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

    Neuronpedia

    INDEX
    Explanations

    the start of a new section or paragraph in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tern
    -0.44
    .
    -0.42
     v
    -0.41
    terns
    -0.41
     tal
    -0.41
     once
    -0.41
    立た
    -0.40
     sil
    -0.40
     fallu
    -0.40
     even
    -0.40
    POSITIVE LOGITS
    Билгалдахарш
    1.04
     للاسماء
    0.94
    Geplaatst
    0.86
    Manbalar
    0.84
    الحياه
    0.81
    цездатний
    0.81
    CodeAttribute
    0.79
    Kaynakça
    0.78
     &___
    0.76
    Personensuche
    0.75
    Act Density 0.278%

    No Known Activations