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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or recurrence over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    over periods of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.84
    IUrlHelper
    -0.81
     autorytatywna
    -0.77
    uxxxx
    -0.70
    AlterField
    -0.69
     PeEnEo
    -0.69
    Autoritní
    -0.69
     createState
    -0.68
    httphttps
    -0.68
     Paglinawan
    -0.67
    POSITIVE LOGITS
     during
    0.46
     times
    0.39
     year
    0.38
     počas
    0.38
     tijden
    0.37
     gedurende
    0.36
     years
    0.35
     giudi
    0.35
    hidupan
    0.33
     leiding
    0.33
    Act Density 0.031%

    No Known Activations