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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or symbols indicating relationships and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     illustrationer
    -0.56
    tagHelper
    -0.55
     שוליים
    -0.54
     Publikum
    -0.52
    Erreferentziak
    -0.51
     seragam
    -0.50
     препратки
    -0.50
     المعيارى
    -0.48
     felices
    -0.48
     dalamnya
    -0.48
    POSITIVE LOGITS
    >−</
    0.73
    −
    0.73
    }-\
    0.72
     -=
    0.69
    )}-\
    0.68
    }}-\
    0.68
     −
    0.68
     (−
    0.67
     -\
    0.66
    setminus
    0.64
    Act Density 0.944%

    No Known Activations