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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with betrayal and support dynamics within social groups

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

    competition and backstabbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dư
    -0.40
    NUMX
    -0.40
    postmedia
    -0.39
     AttributeSet
    -0.38
     binding
    -0.37
     desembar
    -0.36
     Binding
    -0.36
     thừa
    -0.35
    ItemLayout
    -0.35
    setDuration
    -0.35
    POSITIVE LOGITS
    :✨
    0.56
     competitors
    0.50
    Rüyada
    0.46
     ModelExpression
    0.46
     competitor
    0.46
    Competi
    0.46
    üyada
    0.44
    competi
    0.43
     Competitors
    0.42
    Competition
    0.42
    Act Density 0.020%

    No Known Activations