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

    Neuronpedia

    INDEX
    Explanations

    references to compliance and documentation requirements in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oft
    -0.16
    ">//
    -0.16
    stalk
    -0.15
    oldt
    -0.15
    heimer
    -0.15
     Protected
    -0.14
    642
    -0.14
    aney
    -0.13
    lesc
    -0.13
    fld
    -0.13
    POSITIVE LOGITS
    chied
    0.15
    ouden
    0.15
    uez
    0.15
    ilee
    0.15
     automát
    0.14
    ất
    0.14
    iggins
    0.14
     meiden
    0.14
     rat
    0.14
     mec
    0.14
    Act Density 0.117%

    No Known Activations