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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     britannique
    0.48
     conditions
    0.47
     condiciones
    0.46
     brez
    0.45
     smrti
    0.45
     submitted
    0.44
     brittle
    0.44
     known
    0.44
     fucking
    0.44
     slaw
    0.44
    POSITIVE LOGITS
    ג
    0.54
    د
    0.50
    𠃍
    0.49
    g
    0.47
    ле
    0.46
     김
    0.46
    בי
    0.45
     Attitudes
    0.45
    ্া
    0.44
    화
    0.43
    Act Density 0.007%

    No Known Activations