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

    Neuronpedia

    INDEX
    Explanations

    terms related to optimization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fro
    -0.15
    oran
    -0.15
    938
    -0.15
    amburger
    -0.14
    uchar
    -0.14
    ILogger
    -0.14
    ingle
    -0.14
    ASSES
    -0.14
    elijke
    -0.14
    rp
    -0.14
    POSITIVE LOGITS
    acy
    0.15
    riding
    0.15
    /browse
    0.15
    ī
    0.15
    oplay
    0.14
    /rem
    0.14
    /max
    0.13
    ваем
    0.13
    erten
    0.13
     riding
    0.13
    Act Density 0.017%

    No Known Activations