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

    Neuronpedia

    INDEX
    Explanations

    references to specific classes and methods in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.33
     (
    -0.31
     and
    -0.28
     "
    -0.28
     a
    -0.27
    ,
    -0.27
     the
    -0.26
     B
    -0.25
     in
    -0.25
     M
    -0.24
    POSITIVE LOGITS
    utils
    0.34
    framework
    0.31
    .util
    0.29
    commons
    0.26
    lib
    0.26
    .utils
    0.26
    util
    0.25
    tools
    0.25
    ql
    0.25
    kit
    0.25
    Act Density 0.072%

    No Known Activations