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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sooner
    -0.74
     Esports
    -0.74
     steroids
    -0.72
     Fin
    -0.69
     Vale
    -0.68
     Owl
    -0.67
     Society
    -0.67
    }}}
    -0.66
     Athletics
    -0.64
    !/
    -0.64
    POSITIVE LOGITS
    birth
    0.72
     mosqu
    0.70
    gling
    0.70
    worker
    0.69
    dn
    0.69
    Muslim
    0.69
    typ
    0.68
    odd
    0.67
    emin
    0.65
    bryce
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.