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

    Neuronpedia

    INDEX
    Explanations

    words related to medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "le" followed by various endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.92
    âĶģ
    -0.79
    ãĥ¼ãĥĨ
    -0.77
    ĸļ
    -0.76
    etheless
    -0.76
    aneers
    -0.76
    MODE
    -0.70
    ����
    -0.67
    ilities
    -0.67
    ãģĨ
    -0.66
    POSITIVE LOGITS
    opard
    1.14
    isure
    1.01
    icester
    0.97
    gging
    0.97
    vered
    0.96
    ather
    0.96
    aven
    0.96
    lla
    0.94
    yton
    0.93
    mons
    0.93
    Act Density 0.018%

    No Known Activations