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

    Neuronpedia

    INDEX
    Explanations

    frequency adverbs indicating commonality or frequency of occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quelcon
    -0.46
    yecek
    -0.43
    endpush
    -0.41
    pecabe
    -0.41
    already
    -0.40
    ToMove
    -0.40
    ucket
    -0.39
    一片
    -0.38
     olacak
    -0.38
    一系列
    -0.38
    POSITIVE LOGITS
     often
    2.19
     sometimes
    2.06
     Often
    1.94
    often
    1.94
     occasionally
    1.91
    Often
    1.90
     Sometimes
    1.82
     Occasionally
    1.82
     spesso
    1.82
    sometimes
    1.81
    Act Density 1.550%

    No Known Activations