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

    Neuronpedia

    INDEX
    Explanations

    expressions related to inner thoughts and self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     longevity
    -0.14
    çĺ
    -0.14
     ë°ĶëĿ¼
    -0.14
    Ñĸдом
    -0.13
    ccione
    -0.13
    enuity
    -0.13
    hton
    -0.13
    coni
    -0.13
    tingham
    -0.13
    sem
    -0.13
    POSITIVE LOGITS
    λÏİ
    0.15
    kov
    0.14
    createFrom
    0.14
     Parker
    0.13
    ãĥ¥
    0.13
    俺ãģ¯
    0.13
     tts
    0.13
    ÙĦاÙĨ
    0.13
    ýš
    0.13
    à¸Ńà¸ļ
    0.12
    Act Density 0.251%

    No Known Activations