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

    Neuronpedia

    INDEX
    Explanations

    multiple instances of numeric data and their various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ../../../
    -0.20
    amoto
    -0.19
    elerik
    -0.18
    ler
    -0.18
    akedirs
    -0.16
    ideographic
    -0.15
    à¸Ń
    -0.15
    User
    -0.15
    à¸Ļ
    -0.15
    ar
    -0.14
    POSITIVE LOGITS
    ties
    0.17
    ighton
    0.16
    auga
    0.15
    ecies
    0.15
    ebra
    0.15
    à¥įण
    0.15
    imdi
    0.14
     ---------------------------------------------------------------------------↵
    0.14
    eydi
    0.14
    ÌĨ
    0.14
    Act Density 0.230%

    No Known Activations