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

    Neuronpedia

    INDEX
    Explanations

    numeric values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "I have a" followed by a noun

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FIG
    -0.92
    inventoryQuantity
    -0.87
    advertising
    -0.74
    independence
    -0.73
    imar
    -0.71
    apo
    -0.71
    vale
    -0.71
    icio
    -0.69
    Ĥİ
    -0.69
    querade
    -0.68
    POSITIVE LOGITS
     doubts
    1.15
     knack
    1.10
     recollection
    1.05
     boyfriend
    1.04
     spare
    1.03
     girlfriend
    1.03
     question
    1.02
     idea
    1.02
     suggestion
    1.02
     clue
    1.01
    Act Density 0.155%

    No Known Activations