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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ¬
    -0.71
     Moving
    -0.69
    isky
    -0.67
     HIP
    -0.66
    Ops
    -0.65
     Liter
    -0.65
    =]
    -0.65
     Geo
    -0.64
    Wra
    -0.63
    Running
    -0.62
    POSITIVE LOGITS
    alty
    0.75
    è¦ļéĨĴ
    0.70
    ibles
    0.69
    inker
    0.69
    irs
    0.67
    orge
    0.65
     Santos
    0.64
    oe
    0.63
    oy
    0.63
     dream
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.