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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal stories and questions

    oai_token-act-pair · gpt-3.5-turbo

    prompts or questions that seek information or clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     flowing
    -0.83
     sustained
    -0.82
     synerg
    -0.81
     piled
    -0.79
     downstream
    -0.79
     committed
    -0.78
     flowering
    -0.77
     funeral
    -0.76
     flavored
    -0.76
     overt
    -0.75
    POSITIVE LOGITS
    Answer
    2.23
    Well
    1.87
    Yes
    1.78
    Absolutely
    1.72
    Probably
    1.61
    Wr
    1.53
    Certainly
    1.53
    Yeah
    1.52
    Actually
    1.49
    Sure
    1.48
    Act Density 0.202%

    No Known Activations