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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    essa
    -0.94
    ppard
    -0.86
    hart
    -0.85
    pillar
    -0.83
    nex
    -0.82
    zens
    -0.82
    heed
    -0.81
    haven
    -0.81
    orio
    -0.81
    oak
    -0.78
    POSITIVE LOGITS
     Purg
    0.75
    NZ
    0.71
     Phar
    0.67
     Cerberus
    0.66
     Psychic
    0.66
    BN
    0.64
     Panic
    0.63
     slang
    0.62
     Conversion
    0.61
     Palin
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.