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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities or proportions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooks
    -0.93
    uits
    -0.76
    ypes
    -0.76
    folk
    -0.76
    actions
    -0.73
    lations
    -0.73
    oof
    -0.71
    uts
    -0.70
    cases
    -0.70
    models
    -0.70
    POSITIVE LOGITS
     hundred
    1.22
     thousand
    1.07
     million
    1.04
     hour
    1.00
     Hundred
    0.96
     crore
    0.93
     billion
    0.91
     month
    0.91
     dimensional
    0.88
     ounce
    0.87
    Act Density 0.117%

    No Known Activations