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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Oops
    -0.73
    Too
    -0.69
    ãĤ§
    -0.68
    perture
    -0.65
    Correct
    -0.63
    nexpected
    -0.62
    00007
    -0.61
    pants
    -0.61
    astrous
    -0.61
    gency
    -0.61
    POSITIVE LOGITS
     Templ
    0.85
     Franch
    0.76
     Halls
    0.71
     Sod
    0.71
    terness
    0.70
    pieces
    0.69
     Brom
    0.69
    bread
    0.68
    aunts
    0.68
    llor
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.