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

    Neuronpedia

    INDEX
    Explanations

    phrases related to autonomy and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antity
    -0.17
    DataExchange
    -0.16
    imap
    -0.15
    HeaderCode
    -0.15
    itational
    -0.15
    ίο
    -0.15
    lds
    -0.14
    .framework
    -0.14
    Debe
    -0.14
    braco
    -0.14
    POSITIVE LOGITS
     discretion
    0.34
     vol
    0.30
     convenience
    0.30
     liking
    0.29
     sole
    0.29
     pleasure
    0.28
     initiative
    0.26
     benefit
    0.26
     choosing
    0.25
     direction
    0.25
    Act Density 0.139%

    No Known Activations