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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Ta
    -0.70
     porous
    -0.68
     Hatch
    -0.68
     Bake
    -0.67
     parting
    -0.66
     liking
    -0.65
     rapport
    -0.63
     Bang
    -0.63
     Spect
    -0.63
     Passage
    -0.62
    POSITIVE LOGITS
    bis
    0.86
    ibrary
    0.83
    APD
    0.82
    afort
    0.77
    glers
    0.75
    UV
    0.74
    calling
    0.74
    MIC
    0.73
    Dex
    0.72
    wd
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.