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

    Neuronpedia

    INDEX
    Explanations

    significant descriptors of books or publications, particularly in terms of their impact and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     heavenly
    -0.14
    .SizeType
    -0.14
    cheon
    -0.13
    dux
    -0.13
     cush
    -0.12
    AVIS
    -0.12
    äd
    -0.12
    azy
    -0.12
     Heavenly
    -0.12
    braco
    -0.12
    POSITIVE LOGITS
     luc
    0.29
     readable
    0.26
     er
    0.26
     cog
    0.22
     learned
    0.21
     penetrating
    0.21
     trench
    0.21
     mag
    0.21
     exhaust
    0.20
     scholarly
    0.20
    Act Density 0.073%

    No Known Activations