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

    Neuronpedia

    INDEX
    Explanations

    instances of concrete numerical values associated with people in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to mass gatherings or significant public participation events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.70
     holster
    -0.68
     Pair
    -0.67
    pter
    -0.63
     superiors
    -0.61
     Gentleman
    -0.61
    wcsstore
    -0.61
    SourceFile
    -0.59
    affer
    -0.59
    direction
    -0.58
    POSITIVE LOGITS
     voluntarily
    0.88
     illegally
    0.84
     annually
    0.79
     converge
    0.74
     migrate
    0.72
     homes
    0.70
     crammed
    0.70
    igrate
    0.70
     contrace
    0.69
     voluntary
    0.68
    Act Density 0.466%

    No Known Activations