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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    >[
    -0.82
    BSD
    -0.75
    DragonMagazine
    -0.75
    repair
    -0.74
    May
    -0.73
    APP
    -0.73
    chin
    -0.70
    Tact
    -0.69
    affected
    -0.68
     undone
    -0.68
    POSITIVE LOGITS
    ordes
    0.76
     arsen
    0.69
     fiat
    0.68
     rulers
    0.67
     abroad
    0.66
     stockp
    0.65
     overse
    0.64
     regards
    0.64
     foreigners
    0.64
     whom
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.