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

    Neuronpedia

    INDEX
    Explanations

    numbers denoting a span of time, particularly 'six'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number six and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HY
    -0.72
    Hub
    -0.70
    TM
    -0.68
    ULE
    -0.68
    lance
    -0.68
    LER
    -0.67
    OCK
    -0.67
    LAN
    -0.66
    ller
    -0.66
    ACTION
    -0.65
    POSITIVE LOGITS
    teenth
    1.58
    teen
    1.52
     hundred
    1.34
    fold
    1.23
     thousand
    1.20
    eenth
    1.17
    een
    1.13
    aciously
    1.11
     months
    1.06
    uously
    1.04
    Act Density 0.111%

    No Known Activations