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

    Neuronpedia

    INDEX
    Explanations

    mentions of famous personalities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enthusi
    -0.82
     idle
    -0.75
     emotion
    -0.72
     harvest
    -0.70
     silent
    -0.70
     quir
    -0.69
     reflection
    -0.69
     challeng
    -0.68
     hiber
    -0.68
     jer
    -0.68
    POSITIVE LOGITS
     Though
    1.07
     Likewise
    1.05
     Interestingly
    1.04
     Fortunately
    1.03
     Throughout
    1.03
     Thankfully
    1.03
     Luckily
    1.02
     Their
    1.02
     Initially
    1.02
     Shortly
    1.02
    Act Density 0.592%

    No Known Activations