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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Ster
    -0.81
     Reincarn
    -0.73
    tons
    -0.72
    uploads
    -0.71
     Mash
    -0.66
     Tad
    -0.66
     Schr
    -0.65
     Abrams
    -0.65
     Lean
    -0.65
    ACTION
    -0.62
    POSITIVE LOGITS
    ":["
    0.81
    iov
    0.75
    phis
    0.71
    jah
    0.71
    romy
    0.69
     gou
    0.67
    atana
    0.67
    ioch
    0.66
    umbn
    0.65
    gage
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.