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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    fits
    -0.62
    otton
    -0.61
    BOOK
    -0.60
     iceberg
    -0.60
    hen
    -0.60
    Done
    -0.59
    icism
    -0.59
    Nar
    -0.59
    åĩ
    -0.59
    Cry
    -0.58
    POSITIVE LOGITS
     veter
    0.77
     Serving
    0.72
     Burton
    0.69
     Means
    0.68
    ewitness
    0.65
     Powder
    0.65
    urry
    0.64
     mosqu
    0.64
     Pur
    0.64
     Rowe
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.