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

    Neuronpedia

    INDEX
    Explanations

    terminology and structures related to question and answer formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fucking
    -0.43
     jugu
    -0.41
    upa
    -0.41
     изо
    -0.40
    mains
    -0.39
     alone
    -0.39
     τὸ
    -0.38
     предлагает
    -0.37
     ${({
    -0.37
     valueOf
    -0.37
    POSITIVE LOGITS
     FAQs
    1.26
     FAQ
    1.25
    FAQ
    1.25
    FAQs
    1.19
     faq
    1.18
     questions
    1.06
     NSCoder
    1.03
     Questions
    1.00
    Faq
    0.99
    Questions
    0.96
    Act Density 0.184%

    No Known Activations