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

    Neuronpedia

    INDEX
    Explanations

    conversations where people discuss or ask questions about specific topics

    oai_token-act-pair · gpt-3.5-turbo

    conversational exchanges and question formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uton
    -0.72
    izens
    -0.71
    ulent
    -0.70
    à©
    -0.65
    Constructed
    -0.65
    Site
    -0.64
    users
    -0.64
    versive
    -0.63
     stalk
    -0.62
    ãĥĭ
    -0.61
    POSITIVE LOGITS
     GOODMAN
    0.73
     gentlemen
    0.67
     independents
    0.66
     VIDE
    0.66
    AMY
    0.66
     Baird
    0.66
    laughs
    0.65
     Robb
    0.64
     Libyan
    0.64
     PRES
    0.62
    Act Density 1.761%

    No Known Activations