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

    Neuronpedia

    INDEX
    Explanations

    numerical counts or quantities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "count" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashi
    -0.84
    rugged
    -0.73
    eous
    -0.61
     flares
    -0.61
    hat
    -0.61
    krit
    -0.61
    internet
    -0.58
     Petersen
    -0.58
    ahi
    -0.58
     Lumpur
    -0.58
    POSITIVE LOGITS
     count
    4.18
     counts
    2.77
    count
    2.40
     Count
    2.35
     counted
    2.30
     counting
    2.07
    Count
    2.02
     tally
    1.70
    OUNT
    1.18
     countdown
    1.13
    Act Density 0.005%

    No Known Activations