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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Calcula
    1.12
     circumst
    1.05
    𝖒
    1.05
     Busca
    1.03
    ো
    1.02
    𝖎
    1.01
    ➢
    0.99
    ⎜
    0.99
     insects
    0.99
     Перейти
    0.98
    POSITIVE LOGITS
    adj
    0.87
    ade
    0.84
    bi
    0.82
    PA
    0.79
     setempat
    0.78
    মূলক
    0.78
    epoch
    0.77
    디오
    0.77
    aggressive
    0.77
    hate
    0.76
    Act Density 0.001%

    No Known Activations