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

    Neuronpedia

    INDEX
    Explanations

    numeric values associated with quantities or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allen
    -0.18
    swick
    -0.17
    uden
    -0.16
    udder
    -0.14
    pto
    -0.14
    uD
    -0.14
    ynet
    -0.14
    utsch
    -0.14
    ebi
    -0.14
    acco
    -0.14
    POSITIVE LOGITS
    úng
    0.14
    åĽº
    0.14
    arlar
    0.14
    /lg
    0.14
     Han
    0.14
    bed
    0.13
    è¿«
    0.13
    &action
    0.13
     stabil
    0.13
    ÏĥÏĦαν
    0.13
    Act Density 0.077%

    No Known Activations