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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oned
    -0.74
    anian
    -0.72
    aying
    -0.71
    encing
    -0.67
    oning
    -0.64
    ogue
    -0.64
    oulos
    -0.64
    ibel
    -0.63
    inian
    -0.63
    aed
    -0.63
    POSITIVE LOGITS
     discrep
    0.86
     nutrit
    0.70
     conduc
    0.70
    Corn
    0.69
    Ear
    0.68
    FactoryReloaded
    0.66
    Mist
    0.64
    CVE
    0.63
     condesc
    0.63
    atl
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.