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

    Neuronpedia

    INDEX
    Explanations

    phrases related to establishing, forming, or creating something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the establishment of new entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.68
    itte
    -0.64
     mates
    -0.58
     itch
    -0.58
     Surviv
    -0.56
     pasture
    -0.56
     whit
    -0.55
     herd
    -0.55
    beard
    -0.55
     Tycoon
    -0.53
    POSITIVE LOGITS
    itored
    0.71
    ģ«
    0.71
    ŃĶ
    0.67
     throughout
    0.65
    iat
    0.64
     whereby
    0.63
    ioxide
    0.63
    NN
    0.63
    ../
    0.63
    Ãł
    0.63
    Act Density 0.353%

    No Known Activations