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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers and numerical references within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eller
    -0.15
    ucker
    -0.14
    ã
    -0.14
    pike
    -0.14
    iedad
    -0.14
    ded
    -0.14
     Rico
    -0.14
     Coat
    -0.14
    inished
    -0.14
    azon
    -0.13
    POSITIVE LOGITS
    oran
    0.18
    rane
    0.16
    achu
    0.16
    oure
    0.15
    Ñĥл
    0.14
    ormsg
    0.14
    ÙĬ
    0.14
    istrovstvÃŃ
    0.14
     ninh
    0.14
    uv
    0.14
    Act Density 0.149%

    No Known Activations