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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.78
    emia
    -0.73
     Tolkien
    -0.69
    igslist
    -0.69
    ritis
    -0.69
    agra
    -0.68
    arma
    -0.67
    ð
    -0.66
    ebook
    -0.66
    dayName
    -0.65
    POSITIVE LOGITS
    ESS
    0.65
    bell
    0.65
     WATCHED
    0.63
    ELF
    0.63
    incible
    0.63
     ty
    0.62
    IAL
    0.61
    dash
    0.61
     -------
    0.60
     lied
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.