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

    Neuronpedia

    INDEX
    Explanations

    text within angled brackets that may indicate formatting errors or anomalies

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "Â"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -1.07
    ãģ®éŃĶ
    -0.93
    enburg
    -0.85
     VK
    -0.76
     Amon
    -0.67
     Moody
    -0.64
     Sidd
    -0.64
    é¾įå
    -0.63
     Shiva
    -0.63
     Kut
    -0.63
    POSITIVE LOGITS
    ³
    1.26
    ¹
    1.21
    ¥
    1.20
    ¬
    1.19
    ¿
    1.16
    µ
    1.13
    ¦
    1.12
    ¼
    1.08
    ¸
    1.06
    ¤
    1.06
    Act Density 0.015%

    No Known Activations