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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bom
    -0.86
    ãģ®éŃĶ
    -0.75
    iversal
    -0.72
    umenthal
    -0.68
    artney
    -0.67
    iership
    -0.66
    mington
    -0.65
    phrine
    -0.64
    otine
    -0.64
     deserve
    -0.63
    POSITIVE LOGITS
     Grain
    0.79
    flation
    0.68
     Marg
    0.68
     Estate
    0.66
     Grac
    0.66
    arts
    0.65
     Noir
    0.64
     Guth
    0.64
    undo
    0.63
    authent
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.