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

    Neuronpedia

    INDEX
    Explanations

    special characters likely indicating a mistake or anomaly in the text

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -1.07
    ãģ®éŃĶ
    -0.85
    gow
    -0.83
    ements
    -0.74
    enburg
    -0.72
    iator
    -0.68
    arians
    -0.66
    EMENT
    -0.66
     Frey
    -0.62
    iants
    -0.62
    POSITIVE LOGITS
    ³
    1.31
    ¹
    1.29
    ¦
    1.26
    ¿
    1.25
    ¬
    1.24
    µ
    1.24
    ¥
    1.22
    ¸
    1.19
    ¼
    1.17
    ¤
    1.15
    Act Density 0.027%

    No Known Activations