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

    Neuronpedia

    INDEX
    Explanations

    emoticons

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters often used in social media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gillespie
    -0.72
    wagen
    -0.72
     Sakuya
    -0.71
    phrine
    -0.69
     Akin
    -0.69
    ioned
    -0.67
     Manit
    -0.65
    oidal
    -0.65
    epad
    -0.65
     Samson
    -0.64
    POSITIVE LOGITS
    ¥ŀ
    1.26
    Ĵ
    1.24
    ĵ
    1.24
    ðŁ
    1.22
    Ķ
    1.19
    į
    1.18
    ĻĤ
    1.16
    Į
    1.16
    ĩ
    1.11
    İ
    1.08
    Act Density 0.004%

    No Known Activations