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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    orsi
    -0.70
    rylic
    -0.64
    chini
    -0.64
    amy
    -0.63
    xa
    -0.63
     secretaries
    -0.63
    endix
    -0.62
     fatig
    -0.62
    etus
    -0.62
     Caldwell
    -0.62
    POSITIVE LOGITS
    âĸ¬
    0.73
     downstairs
    0.65
    bas
    0.65
    Accessory
    0.63
     "...
    0.61
    pex
    0.61
     Pledge
    0.61
     prose
    0.61
    ipal
    0.60
     name
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.