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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to places, names, or specific events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kus
    -0.37
     fili
    -0.33
     once
    -0.31
     gra
    -0.31
    Pol
    -0.30
     individual
    -0.29
    /
    -0.29
     major
    -0.29
     already
    -0.28
     pol
    -0.28
    POSITIVE LOGITS
     autorytatywna
    0.86
     للمعارف
    0.71
     EconPapers
    0.70
    expandindo
    0.66
    ChildScrollView
    0.65
     يتيمه
    0.65
    RegressionTest
    0.64
     виправивши
    0.63
    ReusableCell
    0.63
    帖最后由
    0.62
    Act Density 0.366%

    No Known Activations