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

    Neuronpedia

    INDEX
    Explanations

    mathematical or scientific notation related to concepts and definitions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    :
    -0.57
    gey
    -0.53
    REGION
    -0.52
     ri
    -0.50
     s
    -0.50
     y
    -0.50
    [[
    -0.50
    题
    -0.49
    kete
    -0.49
     cí
    -0.49
    POSITIVE LOGITS
     متعلقه
    0.80
     архивлан
    0.72
     MainAxisSize
    0.71
     himſelf
    0.71
     itſelf
    0.71
     myſelf
    0.69
    Rujuakan
    0.68
     tartalomajánló
    0.68
     pleaſure
    0.68
     فريبيس
    0.68
    Act Density 0.022%

    No Known Activations