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

    Neuronpedia

    INDEX
    Explanations

    references to furniture or furnishings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ennes
    -0.16
    Sharper
    -0.15
    dül
    -0.15
    uyến
    -0.15
     orient
    -0.15
    dete
    -0.15
    jom
    -0.15
    opers
    -0.14
    done
    -0.14
    jual
    -0.14
    POSITIVE LOGITS
    aces
    0.35
    ishing
    0.32
    ace
    0.32
    ished
    0.28
    itures
    0.24
    isher
    0.23
    ISHED
    0.21
    ACES
    0.21
    aced
    0.21
    itur
    0.20
    Act Density 0.012%

    No Known Activations