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

    Neuronpedia

    INDEX
    Explanations

    keywords related to surveillance and privacy invasion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to surveillance and invasion of privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ISO
    -0.67
     Jiu
    -0.66
    ³³³³³³³³
    -0.65
    UAL
    -0.64
     feder
    -0.63
     SHARES
    -0.61
     tert
    -0.61
     shift
    -0.59
     fri
    -0.58
     huh
    -0.58
    POSITIVE LOGITS
    apping
    1.50
    apped
    1.45
    onduct
    1.29
    aps
    1.22
    appers
    1.22
    appings
    1.21
    olding
    1.15
    dropping
    1.13
    odied
    1.12
    aped
    1.09
    Act Density 0.082%

    No Known Activations