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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ,
    -0.68
     of
    -0.65
    .
    -0.64
     failed
    -0.63
     
    -0.62
     he
    -0.61
     also
    -0.61
     so
    -0.61
     in
    -0.61
     также
    -0.61
    POSITIVE LOGITS
    <bos>
    8.32
     fta
    2.00
     dispen
    1.93
     effe
    1.93
     ftu
    1.91
     !...
    1.88
     squa
    1.85
     fte
    1.85
     guarante
    1.85
     erec
    1.82
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.