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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    gered
    -0.75
    DragonMagazine
    -0.73
    TPPStreamerBot
    -0.72
     Patriarch
    -0.70
    Lens
    -0.70
    Beh
    -0.68
     Adidas
    -0.66
    ¥µ
    -0.66
    »Ĵ
    -0.65
    Magikarp
    -0.64
    POSITIVE LOGITS
    arr
    0.70
    cale
    0.68
    vati
    0.67
    illin
    0.66
    idad
    0.65
    creen
    0.64
     fleets
    0.62
     grit
    0.62
     tribute
    0.62
     endeav
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.