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

    Neuronpedia

    INDEX
    Explanations

    references to different types, categories, or variations of items within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     économies
    -0.73
     समीक्षाएं
    -0.73
    rawDesc
    -0.64
     везе
    -0.60
     GetEnumerator
    -0.59
     investissements
    -0.59
     mesmos
    -0.57
     vœux
    -0.57
     Greed
    -0.55
    intervento
    -0.55
    POSITIVE LOGITS
     different
    0.95
     types
    0.83
    different
    0.77
    Different
    0.74
     unterschiedlich
    0.72
     forms
    0.72
     verschiedene
    0.70
     مختلف
    0.68
     distintos
    0.68
     distintas
    0.68
    Act Density 0.546%

    No Known Activations