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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     endors
    -0.68
     weeds
    -0.65
     morphed
    -0.65
     lined
    -0.61
     coercive
    -0.60
     recess
    -0.59
     Judd
    -0.59
     overturned
    -0.59
    noxious
    -0.58
     benches
    -0.58
    POSITIVE LOGITS
    hov
    0.88
    ription
    0.72
    zb
    0.71
    erest
    0.71
    igan
    0.70
    igans
    0.69
     Byte
    0.67
    colour
    0.67
     Britann
    0.67
    imilation
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.