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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    uria
    -0.74
    arbon
    -0.67
    vier
    -0.66
    patrick
    -0.65
    arest
    -0.65
    amps
    -0.65
    reated
    -0.65
     grate
    -0.64
    intosh
    -0.63
    ateg
    -0.62
    POSITIVE LOGITS
     soar
    0.70
    Flight
    0.68
    Fly
    0.67
     HAL
    0.65
     Robbie
    0.62
    */(
    0.61
     Sik
    0.61
    )=(
    0.61
    LLOW
    0.61
    pload
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.