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

    Neuronpedia

    INDEX
    Explanations

    words related to specific objects, such as 'car', 'bike', 'beer', 'phone', 'device', and 'card'

    oai_token-act-pair · gpt-3.5-turbo

    common objects or items, particularly vehicles and electronic devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dhabi
    -0.80
    amy
    -0.72
    ync
    -0.69
    imon
    -0.69
    20439
    -0.67
    azeera
    -0.65
    cffff
    -0.64
    Enlarge
    -0.63
    Ĥ¬
    -0.62
    ara
    -0.61
    POSITIVE LOGITS
     itself
    0.99
     underwent
    0.90
     belonged
    0.86
    wright
    0.83
     manufact
    0.75
    maker
    0.73
     premiered
    0.73
     revolves
    0.73
     resided
    0.72
     owner
    0.72
    Act Density 0.391%

    No Known Activations