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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Pearce
    -0.72
    zinski
    -0.69
     McCoy
    -0.67
    254
    -0.66
    oric
    -0.66
     Imper
    -0.64
    Apr
    -0.63
    ysics
    -0.62
    Ol
    -0.61
    iak
    -0.60
    POSITIVE LOGITS
    ÅŁ
    0.80
    soever
    0.80
    cill
    0.73
    nect
    0.71
    ulhu
    0.70
    itone
    0.66
    cled
    0.66
    lehem
    0.66
    gdala
    0.66
    ñ
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.