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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    venge
    -0.73
    UU
    -0.70
    Ak
    -0.70
    士
    -0.67
     Ys
    -0.67
     Wad
    -0.67
    DCS
    -0.67
    ²¾
    -0.66
    vp
    -0.66
    ctive
    -0.66
    POSITIVE LOGITS
    ucky
    0.83
    agine
    0.80
    aney
    0.75
     fixme
    0.74
    itton
    0.73
    finger
    0.70
    meier
    0.67
     unravel
    0.65
    ikes
    0.65
    olean
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.