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

    Neuronpedia

    INDEX
    Explanations

    elements related to coding and syntax structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AW
    -0.61
     FW
    -0.58
     AQ
    -0.57
     MW
    -0.56
     FN
    -0.56
     CW
    -0.55
    Datuak
    -0.54
     שוליים
    -0.53
     OA
    -0.53
    FJ
    -0.52
    POSITIVE LOGITS
    xff
    0.75
    Ợ
    0.59
    orance
    0.58
     yazılı
    0.58
    xFF
    0.57
    Spoljašnje
    0.56
     yelek
    0.56
     katze
    0.56
    xffff
    0.55
    strokeColor
    0.54
    Act Density 0.290%

    No Known Activations