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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific foreign language

    oai_token-act-pair · gpt-3.5-turbo

    the character "å" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agonist
    -0.79
    puted
    -0.72
    idepress
    -0.70
    Uncommon
    -0.68
    enegger
    -0.67
    PLIED
    -0.65
     overdoses
    -0.65
    iple
    -0.64
     entirety
    -0.63
    aires
    -0.62
    POSITIVE LOGITS
    å
    0.89
    sson
    0.88
    rd
    0.87
    sb
    0.85
    ¢
    0.82
    ĺ
    0.79
    hl
    0.79
    ø
    0.77
    «
    0.77
    µ
    0.77
    Act Density 0.015%

    No Known Activations