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

    Neuronpedia

    INDEX
    Explanations

    instances where sentences end with punctuation, specifically periods

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude with a period, indicating complete thoughts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     awaited
    -0.75
     alleged
    -0.75
    iannopoulos
    -0.75
     millenn
    -0.74
     hailed
    -0.73
     descendants
    -0.73
     imprisoned
    -0.72
     detained
    -0.72
     unspecified
    -0.71
     unmanned
    -0.70
    POSITIVE LOGITS
     Ideally
    1.42
     Avoid
    1.34
     Remember
    1.30
     Knowing
    1.27
     Especially
    1.27
    Avoid
    1.27
     Include
    1.27
     Often
    1.26
     Always
    1.22
     Lastly
    1.22
    Act Density 0.511%

    No Known Activations