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

    Neuronpedia

    INDEX
    Explanations

    key programming constructs and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sung
    -0.85
     Greene
    -0.85
    hunt
    -0.83
     Caldwell
    -0.81
     Hust
    -0.79
     Raleigh
    -0.78
     Hamburg
    -0.78
     Reyes
    -0.77
     Jed
    -0.77
    Salt
    -0.76
    POSITIVE LOGITS
     item
    1.32
    Item
    1.14
    item
    1.10
     particle
    1.09
     Item
    1.09
     artifact
    1.04
     object
    1.00
    object
    0.98
     product
    0.97
    attribute
    0.97
    Act Density 0.092%

    No Known Activations