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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interaction and social media

    oai_token-act-pair · gpt-3.5-turbo

    symbols or special characters used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Donna
    -0.77
     Billy
    -0.76
     unbeliev
    -0.75
     laund
    -0.72
     disse
    -0.71
     Mill
    -0.71
     Harley
    -0.70
     excuses
    -0.69
     Haj
    -0.69
     Debor
    -0.69
    POSITIVE LOGITS
    ĺ
    1.84
    ĺħ
    1.10
    ĸ
    1.08
    Ĺ
    1.06
    IJ
    1.04
    Ĵ
    0.96
    Ķ
    0.96
    ĥ
    0.95
    ¦
    0.94
    ¥
    0.94
    Act Density 0.105%

    No Known Activations