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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sequences and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uard
    -0.15
     Tar
    -0.13
     Rodr
    -0.13
    isible
    -0.13
     Sext
    -0.13
     داÙħ
    -0.12
    alent
    -0.12
    vé
    -0.12
    tfoot
    -0.12
     Masks
    -0.12
    POSITIVE LOGITS
     order
    0.66
    order
    0.53
    éłĨ
    0.49
    -order
    0.49
    Order
    0.49
     Order
    0.48
     ORDER
    0.47
    顺
    0.46
    _order
    0.46
     sequence
    0.46
    Act Density 0.161%

    No Known Activations