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

    Neuronpedia

    INDEX
    Explanations

    sentences that end with a period and potentially have quotations and descriptions of people's reactions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express skepticism or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     levers
    -0.65
    mine
    -0.64
    HM
    -0.64
     sleeper
    -0.63
     optional
    -0.63
     unsus
    -0.62
    »Ĵ
    -0.62
    united
    -0.61
    hesda
    -0.61
    leigh
    -0.60
    POSITIVE LOGITS
     "[
    1.21
     Asked
    1.14
     Instead
    1.08
     Speaking
    1.05
     He
    1.02
     Whereas
    1.01
     Specifically
    0.99
     "#
    0.98
     Saying
    0.98
     Whenever
    0.97
    Act Density 0.333%

    No Known Activations