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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Nich
    -0.73
     Tiff
    -0.72
    ©¶æ
    -0.68
     Drew
    -0.67
     Prelude
    -0.66
     Tar
    -0.64
     Nationwide
    -0.64
     Matt
    -0.62
     1953
    -0.62
     casc
    -0.61
    POSITIVE LOGITS
     intelligence
    1.39
     Intelligence
    1.27
    elligence
    1.06
    intelligence
    1.03
    dinand
    0.81
    iable
    0.79
     dexterity
    0.78
    elligent
    0.77
    urion
    0.77
    ieth
    0.76
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.