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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pulse
    -0.66
    wash
    -0.64
     Vance
    -0.63
     Colin
    -0.60
    olk
    -0.59
    uke
    -0.59
    perture
    -0.58
    rup
    -0.57
    tip
    -0.57
    espie
    -0.57
    POSITIVE LOGITS
     "$:/
    0.87
     Flavoring
    0.80
    Sov
    0.79
     divid
    0.78
    ¶ħ
    0.77
    è¦ļéĨĴ
    0.75
    ģĸ
    0.73
    ographers
    0.70
    ç«
    0.69
     [&
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.