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

    Neuronpedia

    INDEX
    Explanations

    statistical and numerical data

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and colons in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     amnesty
    -0.85
     divest
    -0.81
     uncond
    -0.80
     unconditional
    -0.80
     solic
    -0.78
     citizenship
    -0.74
     withholding
    -0.74
     initi
    -0.73
     repatri
    -0.72
     affirmative
    -0.71
    POSITIVE LOGITS
    Conclusion
    1.06
    Ingredients
    1.06
    Screenshot
    1.04
    Features
    1.02
    Pict
    0.98
    Notice
    0.97
    RGB
    0.97
    Figure
    0.96
    Compar
    0.96
    References
    0.96
    Act Density 0.485%

    No Known Activations