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

    Neuronpedia

    INDEX
    Explanations

    mentions of quantities of people, specifically "hundreds"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hundreds" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igion
    -0.66
     fixation
    -0.63
     Rib
    -0.62
    llor
    -0.62
     symmetry
    -0.61
    atorium
    -0.59
     pessim
    -0.59
    ema
    -0.58
    AMA
    -0.57
     darkness
    -0.57
    POSITIVE LOGITS
    ourcing
    0.95
     thousands
    0.95
     thousand
    0.93
    ourced
    0.87
    undreds
    0.85
    ousands
    0.84
     tens
    0.83
     Thousand
    0.83
     millions
    0.82
     Thousands
    0.80
    Act Density 0.016%

    No Known Activations