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

    Neuronpedia

    INDEX
    Explanations

    numbers specifically related to quantities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the words "eight" and "nine" related to age or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lance
    -0.76
    Hub
    -0.74
    ACTION
    -0.70
    hub
    -0.66
     Rica
    -0.65
    berman
    -0.65
    TM
    -0.64
    LAN
    -0.64
    HY
    -0.64
    LAND
    -0.63
    POSITIVE LOGITS
    teenth
    1.45
    eenth
    1.42
    teen
    1.38
    een
    1.35
     hundred
    1.29
    fold
    1.28
     thousand
    1.20
     months
    1.08
    ieth
    1.04
    aciously
    1.01
    Act Density 0.079%

    No Known Activations