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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authority and control over institutions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     modalités
    -0.56
     سكانية
    -0.56
     ulike
    -0.53
    ngOn
    -0.50
    masing
    -0.50
     particulières
    -0.49
    Према
    -0.49
     besonderer
    -0.48
     marquées
    -0.48
    fromnode
    -0.48
    POSITIVE LOGITS
    好不容易
    1.10
    せっかく
    1.05
     valuable
    0.91
     innocent
    0.90
     legitimate
    0.84
    本来
    0.80
     vital
    0.79
    大事な
    0.78
     precious
    0.76
     wichtige
    0.75
    Act Density 0.727%

    No Known Activations