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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles starting with '@'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media handles or usernames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Curry
    -0.86
    kaya
    -0.82
     IR
    -0.80
     SAR
    -0.80
     Rao
    -0.79
    iola
    -0.79
     Ãĸ
    -0.78
    iru
    -0.77
    Ãį
    -0.75
    IR
    -0.75
    POSITIVE LOGITS
    Matt
    2.27
     Matt
    2.19
     matt
    1.70
     Mattis
    1.58
     Matthew
    1.56
    Matthew
    1.53
     mattress
    1.29
     Matthews
    1.20
     Duff
    1.02
     Madd
    1.02
    Act Density 0.211%

    No Known Activations