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

    Neuronpedia

    INDEX
    Explanations

    mentions of family relationships

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and places associated with identifiable attributes or significant contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibraries
    -0.68
    ocate
    -0.66
    soDeliveryDate
    -0.59
    د
    -0.58
    ritis
    -0.58
    orically
    -0.57
    AMA
    -0.56
    hov
    -0.55
    cerpt
    -0.55
    enegger
    -0.54
    POSITIVE LOGITS
     basis
    1.47
     occasions
    1.30
     grounds
    1.18
     occasion
    1.16
     behalf
    1.12
     shores
    1.08
    imeo
    1.07
     doorstep
    1.06
     shelf
    1.04
     horizon
    1.03
    Act Density 0.525%

    No Known Activations