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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    gio
    -0.69
     improv
    -0.65
     Bourbon
    -0.64
    anian
    -0.63
    fm
    -0.62
    amon
    -0.61
     Lerner
    -0.61
     Amend
    -0.59
    endment
    -0.59
     1933
    -0.59
    POSITIVE LOGITS
    ãĤ©
    1.15
    ãĤ§
    0.92
    ãĥĥãĥī
    0.90
    ãĥ¯ãĥ³
    0.88
    Ń·
    0.80
    ãĤ¤
    0.74
    ãĥ³ãĤ¸
    0.74
    åŃ
    0.74
    ãĤ¨ãĥ«
    0.72
    ãĤ£
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.