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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific articles and researchers

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     onOptions
    -0.61
    MessageOf
    -0.56
    nats
    -0.55
     cherchés
    -0.52
    AutoScaleMode
    -0.52
    toHaveBeen
    -0.49
     Abo
    -0.49
    ergies
    -0.49
     Infórmanos
    -0.48
    Dès
    -0.48
    POSITIVE LOGITS
    isti
    3.25
    istia
    1.28
    istik
    1.16
    isin
    0.81
    istin
    0.76
    istir
    0.75
    ysty
    0.75
     isti
    0.74
    pete
    0.73
    iste
    0.71
    Act Density 0.001%

    No Known Activations