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

    Neuronpedia

    INDEX
    Explanations

    specific token sequences that include a unique symbol sequence "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotional expressions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     regener
    -0.69
     sight
    -0.68
     lifes
    -0.67
     critically
    -0.65
     regenerate
    -0.65
     endeav
    -0.64
     star
    -0.63
     Reincarnated
    -0.62
     intended
    -0.62
     commission
    -0.61
    POSITIVE LOGITS
    Advertisements
    1.21
    --------------------------------------------------------
    1.18
    Newsletter
    1.12
    ONSORED
    1.09
    CONCLUS
    1.06
    Said
    0.99
    Anonymous
    0.99
    Comment
    0.99
    Therefore
    0.99
    Conclusion
    0.98
    Act Density 0.359%

    No Known Activations