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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     quot
    -0.84
     '.
    -0.70
     Jonas
    -0.68
    othal
    -0.68
    incial
    -0.67
    ãĤ¡
    -0.63
    irc
    -0.63
     Hispan
    -0.61
    Columb
    -0.61
     Tup
    -0.60
    POSITIVE LOGITS
    abee
    0.96
    berry
    0.78
    velt
    0.77
    xual
    0.74
    hower
    0.70
    zai
    0.69
    handled
    0.69
    etta
    0.69
    ibur
    0.68
    esian
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.