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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    mselves
    0.79
     söyledi
    0.75
    sing
    0.74
    noticed
    0.74
     Huffington
    0.74
     Minkowski
    0.73
    explain
    0.73
    Slate
    0.72
    TouchableOpacity
    0.71
    ".$
    0.71
    POSITIVE LOGITS
    仅
    0.94
     endet
    0.81
     främ
    0.80
     seulement
    0.77
     precluded
    0.77
     endast
    0.77
     yalnızca
    0.76
    केवल
    0.75
     compren
    0.75
     فقط
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.