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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ted
    -0.78
    USS
    -0.76
    ukong
    -0.75
    EVA
    -0.72
    ithub
    -0.71
    Kids
    -0.70
    bley
    -0.67
    Rick
    -0.66
    UID
    -0.65
    Credit
    -0.65
    POSITIVE LOGITS
    tics
    0.67
     alike
    0.67
     è£ıç
    0.67
    mob
    0.65
     extracts
    0.64
     besie
    0.63
    alian
    0.61
     infiltr
    0.61
     Bulgar
    0.60
    ceivable
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.