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

    Neuronpedia

    INDEX
    Explanations

    references to proofs and mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     typelib
    -1.00
     незавершена
    -0.95
    存于互联网档案馆
    -0.90
     itſelf
    -0.87
     saites
    -0.85
    ValueStyle
    -0.83
     whichever
    -0.80
    تقاوى
    -0.78
     Wikimedijinoj
    -0.76
     $_"
    -0.75
    POSITIVE LOGITS
    ...
    0.71
    .../
    0.70
     R
    0.63
    :
    0.62
     E
    0.61
     ...
    0.60
    …
    0.60
    ...@
    0.59
     S
    0.57
     G
    0.57
    Act Density 0.657%

    No Known Activations