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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to roles, concepts, and messages in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aille
    -0.15
    trait
    -0.14
    licit
    -0.14
    lander
    -0.14
    erv
    -0.14
    manship
    -0.14
    nage
    -0.14
    val
    -0.14
    anh
    -0.13
    _BO
    -0.13
    POSITIVE LOGITS
     Of
    0.15
    aucoup
    0.15
    OfWork
    0.14
    Of
    0.14
    erde
    0.14
    _of
    0.14
    ivy
    0.14
     TMPro
    0.13
    åŃĺäºİ
    0.13
     Yourself
    0.13
    Act Density 0.657%

    No Known Activations