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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĤ¨ãĥ«
    -0.75
    ãĥ¼ãĥĨãĤ£
    -0.74
     Odin
    -0.71
    minecraft
    -0.70
    arded
    -0.68
     Tunis
    -0.66
     Yug
    -0.66
    ãĥ¤
    -0.65
     XVI
    -0.63
    ulic
    -0.63
    POSITIVE LOGITS
    colm
    0.68
    eredith
    0.65
    exit
    0.62
     footnote
    0.62
     Trace
    0.61
    omore
    0.61
    ull
    0.61
    ridor
    0.61
    comment
    0.61
     Sector
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.