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

    Neuronpedia

    INDEX
    Explanations

    emphasized content or formatted text elements in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hou
    -0.16
    arn
    -0.15
    anga
    -0.15
    ighton
    -0.14
    ivel
    -0.14
    encer
    -0.14
    awai
    -0.14
    aid
    -0.14
     Bret
    -0.14
    ight
    -0.13
    POSITIVE LOGITS
    ph
    0.19
    {
    0.18
    nesc
    0.17
    shape
    0.15
    cheng
    0.15
    IFA
    0.14
    ery
    0.14
    ÑĪин
    0.14
    854
    0.14
    positor
    0.14
    Act Density 0.011%

    No Known Activations