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

    Neuronpedia

    INDEX
    Explanations

    references to historical kingdoms and empires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Colon
    -0.15
     Bounty
    -0.14
    Circular
    -0.14
     colonial
    -0.14
    ariat
    -0.14
    apiro
    -0.13
    Colon
    -0.13
     TG
    -0.13
    quip
    -0.13
    ugas
    -0.13
    POSITIVE LOGITS
     tribute
    0.20
     rule
    0.19
     ruler
    0.18
     ruled
    0.18
     decline
    0.18
     raids
    0.17
     consolidation
    0.17
     founder
    0.17
     дина
    0.17
    tribute
    0.16
    Act Density 0.150%

    No Known Activations