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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their usage in the context of making claims or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Искәрмәләр
    -0.65
     betweenstory
    -0.60
    DockStyle
    -0.59
     tyran
    -0.58
    styleType
    -0.58
     Efq
    -0.57
     समीक्षक
    -0.57
    basicConfig
    -0.56
     eredmény
    -0.56
     Sixteenth
    -0.55
    POSITIVE LOGITS
    Für
    0.61
     für
    0.59
    complexContent
    0.57
     Für
    0.56
    клопе
    0.55
    iama
    0.54
     voor
    0.53
    MemoryWarning
    0.51
     kapas
    0.50
    Για
    0.49
    Act Density 0.251%

    No Known Activations