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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe attributes of items or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bes
    -0.17
     tá»Ń
    -0.15
     Bes
    -0.15
    ortal
    -0.14
     Basics
    -0.13
    ust
    -0.13
    anas
    -0.13
    人çļĦ
    -0.13
    un
    -0.13
    loat
    -0.13
    POSITIVE LOGITS
     enough
    0.30
     Enough
    0.20
    ä¸Ķ
    0.20
     indeed
    0.17
    emente
    0.16
    çļĦæĺ¯
    0.16
    ;y
    0.15
    ly
    0.15
    Enough
    0.15
     throughout
    0.15
    Act Density 0.360%

    No Known Activations