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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences representing user interactions or timestamps

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numerical data and their contextual usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ´
    -0.79
    ãĤ®
    -0.79
    ãĥĩãĤ£
    -0.71
    ãĥ¼ãĥĨ
    -0.70
     tabl
    -0.69
    soDeliveryDate
    -0.68
    numbered
    -0.66
    ãĥŁ
    -0.66
    Þ
    -0.66
    ãĥīãĥ©
    -0.66
    POSITIVE LOGITS
     Quote
    0.91
    uin
    0.75
     Removed
    0.73
     Edited
    0.71
    eous
    0.69
     Alright
    0.69
     Seems
    0.69
     Thanks
    0.67
     Interesting
    0.67
     Related
    0.66
    Act Density 0.031%

    No Known Activations