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

    Neuronpedia

    INDEX
    Explanations

    sections of code that provide summaries or descriptions of methods and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñıн
    -0.16
    upo
    -0.15
    ÑĢоÑĤ
    -0.15
    stoff
    -0.14
    owitz
    -0.14
    etty
    -0.14
     Vog
    -0.14
     Ø¥ÙĦÙĬÙĩ
    -0.13
    خش
    -0.13
    ewart
    -0.13
    POSITIVE LOGITS
    >↵
    0.25
    )↵
    0.19
    typeparam
    0.19
    >s
    0.17
    remarks
    0.17
     Fancy
    0.16
    ')↵
    0.16
    ]↵
    0.16
    ")↵
    0.15
    }↵
    0.15
    Act Density 0.003%

    No Known Activations