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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers and their relation to rankings or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    495
    -0.16
    ÑģпÑĸлÑĮ
    -0.15
    út
    -0.15
    rio
    -0.15
    aub
    -0.15
    emen
    -0.14
    quit
    -0.14
    ens
    -0.14
    nice
    -0.13
     ÑĥÑģ
    -0.13
    POSITIVE LOGITS
    sembly
    0.17
    urette
    0.16
    eka
    0.14
    ï¸
    0.14
     Latter
    0.14
    )./
    0.14
     sca
    0.14
    ÌĨ
    0.13
     –↵↵
    0.13
    eko
    0.13
    Act Density 0.061%

    No Known Activations