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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names, possibly with characters that are not commonly found in English words such as "Äį", "é", and "Ħ"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities, particularly names and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idious
    -0.58
    sold
    -0.56
    abbage
    -0.55
    ALLY
    -0.54
    ulative
    -0.54
    tro
    -0.53
     FIRE
    -0.53
    inous
    -0.53
    ively
    -0.53
    «ĺ
    -0.52
    POSITIVE LOGITS
     Cyrus
    0.57
     inherit
    0.55
    ordan
    0.55
    theless
    0.54
    Reply
    0.53
    parts
    0.52
    uden
    0.51
    kj
    0.50
    idays
    0.50
    vana
    0.49
    Act Density 1.021%

    No Known Activations