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

    Neuronpedia

    INDEX
    Explanations

    social media or online posting actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of authorship or posting in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasm
    -0.81
    figured
    -0.78
    conom
    -0.77
    MpServer
    -0.77
    chwitz
    -0.76
    imental
    -0.75
    ciples
    -0.72
    asers
    -0.69
    earchers
    -0.69
    split
    -0.68
    POSITIVE LOGITS
     Entry
    0.73
     Share
    0.70
     Tue
    0.70
     Anonymous
    0.68
     Blog
    0.68
     Guest
    0.66
     guiActive
    0.66
     Hello
    0.65
     Contribut
    0.65
     Tai
    0.64
    Act Density 0.054%

    No Known Activations