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

    Neuronpedia

    INDEX
    Explanations

    references to historical events, figures, or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.44
    Quoi
    -0.43
    Scénario
    -0.40
     Herausforderung
    -0.37
     يتيمه
    -0.37
     vyk
    -0.37
    商品説明
    -0.36
     Möglichkeiten
    -0.36
     deren
    -0.35
     Unterkunft
    -0.35
    POSITIVE LOGITS
     origins
    0.61
     term
    0.60
     original
    0.60
     Romans
    0.60
     Nazis
    0.59
     story
    0.58
     invention
    0.57
     exploits
    0.56
     birth
    0.56
     concept
    0.56
    Act Density 0.847%

    No Known Activations