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

    Neuronpedia

    INDEX
    Explanations

    words related to surveillance and privacy invasion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to surveillance and wiretapping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anthrop
    -0.72
     Ath
    -0.71
     Centauri
    -0.71
     Cout
    -0.69
     FAT
    -0.69
     Mankind
    -0.68
    nil
    -0.67
     Leap
    -0.67
     Athlet
    -0.66
    HY
    -0.66
    POSITIVE LOGITS
    apped
    1.16
     wiret
    1.15
    apping
    1.04
     eaves
    0.98
    apper
    0.93
    appers
    0.88
    appings
    0.87
    apons
    0.82
    dropping
    0.78
    obook
    0.78
    Act Density 0.027%

    No Known Activations