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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "ire" in the text

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the term "Pirelli."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļé
    -0.84
    ¬¼
    -0.80
    ĸļ
    -0.75
    sylv
    -0.74
    ĺħ
    -0.71
    ĨĴ
    -0.71
    Ĥ¬
    -0.70
    oulos
    -0.70
    onent
    -0.70
    acca
    -0.69
    POSITIVE LOGITS
    lli
    1.17
    nces
    1.17
    ly
    0.98
    lessly
    0.97
    ttes
    0.97
    lla
    0.94
    ndra
    0.89
    cki
    0.86
    tta
    0.84
    MENTS
    0.84
    Act Density 0.045%

    No Known Activations