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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating obligations or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     esternos
    -0.81
    SharedDtor
    -0.67
    Spoljašnje
    -0.64
    ########.
    -0.60
    Rohy
    -0.58
     droog
    -0.55
    AsUp
    -0.55
    Хьажоргаш
    -0.54
    mos
    -0.53
    vateľov
    -0.53
    POSITIVE LOGITS
    enumerate
    1.29
     مشين
    0.95
    itemize
    0.86
    setcounter
    0.74
    ".
    0.70
    $.
    0.70
    displayquote
    0.68
    __':
    0.67
    antiation
    0.66
    )':
    0.66
    Act Density 0.002%

    No Known Activations