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

    Neuronpedia

    INDEX
    Explanations

    numerical values and counts related to various entities or components

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    HtmlAttribute
    -0.83
     NSCoder
    -0.73
     Majefty
    -0.69
     bershka
    -0.69
     iſt
    -0.67
    Datuak
    -0.67
     poffe
    -0.67
     Chriftian
    -0.66
    DockStyle
    -0.66
     Cister
    -0.66
    POSITIVE LOGITS
     kasarigan
    0.62
    __["
    0.51
     post
    0.49
     собой
    0.48
     main
    0.48
    ParallelGroup
    0.48
    ARIUS
    0.48
    ρίες
    0.47
    :
    0.45
    hörigen
    0.44
    Act Density 0.078%

    No Known Activations