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

    Neuronpedia

    INDEX
    Explanations

    text marked with a specific formatting element, represented by Ċ

    oai_token-act-pair · gpt-3.5-turbo

    sections of text related to academic citations and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     diving
    -0.71
     ideal
    -0.71
     health
    -0.66
     teammates
    -0.66
     targets
    -0.66
     frontline
    -0.65
     volleyball
    -0.64
     Horizon
    -0.64
     vision
    -0.63
     priority
    -0.63
    POSITIVE LOGITS
    ³³³³³³³³
    1.54
    ³³³
    1.50
    ³³³³³³³³³³³³³³³³
    1.44
    ³³³³
    1.38
    Thus
    1.30
    posted
    1.23
    ³³
    1.20
    Conclusion
    1.19
    CONCLUS
    1.19
    Indeed
    1.16
    Act Density 0.389%

    No Known Activations