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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to systems and mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éŀ
    -0.15
    atcher
    -0.15
    ards
    -0.15
    енноÑģÑĤÑĮ
    -0.14
    enger
    -0.14
    assi
    -0.14
    _REC
    -0.14
    pty
    -0.14
    BaseContext
    -0.14
     СÑĢед
    -0.13
    POSITIVE LOGITS
    级
    0.17
    ç´ļ
    0.16
    oa
    0.15
    isky
    0.15
    775
    0.15
    949
    0.15
    isinden
    0.14
    оваÑĢ
    0.14
    èį·
    0.14
    -level
    0.14
    Act Density 0.549%

    No Known Activations