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

    Neuronpedia

    INDEX
    Explanations

    URLs prompting viewers to share a story

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the action of sharing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.87
    schild
    -0.85
    anwhile
    -0.83
    paio
    -0.82
    £ı
    -0.81
    anthrop
    -0.81
    undai
    -0.80
     desper
    -0.77
    wagen
    -0.75
     submar
    -0.74
    POSITIVE LOGITS
    holder
    1.01
    holders
    0.96
     Share
    0.84
    cro
    0.82
    ning
    0.81
     Shares
    0.78
    ables
    0.78
    edin
    0.78
    ned
    0.76
    ership
    0.76
    Act Density 0.011%

    No Known Activations