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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    arist
    -0.66
    omial
    -0.65
    ric
    -0.65
    erning
    -0.63
    oros
    -0.62
    */(
    -0.62
    OULD
    -0.62
    IDENT
    -0.61
    uca
    -0.61
     Tycoon
    -0.60
    POSITIVE LOGITS
    ILA
    0.77
     Ging
    0.69
    irlf
    0.68
    cade
    0.67
    aeus
    0.64
     Lanka
    0.63
     Shuttle
    0.62
     Kard
    0.60
     Bleach
    0.60
    izoph
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.