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

    Neuronpedia

    INDEX
    Explanations

    references to cities, particularly Paris and Berlin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anel
    -0.17
    ]={↵
    -0.14
    olls
    -0.14
    hod
    -0.14
    vice
    -0.14
    ein
    -0.13
    ¥¿
    -0.13
    nbsp
    -0.13
    itre
    -0.13
    ãĥ©ãĥ³ãĥī
    -0.13
    POSITIVE LOGITS
    hausen
    0.16
    ãĤī
    0.15
    shire
    0.15
    -average
    0.15
    ois
    0.15
    TextWriter
    0.14
    estone
    0.14
    _HOOK
    0.14
    265
    0.13
    ian
    0.13
    Act Density 0.103%

    No Known Activations