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

    Neuronpedia

    INDEX
    Explanations

    text related to reproduction rights and affiliate links

    oai_token-act-pair · gpt-3.5-turbo

    mentions of affiliate links and copyright or distribution policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pist
    -0.73
     Fam
    -0.65
     Eug
    -0.65
    etts
    -0.64
     Conc
    -0.62
    naire
    -0.62
     Gest
    -0.60
     Nig
    -0.59
     Gork
    -0.58
     Patri
    -0.58
    POSITIVE LOGITS
    Content
    0.74
    content
    0.73
    Asset
    0.73
    yright
    0.72
    NPR
    0.71
    oa
    0.70
     Flavoring
    0.70
     {*
    0.68
     attribution
    0.68
    iliate
    0.67
    Act Density 0.202%

    No Known Activations