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

    Neuronpedia

    INDEX
    Explanations

    references to prisoners and detainees

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

    people in specific roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.69
     surla
    -0.59
     يتيمه
    -0.57
     Мексичка
    -0.55
    AxisAlignment
    -0.55
    Clik
    -0.52
    tagHelperRunner
    -0.52
    GenerationType
    -0.51
     setPrice
    -0.51
    :✨
    -0.51
    POSITIVE LOGITS
    signee
    0.66
     participant
    0.64
     contestant
    0.63
     nominee
    0.63
     candidate
    0.62
     beneficiary
    0.60
     Candidate
    0.60
    tee
    0.60
    tees
    0.59
    participant
    0.59
    Act Density 0.016%

    No Known Activations