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

    Neuronpedia

    INDEX
    Explanations

    references to opposing sides or parties in a discussion or argument

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooth
    -0.16
    ilig
    -0.15
    ErrorException
    -0.15
    582
    -0.15
    ucch
    -0.15
    çŃĭ
    -0.14
     traction
    -0.14
    ัà¸Ķส
    -0.14
    unas
    -0.14
    indr
    -0.14
    POSITIVE LOGITS
     coin
    0.42
     aisle
    0.37
    coin
    0.34
     equation
    0.31
     Coin
    0.31
     fence
    0.29
     coins
    0.28
     divide
    0.28
    Coin
    0.28
     ledger
    0.25
    Act Density 0.028%

    No Known Activations