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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ilater
    -0.78
     Hawth
    -0.77
    regon
    -0.76
     Bowie
    -0.75
    acebook
    -0.74
     Hampton
    -0.73
     Townsend
    -0.73
     Berkshire
    -0.71
     Gould
    -0.70
     Kaufman
    -0.70
    POSITIVE LOGITS
     gravity
    0.75
     crater
    0.70
    tyard
    0.67
     nexus
    0.65
    ansom
    0.64
    fuck
    0.64
     blender
    0.64
     dependency
    0.64
     rift
    0.64
     void
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.