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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ids
    -0.08
     sø
    -0.07
    ’an
    -0.07
     society
    -0.07
    -pencil
    -0.07
    Jul
    -0.07
     ammonia
    -0.07
     Paul
    -0.07
     BUS
    -0.06
     soo
    -0.06
    POSITIVE LOGITS
    Distinct
    0.07
    enemy
    0.07
    (mid
    0.07
     caracteres
    0.07
    Stories
    0.07
    夙
    0.07
    ⽅
    0.07
     songs
    0.07
    DEF
    0.07
    ريب
    0.06
    Act Density 0.109%

    No Known Activations