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

    Neuronpedia

    INDEX
    Explanations

    the initials "DL" followed by various digits

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific acronym or designation, particularly "DL"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eering
    -0.83
    ãĥ¼ãĥĨ
    -0.72
    ãĤ¡
    -0.72
    ulatory
    -0.70
    eers
    -0.69
    flies
    -0.69
    âĸĪâĸĪ
    -0.69
     pleasing
    -0.66
    ãĤ±
    -0.66
    eer
    -0.66
    POSITIVE LOGITS
    anguage
    1.07
    owship
    1.03
    ibrary
    0.99
    uce
    0.99
    iamond
    0.86
    DL
    0.86
    ysis
    0.86
    inking
    0.84
    UX
    0.83
    ouble
    0.79
    Act Density 0.011%

    No Known Activations