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

    Neuronpedia

    INDEX
    Explanations

    terms related to revolutionary ideologies and critiques of capitalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     policy
    -0.49
    ToAdd
    -0.48
     compliance
    -0.47
    ToCheck
    -0.47
     annoy
    -0.46
    diplom
    -0.46
    compliance
    -0.46
     
    -0.46
     spend
    -0.45
    Compliance
    -0.44
    POSITIVE LOGITS
    ագրություններ
    0.86
    Хьажоргаш
    0.86
    
    0.83
     esternos
    0.82
     للمعارف
    0.80
    ArgsConstructor
    0.80
     فريبيس
    0.80
    EDEFAULT
    0.79
     InputDecoration
    0.78
    setVerticalGroup
    0.78
    Act Density 0.382%

    No Known Activations