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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ="#
    -0.72
     Mondays
    -0.65
     Week
    -0.63
    #$
    -0.63
     Feast
    -0.63
     Hopkins
    -0.63
     Moonlight
    -0.62
     curl
    -0.61
     rgb
    -0.61
     Oscars
    -0.60
    POSITIVE LOGITS
    senal
    0.96
    pecially
    0.71
    ussen
    0.67
    nance
    0.65
    luster
    0.65
    roup
    0.65
     brill
    0.63
     treacherous
    0.63
    aint
    0.63
    gui
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.