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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    CVE
    -0.78
     deteriorated
    -0.65
     superior
    -0.65
     neglig
    -0.65
     mamm
    -0.63
     sheer
    -0.63
     behold
    -0.62
    oxide
    -0.60
     admitting
    -0.60
    catentry
    -0.60
    POSITIVE LOGITS
    Reader
    0.81
     Tags
    0.75
    fields
    0.70
    OPLE
    0.70
     thous
    0.67
    eral
    0.67
    arez
    0.66
    rer
    0.66
    erman
    0.65
    swer
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.