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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĥ³ãĤ¸
    -0.77
    Topic
    -0.72
     intercept
    -0.68
    äºĶ
    -0.66
     demons
    -0.66
     guarded
    -0.65
     hypoc
    -0.65
     volatile
    -0.64
    ãĤŃ
    -0.63
     Barron
    -0.63
    POSITIVE LOGITS
    ploma
    0.83
    jri
    0.81
    bent
    0.79
    uden
    0.78
    ratulations
    0.75
    lege
    0.74
    dri
    0.74
    aye
    0.73
    qual
    0.73
    tf
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.