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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking actions or making changes

    oai_token-act-pair · gpt-3.5-turbo

    statements or phrases that imply responsibility or accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    currently
    -0.86
    DM
    -0.82
    oubt
    -0.73
    hello
    -0.71
    arel
    -0.70
    uku
    -0.70
    whe
    -0.69
     hereafter
    -0.69
    Member
    -0.68
    weekly
    -0.68
    POSITIVE LOGITS
     Bain
    0.77
     Yanukovych
    0.73
     last
    0.71
     originally
    0.71
     yesterday
    0.70
     Katrina
    0.69
     Jacobs
    0.68
     Moss
    0.68
     Saban
    0.65
     Yanuk
    0.64
    Act Density 1.177%

    No Known Activations