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

    Neuronpedia

    INDEX
    Explanations

    punctuation and structural elements within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Slf
    -0.15
     Rams
    -0.15
     Palette
    -0.14
    ounded
    -0.14
    /Dk
    -0.14
    ULE
    -0.13
    eor
    -0.13
     ?>'
    -0.13
    stock
    -0.13
    thon
    -0.13
    POSITIVE LOGITS
    oven
    0.16
    byterian
    0.16
    еÑĢж
    0.15
    azon
    0.15
    è¨Ĥ
    0.15
    quin
    0.15
    azen
    0.15
    elop
    0.14
    Ù¬
    0.14
    uster
    0.14
    Act Density 0.082%

    No Known Activations