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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ateful
    -0.70
    atos
    -0.69
     afford
    -0.67
    osuke
    -0.66
    uron
    -0.63
     coerc
    -0.62
    lux
    -0.61
     tut
    -0.61
    icides
    -0.61
    nington
    -0.61
    POSITIVE LOGITS
     Fn
    0.82
    âĹ¼
    0.80
    INTON
    0.71
    ICAL
    0.71
    earable
    0.70
    dylib
    0.68
    Offline
    0.65
     caveats
    0.65
    EEK
    0.64
    AKING
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.