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

    Neuronpedia

    INDEX
    Explanations

    references to specific missions or mission statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shelf
    -0.15
    adian
    -0.15
    action
    -0.15
    elier
    -0.15
    ude
    -0.14
    sed
    -0.14
     cautious
    -0.14
    itus
    -0.14
    961
    -0.14
    lee
    -0.14
    POSITIVE LOGITS
    aries
    0.32
     statement
    0.28
    ary
    0.28
     statements
    0.25
     Statement
    0.25
    naires
    0.25
    naire
    0.24
     accomplished
    0.23
     Impossible
    0.23
    statement
    0.22
    Act Density 0.014%

    No Known Activations