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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     incorpor
    -0.79
    0000000000000000
    -0.72
     discord
    -0.67
    ãĤĮ
    -0.64
    dial
    -0.63
    ¯¯¯¯
    -0.62
    Disclaimer
    -0.61
     Reson
    -0.60
     reconc
    -0.60
    TABLE
    -0.60
    POSITIVE LOGITS
    ults
    0.80
    visors
    0.78
    umes
    0.73
    embed
    0.72
    ams
    0.69
    aff
    0.68
    competitive
    0.67
    ilyn
    0.67
    aching
    0.66
    asts
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.