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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Camer
    -0.65
     nud
    -0.64
     pes
    -0.64
     DSL
    -0.63
     beginners
    -0.63
     naked
    -0.62
     Convers
    -0.61
    bians
    -0.61
     logger
    -0.60
     newcomer
    -0.59
    POSITIVE LOGITS
    ship
    0.85
    ships
    0.81
    anamo
    0.76
    usters
    0.72
    warts
    0.72
    SHIP
    0.70
    wart
    0.69
    ombat
    0.67
    ategic
    0.65
    isson
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.