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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ongo
    -0.76
    uba
    -0.68
    ones
    -0.68
    Rs
    -0.68
    obi
    -0.68
    Medic
    -0.66
    Meta
    -0.65
    ogen
    -0.64
    endo
    -0.64
     twitter
    -0.63
    POSITIVE LOGITS
    ĪĴ
    0.91
     Dull
    0.87
    yss
    0.85
    mble
    0.76
    irlwind
    0.72
     Balkans
    0.72
    sembly
    0.71
    allery
    0.71
    ratulations
    0.71
    igree
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.