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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "all" or inclusivity across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĽ
    -0.15
     Hoe
    -0.15
    oly
    -0.14
    terdam
    -0.13
    ungal
    -0.13
    urban
    -0.13
    cape
    -0.13
    usic
    -0.13
     Ellis
    -0.13
    inen
    -0.13
    POSITIVE LOGITS
    dorf
    0.17
    elves
    0.15
    ients
    0.14
    otts
    0.14
    rippling
    0.14
    intage
    0.14
     levels
    0.14
    otate
    0.14
    tres
    0.13
     Levels
    0.13
    Act Density 0.185%

    No Known Activations