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

    Neuronpedia

    INDEX
    Explanations

    years and numbers associated with historical events or biographical information

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical and date references related to historical events or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RAID
    -0.74
    ciating
    -0.64
    inventoryQuantity
    -0.63
    notations
    -0.62
     warr
    -0.62
     neighb
    -0.61
    uden
    -0.61
    Weak
    -0.60
     welf
    -0.56
    udeb
    -0.56
    POSITIVE LOGITS
    -'
    0.76
     Bomber
    0.71
    å¹
    0.69
     Engels
    0.67
    çļ
    0.67
    enegger
    0.67
    meier
    0.65
     MacArthur
    0.64
    aucas
    0.62
     Edition
    0.61
    Act Density 0.036%

    No Known Activations