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

    Neuronpedia

    INDEX
    Explanations

    quotations and reported statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express opinions or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     helicop
    -0.52
    aldi
    -0.48
     challeng
    -0.48
     Vaugh
    -0.48
    ãĥ¼ãĥĨ
    -0.47
     Hutchinson
    -0.45
    aminer
    -0.44
     Moroc
    -0.44
    Runner
    -0.43
    bledon
    -0.43
    POSITIVE LOGITS
     âĺ
    0.62
    É
    0.61
     âĢº
    0.59
     ðŁ
    0.57
     âľ
    0.56
     â
    0.55
     largeDownload
    0.55
     ðŁij
    0.54
     Abandon
    0.53
    ËĪ
    0.52
    Act Density 3.294%

    No Known Activations