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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals involved in personal stories or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     embassies
    -0.62
     Ames
    -0.61
    interstitial
    -0.57
     rese
    -0.56
     surve
    -0.55
     blight
    -0.54
     pest
    -0.54
     Millenn
    -0.54
     grading
    -0.54
     bacterial
    -0.53
    POSITIVE LOGITS
    orah
    0.72
    andr
    0.71
    ModLoader
    0.68
    )=(
    0.68
    itech
    0.67
    stellar
    0.67
    eln
    0.67
    DCS
    0.67
    ija
    0.66
    aiman
    0.66
    Act Density 0.377%

    No Known Activations