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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    APTER
    -0.65
    alach
    -0.64
    edly
    -0.64
    zzo
    -0.64
     yawn
    -0.64
    ATER
    -0.63
    zsche
    -0.62
    èĢħ
    -0.62
    @@@@
    -0.61
    hyde
    -0.61
    POSITIVE LOGITS
    percent
    0.66
     certs
    0.65
     wards
    0.64
     shields
    0.63
     profile
    0.61
    wcsstore
    0.61
     harmless
    0.60
     neighbourhoods
    0.59
    imeters
    0.59
     kins
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.