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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases that convey persistence or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ialect
    -0.16
    oit
    -0.15
    n
    -0.15
    ud
    -0.14
     Arch
    -0.13
    jet
    -0.13
    units
    -0.13
    Cd
    -0.13
    unit
    -0.13
    åħ
    -0.13
    POSITIVE LOGITS
    Å¡Å¥
    0.15
    سÙħØ©
    0.15
     Shorts
    0.15
    گاÙĩÛĮ
    0.15
    @brief
    0.14
    axter
    0.14
    égor
    0.14
     ApplicationException
    0.14
     rencont
    0.13
     Witness
    0.13
    Act Density 0.050%

    No Known Activations