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

    Neuronpedia

    INDEX
    Explanations

    verbal expressions indicating preference or desire

    oai_token-act-pair · gpt-3.5-turbo

    expressions of preference or desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.76
    Judge
    -0.76
    inventoryQuantity
    -0.75
    Grade
    -0.73
    Neg
    -0.64
    Definition
    -0.63
     scrut
    -0.63
    interstitial
    -0.63
    NK
    -0.63
    SpaceEngineers
    -0.62
    POSITIVE LOGITS
     Clever
    0.77
    ĸļ
    0.70
    plin
    0.63
    ogue
    0.61
    icably
    0.61
    ijn
    0.60
    abase
    0.60
     bi
    0.60
    initely
    0.59
     kidding
    0.57
    Act Density 0.066%

    No Known Activations