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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    wcs
    -0.76
    sign
    -0.74
    osite
    -0.73
    tar
    -0.70
    rogram
    -0.70
    cape
    -0.70
    witch
    -0.69
    beck
    -0.69
    press
    -0.67
    walker
    -0.67
    POSITIVE LOGITS
     dictionary
    0.70
     Aus
    0.69
     din
    0.65
     defamation
    0.64
    merce
    0.63
    awei
    0.63
    iatus
    0.63
     Gadget
    0.62
     Missile
    0.62
     Kard
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.