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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "originally" or similar phrases indicating origin or initial status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ắp
    -0.17
    avier
    -0.17
    ifer
    -0.16
    ä¼ij
    -0.14
    Ĵáŀ
    -0.14
    irc
    -0.14
     Williamson
    -0.13
     åł
    -0.13
    ossal
    -0.13
    idd
    -0.13
    POSITIVE LOGITS
    occo
    0.15
     Heights
    0.15
    _trampoline
    0.15
    ków
    0.14
    cio
    0.14
    iou
    0.14
    daf
    0.14
    лÑıÑħ
    0.13
    ndx
    0.13
    peri
    0.13
    Act Density 0.012%

    No Known Activations