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

    Neuronpedia

    INDEX
    Explanations

    numbers in the range of thousands

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities in numerical or monetary terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.81
     shell
    -0.70
     bay
    -0.70
     Bok
    -0.67
     omission
    -0.65
    querque
    -0.63
     Directorate
    -0.62
     resemblance
    -0.60
     gate
    -0.59
    worldly
    -0.59
    POSITIVE LOGITS
    000
    1.04
    0000
    0.73
    utsche
    0.73
    00000000
    0.72
    WT
    0.70
    001
    0.68
    DragonMagazine
    0.68
    reference
    0.68
    lde
    0.68
    cies
    0.67
    Act Density 0.204%

    No Known Activations