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

    Neuronpedia

    INDEX
    Explanations

    names starting with "Le" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Le" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.87
    ãĥ¼ãĥĨ
    -0.81
    ividual
    -0.69
    lessly
    -0.65
     CPC
    -0.64
    etheless
    -0.64
     clock
    -0.64
    ãģĨ
    -0.63
    ����
    -0.62
     peanuts
    -0.60
    POSITIVE LOGITS
    isure
    1.35
    ukemia
    1.22
    agues
    1.10
    aping
    1.09
    aky
    1.03
    opard
    1.03
    ighton
    1.03
    ech
    1.01
    yden
    0.99
    grand
    0.97
    Act Density 0.021%

    No Known Activations