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

    Neuronpedia

    INDEX
    Explanations

    references to the color red

    oai_token-act-pair · gpt-3.5-turbo

    references to the color red, particularly in the context of brands or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     uncom
    -0.64
    awaru
    -0.63
    AGES
    -0.63
     incorpor
    -0.62
     prest
    -0.61
    Ö¼
    -0.59
     physic
    -0.56
    merce
    -0.56
     IM
    -0.56
     suffice
    -0.56
    POSITIVE LOGITS
    ucing
    1.37
    emption
    1.32
    eem
    1.30
    uces
    1.25
    irect
    1.22
    uced
    1.22
    ucer
    1.20
    acted
    1.18
    uctions
    1.13
    iscover
    1.13
    Act Density 0.024%

    No Known Activations