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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Å¡ov
    -0.15
    ÎIJ
    -0.15
    ìĸ¼
    -0.14
    olars
    -0.14
    HANDLE
    -0.14
    ιβ
    -0.14
    enumerator
    -0.13
    ÄĽli
    -0.13
    oa
    -0.13
    Æ°á»Ŀ
    -0.13
    POSITIVE LOGITS
     cards
    0.47
     horizon
    0.36
     Cards
    0.36
    cards
    0.33
     agenda
    0.32
    .cards
    0.30
    agenda
    0.28
     card
    0.26
    Cards
    0.25
    _cards
    0.25
    Act Density 0.045%

    No Known Activations