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

    Neuronpedia

    INDEX
    Explanations

    people or places associated with specific names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.54
    selves
    -0.54
    enance
    -0.53
    endiary
    -0.52
    href
    -0.49
    âĢ¢âĢ¢
    -0.49
     Leilan
    -0.48
    terms
    -0.48
    rooms
    -0.47
    *.
    -0.47
    POSITIVE LOGITS
    çİĭ
    0.56
    ®
    0.51
    «
    0.51
    Arcade
    0.50
    Coin
    0.49
    ©
    0.49
    Pack
    0.48
    Armor
    0.48
    ·
    0.48
    İ
    0.47
    Act Density 0.741%

    No Known Activations