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

    Neuronpedia

    INDEX
    Explanations

    references to legal or formal language within sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "Ŀ" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     satell
    -0.99
     tradem
    -0.95
     imperson
    -0.84
     condol
    -0.84
     warr
    -0.84
     millenn
    -0.83
     hemor
    -0.81
     suspic
    -0.79
     overloaded
    -0.79
     cloning
    -0.78
    POSITIVE LOGITS
     Unfortunately
    1.28
     Therefore
    1.27
     Additionally
    1.25
     Furthermore
    1.25
     Similarly
    1.24
    Therefore
    1.23
     However
    1.22
    However
    1.20
     Hence
    1.18
    ï¸ı
    1.18
    Act Density 0.130%

    No Known Activations