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

    Neuronpedia

    INDEX
    Explanations

    words related to quantifiable measurements or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bat
    -0.19
     Spicer
    -0.17
    assi
    -0.17
     Rug
    -0.16
    asil
    -0.15
     rug
    -0.15
    azzi
    -0.15
    znám
    -0.15
    رب
    -0.15
    éc
    -0.14
    POSITIVE LOGITS
    esser
    0.20
     respectively
    0.19
     respective
    0.18
    arella
    0.15
    enstein
    0.15
    WithContext
    0.15
    ÐķС
    0.15
     ÑģооÑĤвеÑĤ
    0.14
    itted
    0.14
    ẽ
    0.14
    Act Density 0.055%

    No Known Activations