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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Rx
    -0.68
     trem
    -0.68
     Lever
    -0.61
    Reloaded
    -0.61
    $$$$
    -0.60
     Giuliani
    -0.60
     Miy
    -0.59
     Crimson
    -0.57
    Brand
    -0.57
     jams
    -0.57
    POSITIVE LOGITS
    atures
    0.86
    tailed
    0.79
    odge
    0.74
    tted
    0.73
    ritten
    0.73
    urbed
    0.73
    cot
    0.71
    cribed
    0.69
    ducers
    0.69
    complex
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.