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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and societal issues, controversies, and inquiries

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks at the ends of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deity
    -0.83
    der
    -0.71
     forgot
    -0.70
     reversible
    -0.68
     creature
    -0.66
     hatch
    -0.65
     cellar
    -0.64
    ishment
    -0.64
    anus
    -0.64
     mate
    -0.64
    POSITIVE LOGITS
     Particularly
    1.16
     Examples
    1.10
     Especially
    1.10
     Whereas
    1.07
     Nonetheless
    1.07
     Whether
    1.06
     Regardless
    1.06
     However
    1.05
     Recent
    1.05
     Including
    1.04
    Act Density 0.928%

    No Known Activations