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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     registrations
    -0.66
     Decay
    -0.64
     sticker
    -0.61
    cam
    -0.59
    REL
    -0.59
    mort
    -0.59
     Gohan
    -0.58
     rentals
    -0.58
     teaser
    -0.57
     placeholder
    -0.57
    POSITIVE LOGITS
    loo
    0.76
    abulary
    0.70
    oute
    0.70
     Dame
    0.68
    irs
    0.66
    ift
    0.63
    lain
    0.61
    kefeller
    0.60
    orsi
    0.59
    di
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.