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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Oss
    -0.71
     sty
    -0.69
    zon
    -0.68
     srfAttach
    -0.68
    ievers
    -0.63
    fort
    -0.63
    osher
    -0.63
    ebted
    -0.63
    Sund
    -0.63
    ascript
    -0.63
    POSITIVE LOGITS
    uh
    1.01
     general
    0.78
    zh
    0.75
    LIST
    0.75
     GENERAL
    0.74
    General
    0.70
    essee
    0.69
    general
    0.69
     General
    0.68
     Fundamental
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.