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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks or calls to action in text

    oai_token-act-pair · gpt-3.5-turbo

    hyperlinks and commands related to reading or viewing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paio
    -0.77
    phony
    -0.74
    testing
    -0.73
    é¾įå¥ij士
    -0.72
    matter
    -0.71
    tests
    -0.70
    furt
    -0.69
    quickShipAvailable
    -0.69
    mill
    -0.68
    existent
    -0.67
    POSITIVE LOGITS
     enlarge
    1.14
     subscribe
    0.94
     view
    0.88
     zoom
    0.87
     download
    0.86
     link
    0.85
     reproduce
    0.83
     enlarg
    0.83
     cite
    0.82
     learn
    0.80
    Act Density 0.041%

    No Known Activations