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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    interstitial
    -0.78
     Flavoring
    -0.77
    monary
    -0.75
    CHAR
    -0.71
     occas
    -0.71
     bunny
    -0.69
    hair
    -0.66
    >>>>
    -0.66
    atism
    -0.65
    Syrian
    -0.64
    POSITIVE LOGITS
     Speedway
    0.73
    imer
    0.68
     brokers
    0.65
     appra
    0.65
    unes
    0.64
     Moreno
    0.64
     Rosenthal
    0.64
     utilities
    0.63
    ero
    0.63
    eson
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.