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

    Neuronpedia

    INDEX
    Explanations

    references to organizational names, locations, and structural data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.84
    出版年
    -0.74
    ⟬
    -0.74
     surla
    -0.73
     للمعارف
    -0.71
    :");
    -0.70
    expandindo
    -0.69
    Cyfeiriadau
    -0.69
     dieſer
    -0.69
     dieſes
    -0.68
    POSITIVE LOGITS
     |
    1.77
     /
    1.29
    |
    1.27
     ||
    1.06
     //
    1.04
     •
    1.02
     ·
    0.91
    ｜
    0.90
    │
    0.88
     │
    0.85
    Act Density 0.919%

    No Known Activations