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

    Neuronpedia

    INDEX
    Explanations

    numeric values or codes, potentially related to technical terminology

    oai_token-act-pair · gpt-3.5-turbo

    numbers and codes related to different systems or categories, particularly in contexts like technology, legislation, and environmental science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     damned
    -0.78
    agna
    -0.73
     unsupported
    -0.65
     prescribed
    -0.64
    retch
    -0.63
    fried
    -0.60
    esses
    -0.59
    fred
    -0.59
    estamp
    -0.58
    antha
    -0.58
    POSITIVE LOGITS
    +,
    1.04
    +.
    0.91
    PO
    0.89
    DM
    0.87
    SO
    0.85
    +
    0.83
    VEN
    0.83
    DX
    0.79
    Edit
    0.79
    Js
    0.79
    Act Density 0.077%

    No Known Activations