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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    acity
    -0.76
    apolis
    -0.75
    hesda
    -0.74
    rounded
    -0.70
    complex
    -0.67
    urate
    -0.65
    ertodd
    -0.65
    amount
    -0.64
    oric
    -0.64
    estate
    -0.64
    POSITIVE LOGITS
     tug
    0.70
    ullivan
    0.69
    aroo
    0.67
     sew
    0.66
     gag
    0.63
     Eliot
    0.63
     struggle
    0.62
     pige
    0.62
     jets
    0.61
     newsletters
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.