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

    Neuronpedia

    INDEX
    Explanations

    mentions of locations or places related to criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their living situations or fatalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inctions
    -0.88
    hemy
    -0.86
    Reviewer
    -0.83
     Cosponsors
    -0.83
    otin
    -0.80
    emis
    -0.78
     largeDownload
    -0.78
    apter
    -0.75
    ernels
    -0.75
    yss
    -0.73
    POSITIVE LOGITS
     apartment
    1.53
     bedroom
    1.38
     driveway
    1.36
     residence
    1.21
     rented
    1.18
     hotel
    1.17
     hometown
    1.16
     garage
    1.16
     backyard
    1.15
     mailbox
    1.15
    Act Density 0.148%

    No Known Activations