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

    Neuronpedia

    INDEX
    Explanations

    adverbs that indicate degrees or manners of occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oficialmente
    -0.81
     ultimately
    -0.80
     officiellement
    -0.78
    specifically
    -0.77
     particolarmente
    -0.76
     particularmente
    -0.75
     spécialement
    -0.74
    finally
    -0.74
     claramente
    -0.74
    fillType
    -0.74
    POSITIVE LOGITS
     speaking
    0.90
     parlant
    0.71
     Yours
    0.69
     worded
    0.68
     hablando
    0.68
    speaking
    0.65
     ترین
    0.65
     positioned
    0.65
     enough
    0.64
     constructed
    0.64
    Act Density 0.625%

    No Known Activations