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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebted
    -0.84
     Faw
    -0.80
    BuyableInstoreAndOnline
    -0.70
    vier
    -0.65
    cliffe
    -0.64
     Druid
    -0.64
     WARN
    -0.63
     Starr
    -0.63
     Barton
    -0.62
    staking
    -0.61
    POSITIVE LOGITS
    ¹
    1.38
    Ĵ
    1.34
    Ķ
    1.31
    Ŀ
    1.31
    ¿
    1.31
    ³
    1.30
    ¡
    1.29
    ±
    1.28
    ł
    1.26
    ·
    1.25
    Act Density 0.008%

    No Known Activations