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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    brance
    -0.88
    ascript
    -0.88
    ebus
    -0.83
    atre
    -0.77
    atha
    -0.74
    ibel
    -0.74
     gestation
    -0.72
    irement
    -0.72
    yre
    -0.70
    bryce
    -0.70
    POSITIVE LOGITS
     Al
    0.78
     Cub
    0.66
     RED
    0.64
     Rampage
    0.64
     Indigo
    0.63
     RL
    0.62
     Quad
    0.61
     Chips
    0.61
     associates
    0.61
     BELOW
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.