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

    Neuronpedia

    INDEX
    Explanations

    keywords related to surveillance and personal reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ekon
    -0.14
    omi
    -0.13
     )↵↵↵↵↵↵↵↵
    -0.13
    _frm
    -0.12
    ÃĤ
    -0.12
    teÅĻÃŃ
    -0.11
    ndo
    -0.11
    kol
    -0.11
    bounding
    -0.11
    zia
    -0.11
    POSITIVE LOGITS
     mastur
    0.18
    --
    0.14
    rát
    0.13
    lassian
    0.13
    огод
    0.13
     strav
    0.12
    arium
    0.12
    .LayoutStyle
    0.12
    macen
    0.12
    atoria
    0.12
    Act Density 0.044%

    No Known Activations