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

    Neuronpedia

    INDEX
    Explanations

    technical details and descriptions related to technology and software

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     triggered
    -0.78
     lifes
    -0.76
     rejected
    -0.75
     honored
    -0.74
     engaged
    -0.73
     deemed
    -0.73
     designated
    -0.73
     undet
    -0.73
     coordinated
    -0.72
     reflex
    -0.71
    POSITIVE LOGITS
    Anyway
    1.87
    Conclusion
    1.78
    Lastly
    1.64
    Secondly
    1.63
    Finally
    1.59
    Nevertheless
    1.58
    CONCLUS
    1.58
    Furthermore
    1.55
    Also
    1.53
    Regardless
    1.52
    Act Density 0.434%

    No Known Activations