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

    Neuronpedia

    INDEX
    Explanations

    references to crafting and card-making activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Collapsed
    -0.17
    ãģķãģ¾
    -0.16
    ider
    -0.15
    pitch
    -0.14
    reh
    -0.14
     Hlav
    -0.14
    Pitch
    -0.14
    _perms
    -0.14
    åīĩ
    -0.14
    ainers
    -0.13
    POSITIVE LOGITS
     card
    0.33
     cards
    0.31
     Card
    0.27
    CARD
    0.26
     CARD
    0.25
     Cards
    0.25
     Stamp
    0.25
    -card
    0.25
    card
    0.24
    Card
    0.24
    Act Density 0.034%

    No Known Activations