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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    jriwal
    -0.71
    pill
    -0.71
    oglu
    -0.70
    kus
    -0.68
    istries
    -0.68
    agra
    -0.68
    ignty
    -0.67
    merce
    -0.66
    estamp
    -0.66
    hammad
    -0.66
    POSITIVE LOGITS
    oret
    0.70
    aic
    0.68
    RESULTS
    0.67
     Frequency
    0.63
    ULAR
    0.62
     misconception
    0.62
    APS
    0.61
    RH
    0.61
     LAPD
    0.61
    ROR
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.