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

    Neuronpedia

    INDEX
    Explanations

    references to support or claim validation in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AnchorTagHelper
    -0.66
    uxxxx
    -0.50
     betweenstory
    -0.48
     noDo
    -0.44
    nezeu
    -0.43
     arşivlendi
    -0.41
     disambiguazione
    -0.40
    RTLD
    -0.40
    новид
    -0.40
    ukone
    -0.40
    POSITIVE LOGITS
     argument
    1.48
     assertion
    1.41
     conclusion
    1.41
     hypothesis
    1.31
     claim
    1.31
     contention
    1.28
     view
    1.23
     idea
    1.22
     assumption
    1.21
     notion
    1.20
    Act Density 1.308%

    No Known Activations