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

    Neuronpedia

    INDEX
    Explanations

    terms related to edible items

    oai_token-act-pair · gpt-3.5-turbo

    words that refer to collectible items or products, especially in the context of their availability or desirability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     synchron
    -0.65
     Pool
    -0.65
     setting
    -0.64
     marathon
    -0.63
     Ren
    -0.62
     dem
    -0.61
     squ
    -0.60
    Govern
    -0.59
     mer
    -0.58
     stroke
    -0.58
    POSITIVE LOGITS
    ibles
    5.19
    ible
    2.77
    ibility
    2.44
    IBLE
    2.35
    ibilities
    2.23
    ibly
    2.14
    ibl
    1.51
    ables
    1.31
    iors
    1.23
    icals
    1.21
    Act Density 0.009%

    No Known Activations