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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ey
    -0.78
    Ĭ
    -0.75
    lov
    -0.73
    »
    -0.72
    esm
    -0.69
    MY
    -0.68
    oak
    -0.66
    oe
    -0.66
    wat
    -0.65
    lees
    -0.65
    POSITIVE LOGITS
     representations
    0.75
     these
    0.75
    conservancy
    0.72
     Turing
    0.70
    abor
    0.65
     goodness
    0.64
    ilater
    0.63
    phabet
    0.63
    alus
    0.62
     interf
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.