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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly focusing on first names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    netflix
    -0.74
    ï¸ı
    -0.66
    prone
    -0.64
    å£
    -0.58
    minecraft
    -0.57
    mint
    -0.56
    usercontent
    -0.56
    ittens
    -0.56
    Downloadha
    -0.56
    avorite
    -0.56
    POSITIVE LOGITS
    oret
    0.68
    ħĭ
    0.66
    vill
    0.64
    wagen
    0.63
    amins
    0.62
    idential
    0.61
    igi
    0.61
    verty
    0.61
    elli
    0.60
    zyk
    0.60
    Act Density 0.103%

    No Known Activations