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

    Neuronpedia

    INDEX
    Explanations

    beginning markers in a text or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.81
    ModelBuilder
    -0.77
    Demografía
    -0.77
    =$("#
    -0.75
    Traducción
    -0.74
    :✨
    -0.74
    Moll
    -0.73
     occaf
    -0.72
     Pender
    -0.71
    țiune
    -0.70
    POSITIVE LOGITS
    ><
    1.27
    "><
    0.92
    \
    0.79
    [toxicity=0]
    0.73
    hidupan
    0.65
     Dunlop
    0.65
    ContextCompat
    0.64
    ="#"><
    0.62
    󠁿
    0.59
    </em>
    0.58
    Act Density 0.089%

    No Known Activations