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

    Neuronpedia

    INDEX
    Explanations

    references to downloadable or printable materials and related functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dys
    -0.14
    rane
    -0.14
    leck
    -0.13
    oland
    -0.13
    etail
    -0.13
     Gent
    -0.13
     geg
    -0.13
     ZemÄĽ
    -0.13
    nce
    -0.13
    icie
    -0.13
    POSITIVE LOGITS
    essenger
    0.17
    ubbo
    0.15
    889
    0.15
    itar
    0.15
    رÙģت
    0.15
    avern
    0.14
    zÄħ
    0.14
    inen
    0.14
    unal
    0.14
    orm
    0.14
    Act Density 0.269%

    No Known Activations