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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    epad
    -0.82
     Carbuncle
    -0.71
    Scroll
    -0.66
     sqor
    -0.66
    ahu
    -0.64
     compr
    -0.63
    uctions
    -0.63
    iv
    -0.62
    aru
    -0.62
     FANT
    -0.62
    POSITIVE LOGITS
     advis
    0.86
     practition
    0.69
     whistlebl
    0.69
    umn
    0.68
     pse
    0.68
    BALL
    0.67
    intensive
    0.67
     undermin
    0.66
    OHN
    0.65
     adolesc
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.