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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gradual change or repetition / emphasis

    oai_token-act-pair · gpt-3.5-turbo

    commas and phrases indicating gradual change or evolution over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assi
    -0.75
    USS
    -0.68
    ãĤ¦ãĤ¹
    -0.65
    uge
    -0.62
    Ĺ
    -0.60
    ħĭ
    -0.60
    ãĥ£
    -0.59
    cluded
    -0.59
    ibles
    -0.58
    heim
    -0.58
    POSITIVE LOGITS
    without
    0.95
     without
    0.95
     preferably
    0.92
     cheaply
    0.89
     irrespective
    0.88
     orally
    0.81
     thanks
    0.81
     uninterrupted
    0.79
     anytime
    0.79
     during
    0.79
    Act Density 0.445%

    No Known Activations