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

    Neuronpedia

    INDEX
    Explanations

    instances of the pattern "/a" typically associated with formatting or referencing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /tos
    -0.13
    ısından
    -0.13
    ibe
    -0.13
    .gwt
    -0.13
    izards
    -0.13
    ķĮ
    -0.12
    á»ijng
    -0.12
    iferay
    -0.12
    decorators
    -0.12
    emoth
    -0.12
    POSITIVE LOGITS
    ा↵
    0.14
    č↵
    0.14
    )↵
    0.13
    ↵↵↵
    0.13
    hek
    0.13
    ี↵
    0.13
    ospace
    0.13
     ,-
    0.12
    ]↵
    0.12
    ")↵
    0.12
    Act Density 0.462%

    No Known Activations