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

    Neuronpedia

    INDEX
    Explanations

    references to employment and workforce-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    people in positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prison
    -0.63
     inmates
    -0.60
    PCell
    -0.60
    EnumMember
    -0.59
    Übernach
    -0.59
    Prison
    -0.59
     Prison
    -0.56
     prisoners
    -0.56
     prison
    -0.56
    Hostel
    -0.56
    POSITIVE LOGITS
    InjectAttribute
    0.47
    AndEndTag
    0.43
    ///</
    0.36
     tourne
    0.34
    isiaj
    0.34
     nonUne
    0.32
    canestro
    0.32
     llegado
    0.32
    hasData
    0.29
     трен
    0.29
    Act Density 0.187%

    No Known Activations