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

    Neuronpedia

    INDEX
    Explanations

    references to human rights reports and statements

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

    human rights violations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.58
    Hentet
    -0.55
     تضيفلها
    -0.52
    WriteBarrier
    -0.52
    InputBorder
    -0.50
     مشين
    -0.50
     createSlice
    -0.50
    gameserver
    -0.48
     صوتيه
    -0.48
    +:+
    -0.47
    POSITIVE LOGITS
    
    0.48
     human
    0.36
    คลิ
    0.35
    HUMAN
    0.35
    Kết
    0.35
    oa̍t
    0.35
    ayat
    0.34
    adpleegd
    0.34
    Bisous
    0.34
    忘
    0.33
    Act Density 0.081%

    No Known Activations