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

    Neuronpedia

    INDEX
    Explanations

    URLs

    oai_token-act-pair · gpt-3.5-turbo

    specific country codes or domain suffixes related to various web and news sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    busters
    -0.78
    rises
    -0.71
    cutting
    -0.63
    izations
    -0.61
    isations
    -0.60
    peat
    -0.60
    Americans
    -0.60
    Grade
    -0.60
    ety
    -0.59
    whether
    -0.58
    POSITIVE LOGITS
    /?
    0.83
     Ltd
    0.76
    /,
    0.76
     Lumpur
    0.74
    /-
    0.73
    ppe
    0.73
    /.
    0.72
    /#
    0.71
    MpServer
    0.69
    erv
    0.68
    Act Density 0.039%

    No Known Activations