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

    Neuronpedia

    INDEX
    Explanations

    references to physical plates, such as license plates or dinner plates

    oai_token-act-pair · gpt-3.5-turbo

    references to license plates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -1.07
    rians
    -0.78
    ITNESS
    -0.77
    Plug
    -0.74
    uish
    -0.73
    lished
    -0.70
    apest
    -0.70
    issance
    -0.69
    =]
    -0.67
    æĢ
    -0.66
    POSITIVE LOGITS
     plate
    1.13
     plates
    1.10
    plate
    1.03
    meal
    0.95
    ographer
    0.87
    aus
    0.83
    washer
    0.83
     Plate
    0.80
     armour
    0.77
    cloth
    0.77
    Act Density 0.016%

    No Known Activations