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

    Neuronpedia

    INDEX
    Explanations

    statistical data involving counts and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĸĻ
    -0.17
    ung
    -0.15
     Hakk
    -0.14
    ght
    -0.14
     Sad
    -0.14
     sad
    -0.14
    ½æķ°
    -0.14
    _ASSUME
    -0.13
    IVEN
    -0.13
    EFI
    -0.13
    POSITIVE LOGITS
     thousands
    0.26
     hundreds
    0.23
     millions
    0.22
     Thousands
    0.20
     billions
    0.18
     Hundreds
    0.18
    Thousands
    0.17
     Millions
    0.17
    ugas
    0.16
    undreds
    0.16
    Act Density 0.437%

    No Known Activations