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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to numerical data or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.60
     taş
    -0.56
     jā
    -0.56
    —
    -0.56
    last
    -0.55
    。
    -0.55
     Berwick
    -0.54
    ol
    -0.54
     kır
    -0.54
    o
    -0.54
    POSITIVE LOGITS
    %");
    1.00
    ")));
    1.00
     Мексичка
    0.94
    "]);
    0.94
    %")
    0.93
    "):
    0.91
    ioutil
    0.90
    '){
    0.88
     nahilalakip
    0.88
    "])
    0.88
    Act Density 0.001%

    No Known Activations