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

    Neuronpedia

    INDEX
    Explanations

    references to medical or health-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſind
    -1.06
     ་་
    -1.02
     itſelf
    -0.99
    .",
    -0.94
     שוליים
    -0.89
     iſt
    -0.89
    </caption>
    -0.87
     fubject
    -0.86
     uſ
    -0.86
     $_"
    -0.85
    POSITIVE LOGITS
     or
    0.67
     too
    0.65
     &
    0.64
     I
    0.61
     тоже
    0.61
     stuff
    0.59
     *
    0.59
    ↵
    0.59
     something
    0.58
    ic
    0.57
    Act Density 1.176%

    No Known Activations