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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal thoughts or emotions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imester
    -0.73
     Colleg
    -0.67
    otos
    -0.63
     �
    -0.62
    onde
    -0.61
    aterasu
    -0.61
    Uncommon
    -0.59
     Cumber
    -0.59
    affles
    -0.58
    fecture
    -0.57
    POSITIVE LOGITS
    ").
    0.99
    "]
    0.98
    .")
    0.97
    "},
    0.93
    )"
    0.92
    ")
    0.91
    "),
    0.90
    "],
    0.88
    )",
    0.85
     nomine
    0.84
    Act Density 1.133%

    No Known Activations