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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hazard
    -0.72
    DAY
    -0.68
    sun
    -0.65
    LOAD
    -0.65
    trak
    -0.64
    meter
    -0.61
    hani
    -0.61
    strike
    -0.59
     mismatch
    -0.58
    CHECK
    -0.58
    POSITIVE LOGITS
    apter
    0.75
    umblr
    0.68
    png
    0.66
    DCS
    0.66
    ulp
    0.66
    dfx
    0.65
     Mechdragon
    0.64
    uffs
    0.64
    ():
    0.63
     flora
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.