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

    Neuronpedia

    INDEX
    Explanations

    sentences with periods at the end

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain conclusive statements or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tyr
    -1.02
     metic
    -0.78
    ributes
    -0.71
     gobl
    -0.69
     enthusi
    -0.69
    ibur
    -0.67
     condol
    -0.67
     pillar
    -0.66
     footing
    -0.66
     boarded
    -0.66
    POSITIVE LOGITS
     Additionally
    1.19
     Moreover
    1.15
     Fortunately
    1.12
     However
    1.12
     Typically
    1.12
     Furthermore
    1.12
     Whereas
    1.10
     Eventually
    1.09
     Luckily
    1.08
     Depending
    1.08
    Act Density 1.239%

    No Known Activations