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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.82
    ãģ®é
    -0.75
     electron
    -0.74
    476
    -0.74
     Payton
    -0.74
     Butter
    -0.73
    ©¶æ
    -0.72
     debit
    -0.71
    [[
    -0.71
     Pyr
    -0.69
    POSITIVE LOGITS
    ang
    1.12
    org
    1.02
    ong
    1.01
    angs
    0.98
    ANG
    0.97
     Mong
    0.88
    ange
    0.88
    anger
    0.87
     lang
    0.84
    mong
    0.83
    Act Density 0.222%

    No Known Activations