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

    Neuronpedia

    INDEX
    Explanations

    laws, regulations, programs, campaigns, and events

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terminology related to laws, campaigns, and programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fal
    -0.79
    inventoryQuantity
    -0.78
    姫
    -0.74
    hin
    -0.72
    utherland
    -0.72
    ixel
    -0.71
    esson
    -0.70
     largeDownload
    -0.69
    DragonMagazine
    -0.67
    anyl
    -0.65
    POSITIVE LOGITS
    naire
    0.83
    naires
    0.80
     spree
    0.67
     loophole
    0.62
     ank
    0.61
     bracelet
    0.60
     Tracker
    0.58
     jointly
    0.58
    orously
    0.58
     bloc
    0.58
    Act Density 0.432%

    No Known Activations