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

    Neuronpedia

    INDEX
    Explanations

    language that conveys strength and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anga
    -0.15
    Sensitive
    -0.14
     universe
    -0.14
     kli
    -0.14
    鬼
    -0.14
     Yap
    -0.14
    afka
    -0.13
    ardon
    -0.13
     Wich
    -0.13
     $?
    -0.13
    POSITIVE LOGITS
     Overwatch
    0.16
    Ä©
    0.16
     council
    0.15
     âĸĪâĸĪâĸĪâĸĪâĸĪ
    0.14
     vitae
    0.14
     XD
    0.14
    Council
    0.14
     NPCs
    0.14
     histories
    0.13
    Åį
    0.13
    Act Density 1.054%

    No Known Activations