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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scrape
    -1.56
     Rhodes
    -1.54
    ray
    -1.50
    ipes
    -1.50
    usc
    -1.49
    elij
    -1.49
     remember
    -1.46
    membrane
    -1.43
    iston
    -1.40
     Scotia
    -1.40
    POSITIVE LOGITS
    ĥ½
    3.31
    ı
    3.15
    Ĩ
    3.03
    Ĥ
    2.83
    ¤
    2.69
    ¹
    2.67
    Ļ
    2.65
    ·
    2.63
    Ģ
    2.50
    ī
    2.49
    Act Density 0.126%

    No Known Activations