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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    exclusive
    -0.73
    lege
    -0.67
    leg
    -0.67
    nes
    -0.65
    demand
    -0.64
    runner
    -0.64
    stood
    -0.62
    inges
    -0.59
    lux
    -0.59
    hs
    -0.58
    POSITIVE LOGITS
    ģ«
    0.74
     miscarriage
    0.68
    ãĥĥãĥī
    0.67
    ãĤ¦
    0.67
     DRAG
    0.65
    APS
    0.64
    ÙĴ
    0.63
    Begin
    0.62
    DN
    0.62
     Higgins
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.