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

    Neuronpedia

    INDEX
    Explanations

    references to pull requests in software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĨĨ
    -0.15
    uml
    -0.14
    zsche
    -0.14
    δί
    -0.14
    coli
    -0.14
    asser
    -0.14
    cri
    -0.14
    REFERRED
    -0.13
     inde
    -0.13
    tdown
    -0.13
    POSITIVE LOGITS
    nees
    0.17
    marsh
    0.16
    ázd
    0.15
    æĺĩ
    0.14
    haps
    0.14
    folk
    0.14
    atile
    0.14
    laus
    0.14
    elian
    0.14
    walls
    0.14
    Act Density 0.032%

    No Known Activations