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

    Neuronpedia

    INDEX
    Explanations

    words related to duplication or errors in files or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лава
    -0.15
    verty
    -0.15
    ago
    -0.15
    iesz
    -0.15
    aggio
    -0.14
    asan
    -0.14
    antanamo
    -0.14
    íĭ´
    -0.14
    iyan
    -0.14
    feit
    -0.14
    POSITIVE LOGITS
    ded
    0.30
     Ded
    0.26
    icated
    0.25
     ded
    0.23
    DED
    0.21
    icates
    0.21
    ding
    0.19
    ication
    0.19
    alus
    0.19
    uced
    0.19
    Act Density 0.007%

    No Known Activations