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

    Neuronpedia

    INDEX
    Explanations

    instances where 'a' is followed by an adjective, suggesting a characteristic or quality of something

    oai_token-act-pair · gpt-3.5-turbo

    articles and quantifiers preceding nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    psons
    -0.88
    mins
    -0.77
    ians
    -0.77
    Express
    -0.75
    ATURES
    -0.73
    Hamilton
    -0.71
    vt
    -0.71
    Events
    -0.71
    Edit
    -0.70
    EDIT
    -0.68
    POSITIVE LOGITS
     piece
    0.98
     bunch
    0.91
     finite
    0.87
     lot
    0.85
     tease
    0.81
     joke
    0.81
     situational
    0.77
     glance
    0.77
     headache
    0.76
     geographically
    0.75
    Act Density 0.127%

    No Known Activations