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

    Neuronpedia

    INDEX
    Explanations

    unique and non-standard characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocab
    -0.15
    __('
    -0.14
     centre
    -0.13
     аÑĢ
    -0.13
     «
    -0.13
     Fairfield
    -0.13
     centres
    -0.13
    cdb
    -0.13
    urga
    -0.13
    ention
    -0.13
    POSITIVE LOGITS
    ))))
    0.17
    ))))↵
    0.16
     myself
    0.16
    алÑİ
    0.15
    ))
    0.15
     offended
    0.15
     zas
    0.15
     Eisen
    0.14
    )))))↵
    0.14
    )))
    0.14
    Act Density 0.028%

    No Known Activations