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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing political dissent and social engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.17
    IsMutable
    -1.10
     оригіналу
    -1.07
    parsedMessage
    -1.07
    PerformLayout
    -1.07
    IsContent
    -1.01
    DoubleQuotes
    -0.97
    脚注の使い方
    -0.96
     متعلقه
    -0.94
     مشين
    -0.94
    POSITIVE LOGITS
     who
    0.76
     or
    0.63
    who
    0.59
      
    0.51
     whom
    0.48
    <eos>
    0.46
     and
    0.45
     themselves
    0.45
    ↵↵
    0.44
     et
    0.44
    Act Density 0.711%

    No Known Activations