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

    Neuronpedia

    INDEX
    Explanations

    keywords related to technology and digital devices

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to business and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.86
    udicrous
    -0.71
     Eag
    -0.71
     Juven
    -0.68
    auld
    -0.67
    among
    -0.66
    hement
    -0.66
    witz
    -0.65
    aiman
    -0.63
    acerb
    -0.63
    POSITIVE LOGITS
     selves
    1.09
    mates
    0.95
     buddies
    0.95
     mates
    0.93
     buddy
    0.90
     counterparts
    0.87
     preferences
    0.87
     wardrobe
    0.83
     spouse
    0.83
     choices
    0.79
    Act Density 0.354%

    No Known Activations