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

    Neuronpedia

    INDEX
    Explanations

    performative actions or tasks that involve a level of personal engagement and moral judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     StringVar
    -0.58
    availability
    -0.56
    readFileSync
    -0.55
     ingrat
    -0.54
     receb
    -0.51
     isShow
    -0.50
    newBuilder
    -0.49
    شنایی
    -0.49
    Appellee
    -0.49
    InputBorder
    -0.48
    POSITIVE LOGITS
     performed
    1.27
     done
    1.25
    performed
    1.05
     perform
    1.05
     executed
    1.03
     Performed
    1.01
    Doing
    1.00
     execute
    1.00
    done
    1.00
     undertaken
    1.00
    Act Density 0.566%

    No Known Activations