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

    Neuronpedia

    INDEX
    Explanations

    references to classes or educational settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     клаÑģÑģ
    -0.20
     class
    -0.20
    _class
    -0.20
    Class
    -0.20
     classes
    -0.19
    _classes
    -0.19
    _classifier
    -0.19
     classified
    -0.19
    ClassName
    -0.18
     classical
    -0.18
    POSITIVE LOGITS
    ä¼¼
    0.34
    mate
    0.32
    (es
    0.30
    ses
    0.28
    ifications
    0.28
    ifying
    0.27
    room
    0.27
    rooms
    0.27
    åĪ«
    0.27
    mates
    0.25
    Act Density 0.076%

    No Known Activations