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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Transformer
    0.99
     renderer
    0.98
    Carpenter
    0.87
    Grace
    0.87
    Bened
    0.86
    Gateway
    0.86
    Router
    0.85
    Realm
    0.84
    Burning
    0.84
    Institute
    0.83
    POSITIVE LOGITS
     He
    0.98
     f
    0.96
     She
    0.92
     Fin
    0.89
     F
    0.89
     Te
    0.86
     n
    0.85
     T
    0.84
     Law
    0.82
     Ta
    0.81
    Act Density 0.000%

    No Known Activations