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

    Neuronpedia

    INDEX
    Explanations

    technology-related terms and companies

    oai_token-act-pair · gpt-3.5-turbo

    references to companies, organizations, or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensional
    -0.65
    ourning
    -0.61
    depending
    -0.60
    jriwal
    -0.57
    ~~~~~~~~~~~~~~~~
    -0.57
     sloppy
    -0.56
     deduct
    -0.56
    ependent
    -0.56
    iblical
    -0.54
    yright
    -0.54
    POSITIVE LOGITS
    ).[
    0.76
    ®,
    0.73
     Ltd
    0.70
    hof
    0.67
    ).
    0.65
    *.
    0.65
    Us
    0.64
    âĦ¢
    0.61
    naire
    0.61
     ("
    0.61
    Act Density 0.561%

    No Known Activations