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

    Neuronpedia

    INDEX
    Explanations

    updates or new information in different domains such as news, art, or technology

    oai_token-act-pair · gpt-3.5-turbo

    references to updates or reports related to social or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omever
    -0.72
     someday
    -0.64
     dwarves
    -0.60
     deduct
    -0.57
    sic
    -0.55
    bernatorial
    -0.55
     Alchemy
    -0.55
    ãĤ©
    -0.54
     optimization
    -0.54
    ichick
    -0.54
    POSITIVE LOGITS
    ccording
    0.74
     IMAGES
    0.68
    SAN
    0.66
    ergus
    0.64
    gyn
    0.64
    LOS
    0.64
    POL
    0.63
    roversial
    0.62
    ype
    0.62
    Updated
    0.62
    Act Density 0.053%

    No Known Activations