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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.84
    )‏
    -0.78
     Verso
    -0.77
    wwwwwwww
    -0.77
     manqué
    -0.73
    aktery
    -0.73
    ціє
    -0.71
     horm
    -0.71
    Grit
    -0.70
    ✨:
    -0.68
    POSITIVE LOGITS
    3
    2.03
    4
    1.37
    5
    1.34
    three
    1.33
     three
    1.32
     Three
    1.31
    Three
    1.26
    THREE
    1.24
     THREE
    1.19
    6
    1.15
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.