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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning the repetition of occurrences or events

    oai_token-act-pair · gpt-3.5-turbo

    the word "several" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ideal
    -0.73
     what
    -0.70
     mark
    -0.67
     peak
    -0.67
     dem
    -0.66
     gross
    -0.65
     dwell
    -0.65
     psy
    -0.64
     magic
    -0.64
     anything
    -0.64
    POSITIVE LOGITS
    Several
    2.41
     Several
    2.31
     Numerous
    1.92
    Various
    1.81
     Dozens
    1.71
    Multiple
    1.55
     Various
    1.48
    everal
    1.36
    Lots
    1.36
    Many
    1.35
    Act Density 0.021%

    No Known Activations