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

    Neuronpedia

    INDEX
    Explanations

    references to development and related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earch
    -0.07
    utin
    -0.07
    ings
    -0.07
     Kou
    -0.06
     Kob
    -0.06
    ÙĪØ·
    -0.06
    _dll
    -0.06
    ruba
    -0.06
    CHA
    -0.06
    aison
    -0.06
    POSITIVE LOGITS
    ally
    0.10
    al
    0.09
    als
    0.08
    alist
    0.07
    ALLY
    0.07
    quip
    0.07
    że
    0.07
    ê¸Ī
    0.06
    oods
    0.06
    _squared
    0.06
    Act Density 0.011%

    No Known Activations