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

    Neuronpedia

    INDEX
    Explanations

    keywords related to news updates

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "More" indicating additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.75
    uca
    -0.69
    itiz
    -0.67
    xtap
    -0.66
     bearer
    -0.65
    adr
    -0.63
    ilogy
    -0.62
    imeter
    -0.62
    AFTA
    -0.61
    )",
    -0.61
    POSITIVE LOGITS
     importantly
    1.32
     than
    1.05
     Than
    1.03
    llo
    0.96
     info
    0.92
     Info
    0.89
     Information
    0.88
     details
    0.87
     interestingly
    0.86
     Details
    0.86
    Act Density 0.044%

    No Known Activations