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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    etsk
    -0.77
    olicy
    -0.72
    cules
    -0.71
    ebin
    -0.69
     psychiat
    -0.68
    illo
    -0.67
    swer
    -0.67
    dylib
    -0.66
    cohol
    -0.65
    enance
    -0.65
    POSITIVE LOGITS
     parallel
    0.67
     flattering
    0.66
     decade
    0.65
    NYSE
    0.65
     century
    0.65
     camel
    0.64
    ©¶æ¥µ
    0.62
     devastating
    0.62
     lot
    0.62
     narrow
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.