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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing characteristics of buildings and homes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to locations and living situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fingerprints
    -0.88
     prophe
    -0.75
     viruses
    -0.73
     Hitman
    -0.72
     mete
    -0.71
     acron
    -0.71
     verbs
    -0.70
     epis
    -0.70
     epigen
    -0.70
     antibodies
    -0.69
    POSITIVE LOGITS
     courtyard
    1.22
    atorium
    1.18
     plaza
    1.15
    tyard
    1.13
     barracks
    1.10
    ominium
    1.10
     rooms
    1.07
    room
    1.05
     courthouse
    1.05
     cavern
    1.03
    Act Density 0.392%

    No Known Activations