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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and references to self and others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amba
    -0.17
    ime
    -0.16
    uff
    -0.15
     dies
    -0.15
    wie
    -0.14
    auf
    -0.14
    472
    -0.14
    åģ¥
    -0.14
    estroy
    -0.14
    weis
    -0.13
    POSITIVE LOGITS
     Conte
    0.13
    _simps
    0.13
    ovsky
    0.13
     Ùħز
    0.13
    ibar
    0.13
    íĭ°
    0.13
    ymes
    0.13
    èĮĤ
    0.13
     å»
    0.13
    äºŃ
    0.13
    Act Density 0.645%

    No Known Activations