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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portály
    -0.79
     Мексичка
    -0.77
    */].
    -0.76
    ècie
    -0.74
    oredCriteria
    -0.73
    ノロ
    -0.71
    AddTagHelper
    -0.70
     ReSharper
    -0.69
    <?
    -0.68
    DockStyle
    -0.68
    POSITIVE LOGITS
     one
    1.12
    one
    0.81
     одного
    0.77
     одной
    0.71
     jednego
    0.65
     одну
    0.64
     אחד
    0.62
     אחת
    0.61
     één
    0.58
     jednej
    0.58
    Act Density 0.242%

    No Known Activations