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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "will" indicating future actions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¼¥
    -0.15
    å¹²
    -0.14
    otime
    -0.14
    489
    -0.14
     vast
    -0.13
    .uf
    -0.13
     ken
    -0.13
    åĺĽ
    -0.13
    ÙĤÙĩ
    -0.13
    _large
    -0.13
    POSITIVE LOGITS
    anity
    0.15
    Äĥr
    0.15
    лин
    0.14
    _locale
    0.14
    igion
    0.14
    orias
    0.14
    icho
    0.13
    pig
    0.13
    agues
    0.13
    wstring
    0.13
    Act Density 0.138%

    No Known Activations