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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oed
    0.72
    𝙡
    0.71
    ﻟ
    0.70
    pmod
    0.69
    roasted
    0.67
     Букмекердик
    0.66
    fotos
    0.64
    ozyg
    0.63
    hamton
    0.63
    <unused2168>
    0.63
    POSITIVE LOGITS
     travelers
    0.73
     those
    0.71
     empathetic
    0.65
     traveler
    0.64
    وى
    0.64
    傳統
    0.64
     Intent
    0.63
     meas
    0.63
    நில
    0.63
     incredible
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.