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

    Neuronpedia

    INDEX
    Explanations

    references to individuals in positions of authority or influence within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ«ãĤ¯
    -0.15
    afone
    -0.14
    omite
    -0.13
    èn
    -0.13
    -prepend
    -0.13
    ores
    -0.13
    çļĨ
    -0.13
    едак
    -0.13
    erties
    -0.13
    åĽ
    -0.13
    POSITIVE LOGITS
     talks
    0.38
     shares
    0.36
     discusses
    0.35
     share
    0.34
     discuss
    0.34
     chats
    0.34
     reflects
    0.31
     talk
    0.30
    talk
    0.30
     dishes
    0.29
    Act Density 0.113%

    No Known Activations