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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    inson
    -0.70
     Compass
    -0.67
     Electro
    -0.65
    Subject
    -0.64
     Magnet
    -0.64
     Shed
    -0.64
    utherford
    -0.63
    iolet
    -0.61
     Wein
    -0.61
    Thor
    -0.60
    POSITIVE LOGITS
    orius
    0.79
     kay
    0.68
    ī
    0.66
    ĸļ
    0.65
     Voy
    0.64
    hai
    0.64
     panties
    0.63
     Nare
    0.63
    lude
    0.62
     Kamp
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.