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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    to
    1.63
    h
    1.37
    꿈
    1.22
     pulgadas
    1.20
    ts
    1.18
    k
    1.15
    tl
    1.13
    trans
    1.11
     successo
    1.10
     annat
    1.08
    POSITIVE LOGITS
     reversible
    1.31
     riveting
    1.28
     dumb
    1.24
     Falcons
    1.16
     scathing
    1.12
     thwarted
    1.10
    Ꮼ
    1.07
     portability
    1.06
    塑料
    1.06
     tackles
    1.06
    Act Density 0.000%

    No Known Activations