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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -0.75
    setof
    -0.70
    offsetof
    -0.67
     Wicidata
    -0.66
    الإنجليزية
    -0.60
    elemField
    -0.56
    InjectAttribute
    -0.56
    ProcessEvent
    -0.55
    NameInMap
    -0.55
    parsedMessage
    -0.55
    POSITIVE LOGITS
     itself
    1.20
     Itself
    0.80
    itself
    0.72
     stesso
    0.71
     inteiro
    0.69
     stessa
    0.66
    verlauf
    0.65
    টি
    0.65
     itse
    0.65
    likation
    0.64
    Act Density 0.982%

    No Known Activations