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

    Neuronpedia

    INDEX
    Explanations

    references to specific names, potentially related to a person's name

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansas
    -0.70
    ned
    -0.68
     depress
    -0.67
    uit
    -0.67
    stream
    -0.66
    wegian
    -0.64
    blind
    -0.63
    locked
    -0.62
    meet
    -0.62
    pir
    -0.62
    POSITIVE LOGITS
    zzi
    1.11
    zzo
    1.11
    orno
    0.99
    otti
    0.98
    zza
    0.98
    ucci
    0.95
    Äĩ
    0.95
    olini
    0.92
    arella
    0.91
     Rossi
    0.89
    Act Density 0.042%

    No Known Activations