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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     “
    1.54
     (“
    1.32
    .“
    1.30
     ‘
    1.27
    .’
    1.21
    ’.
    1.16
     “.
    1.15
     J
    1.13
     「
    1.12
     ”
    1.10
    POSITIVE LOGITS
     feedwater
    0.99
     tcpHeader
    0.87
     imparting
    0.85
     ascertaining
    0.82
     uncovering
    0.81
     ಏಕೆಂದರೆ
    0.81
     overturning
    0.80
     combating
    0.79
     oceanic
    0.77
     ateliers
    0.77
    Act Density 0.000%

    No Known Activations