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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Gork
    -0.66
     Stun
    -0.63
     Cance
    -0.63
     GB
    -0.61
     Peace
    -0.60
     Blaz
    -0.60
    igure
    -0.60
     Clash
    -0.60
     Plans
    -0.59
     Ern
    -0.58
    POSITIVE LOGITS
     pal
    0.95
    ifice
    0.80
    topia
    0.71
    ascript
    0.70
    azor
    0.68
    ships
    0.65
    acea
    0.65
    ILLE
    0.64
    eers
    0.63
    agent
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.