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

    Neuronpedia

    INDEX
    Explanations

    references to built-in features or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udeau
    -0.17
    asper
    -0.17
    enko
    -0.16
     Balt
    -0.15
    lev
    -0.15
    iable
    -0.15
     Bench
    -0.14
    haf
    -0.14
    ubi
    -0.14
    ìĩ
    -0.14
    POSITIVE LOGITS
    IMENT
    0.15
    yre
    0.14
     Hancock
    0.14
    enis
    0.14
    kt
    0.14
    orton
    0.14
    rium
    0.13
     Pond
    0.13
    iry
    0.13
     بÙĨدÛĮ
    0.13
    Act Density 0.012%

    No Known Activations