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

    Neuronpedia

    INDEX
    Explanations

    quantitative descriptions related to large numbers or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.53
     noDo
    -0.44
     незавершена
    -0.42
     propOrder
    -0.42
    éndole
    -0.41
     دیکھیے
    -0.40
    BindView
    -0.40
     الرخصة
    -0.40
    astéro
    -0.40
    ̣t
    -0.39
    POSITIVE LOGITS
    hundreds
    0.92
     hundreds
    0.90
     Hundreds
    0.88
    Hundreds
    0.88
    thousands
    0.87
     thousands
    0.83
     dozens
    0.82
     Thousands
    0.82
    Thousands
    0.82
    数百
    0.76
    Act Density 0.365%

    No Known Activations