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

    Neuronpedia

    INDEX
    Explanations

    numbers related to dates, sequences, quantities, or rankings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the end-of-text token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tnc
    -0.75
     confer
    -0.72
    jri
    -0.66
     vou
    -0.66
     conferred
    -0.64
    cius
    -0.64
    ¬¼
    -0.63
     subsistence
    -0.62
     advant
    -0.62
    etooth
    -0.62
    POSITIVE LOGITS
     sequels
    1.37
     sequel
    1.27
     thriller
    1.21
     screenplay
    1.20
     trilogy
    1.19
     novels
    1.14
     anime
    1.14
     manga
    1.13
     cinematic
    1.13
     anthology
    1.12
    Act Density 2.180%

    No Known Activations