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

    Neuronpedia

    INDEX
    Explanations

    mentions of gifts and acts of giving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     independently
    -0.18
    endor
    -0.15
    ape
    -0.14
     arbit
    -0.14
    urai
    -0.14
    geh
    -0.14
     profile
    -0.14
     cor
    -0.13
     Independ
    -0.13
    obile
    -0.13
    POSITIVE LOGITS
     gift
    0.23
     gifts
    0.20
     Gift
    0.18
     gratis
    0.18
    Gratis
    0.17
     Gratis
    0.17
     Gifts
    0.17
    UFFIX
    0.16
    åħįè´¹
    0.16
    gift
    0.15
    Act Density 0.177%

    No Known Activations