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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    as
    1.13
     incurs
    0.95
    turbulence
    0.94
    坂
    0.93
    챱
    0.91
     impeding
    0.91
    赳
    0.91
    ॓
    0.91
    absorption
    0.88
    asen
    0.87
    POSITIVE LOGITS
    1.18
    gn
    0.96
    えて
    0.95
    rosso
    0.90
    瞩
    0.90
     eloku
    0.89
     chameleon
    0.89
     kc
    0.87
     priorities
    0.85
    část
    0.84
    Act Density 0.000%

    No Known Activations