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

    Neuronpedia

    INDEX
    Explanations

    specific punctuations like periods to end sentences

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain concluding statements or full stops

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tyr
    -0.90
     condol
    -0.76
     metic
    -0.74
     silent
    -0.74
    uly
    -0.72
     redes
    -0.71
     reven
    -0.70
     defe
    -0.70
     forgot
    -0.70
     purse
    -0.70
    POSITIVE LOGITS
     Researchers
    1.21
     Moreover
    1.10
     Scientists
    1.08
     Additionally
    1.07
     Whereas
    1.06
     Furthermore
    1.05
     However
    1.04
     Typically
    1.03
     Ideally
    1.01
     Fortunately
    1.01
    Act Density 0.736%

    No Known Activations