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

    Neuronpedia

    INDEX
    Explanations

    elements related to social and economic structures and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andest
    -0.17
    uco
    -0.15
     #
    -0.15
     här
    -0.15
     Entertainment
    -0.15
    elez
    -0.15
     below
    -0.15
     Industry
    -0.14
    finalize
    -0.14
     fandom
    -0.14
    POSITIVE LOGITS
     essentially
    0.21
     task
    0.20
     sources
    0.19
     tasks
    0.19
     twin
    0.18
     mains
    0.18
     basically
    0.17
     forces
    0.17
     sweep
    0.17
     basic
    0.17
    Act Density 0.371%

    No Known Activations