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

    Neuronpedia

    INDEX
    Explanations

    references to speeches and related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.45
     betweenstory
    -0.41
     downvoted
    -0.41
    :✨
    -0.39
     inoxydable
    -0.39
    AndEndTag
    -0.39
    copg
    -0.38
     plufieurs
    -0.38
    asteroido
    -0.38
    InputBorder
    -0.37
    POSITIVE LOGITS
     offering
    0.86
     Offering
    0.84
     OFFER
    0.82
     brought
    0.80
    Offering
    0.79
    Offer
    0.77
     offers
    0.75
     offered
    0.75
     brings
    0.74
     Offerings
    0.74
    Act Density 0.198%

    No Known Activations