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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    \\\\\\\\\\\\\\\\
    -0.76
    ocaust
    -0.68
    afia
    -0.66
    glers
    -0.64
     lett
    -0.63
     Weasley
    -0.63
    urry
    -0.62
    arie
    -0.61
     Dahl
    -0.61
     Lup
    -0.61
    POSITIVE LOGITS
     Limit
    0.63
     Replace
    0.63
    enegger
    0.61
     Seg
    0.61
     stride
    0.59
    Const
    0.57
     Signed
    0.56
     Dip
    0.56
     Rule
    0.56
    Match
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.