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

    Neuronpedia

    INDEX
    Explanations

    code snippets and file paths

    oai_token-act-pair · gpt-3.5-turbo

    structured data formats and programming language elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /,
    -0.81
    ãĥ¼ãĥĨ
    -0.74
    ãĥ¼ãĥĨãĤ£
    -0.71
    leep
    -0.70
    lihood
    -0.69
    thood
    -0.68
    alogue
    -0.68
    aturdays
    -0.67
     minim
    -0.67
    soever
    -0.67
    POSITIVE LOGITS
     Darkness
    0.68
     Driver
    0.66
     Crusher
    0.62
     ANG
    0.62
     Rim
    0.62
     --------------------------------
    0.61
     Yi
    0.60
     Bai
    0.60
     Drawn
    0.60
    Attach
    0.60
    Act Density 0.255%

    No Known Activations