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

    Neuronpedia

    INDEX
    Explanations

    character names and locations mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    specific character sequences or letter patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fusc
    -0.65
    iors
    -0.60
    _.
    -0.60
     Diaz
    -0.59
     Gamma
    -0.57
     Archdemon
    -0.56
    aea
    -0.56
     Geh
    -0.55
    qs
    -0.54
     Dyn
    -0.54
    POSITIVE LOGITS
    WASHINGTON
    1.19
    VILLE
    1.14
     CITY
    1.08
    MAN
    1.05
    SHARE
    1.02
    LAND
    1.00
    GREEN
    1.00
    HOU
    0.98
    BUS
    0.98
    BIL
    0.98
    Act Density 0.186%

    No Known Activations