
    ãĥĸ
    -0.56
    POSITIVE LOGITS
    adays
    0.90
    Ļ½
    0.79
     secondly
    0.79
     proceeded
    0.73
     came
    0.72
    noon
    0.71
    ebus
    0.71
     Comes
    0.71
     comes
    0.70
    igslist
    0.67
    Act Density 0.048%

    No Known Activations