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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.85
     Templar
    -0.76
     Eli
    -0.75
     Investigative
    -0.75
     Jehovah
    -0.73
     Hatch
    -0.72
     Archdemon
    -0.71
     Kushner
    -0.69
     Phase
    -0.69
     Templ
    -0.67
    POSITIVE LOGITS
    ividual
    0.84
    blank
    0.73
    urg
    0.73
    ography
    0.72
    helle
    0.72
    uggest
    0.72
     enthusi
    0.72
    driver
    0.70
    ding
    0.70
    sung
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.