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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their placement in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antan
    -0.16
    malink
    -0.14
    aines
    -0.14
    zell
    -0.13
    oto
    -0.13
    ÑĢад
    -0.13
    å¼Ĺ
    -0.13
    ï¼Īå¹³æĪIJ
    -0.13
    AIT
    -0.13
    ¯
    -0.13
    POSITIVE LOGITS
    ecure
    0.16
    ìĽĥ
    0.16
    ucz
    0.15
    ears
    0.14
    CRT
    0.14
     Locker
    0.14
     vag
    0.14
    elsius
    0.14
    beros
    0.14
    chat
    0.14
    Act Density 0.044%

    No Known Activations