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

    Neuronpedia

    INDEX
    Explanations

    references to past events and their implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alike
    -0.15
     sor
    -0.15
    ÄĽk
    -0.14
     Followers
    -0.14
     Sor
    -0.14
    aster
    -0.14
    izzer
    -0.14
     pri
    -0.14
    ienne
    -0.13
    peaker
    -0.13
    POSITIVE LOGITS
    unct
    0.18
    ritten
    0.15
    uga
    0.15
     Wort
    0.14
    ibility
    0.14
    اعب
    0.14
    enance
    0.14
     bý
    0.13
     aside
    0.13
    ugal
    0.13
    Act Density 0.395%

    No Known Activations