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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Verge
    -0.83
    ORPG
    -0.68
     Bowen
    -0.64
    Palest
    -0.62
    ones
    -0.60
     pod
    -0.59
     lum
    -0.59
     Airways
    -0.58
     thrott
    -0.57
    anges
    -0.56
    POSITIVE LOGITS
    arcity
    0.77
    hra
    0.72
    atility
    0.72
    agame
    0.71
     insure
    0.69
    rehensive
    0.68
    itness
    0.67
    emort
    0.66
    eree
    0.65
    paio
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.