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

    Neuronpedia

    INDEX
    Explanations

    discussions about trade-offs and exchanges in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cahill
    -0.83
     Италијани
    -0.83
     Felton
    -0.82
     verily
    -0.82
    полнитель
    -0.79
    %;">
    -0.78
     psychiatrists
    -0.78
     Velasco
    -0.77
     Punct
    -0.77
     Senna
    -0.74
    POSITIVE LOGITS
     trade
    1.73
     Trade
    1.56
     trades
    1.55
    trade
    1.53
     traded
    1.52
    Trade
    1.51
     TRADE
    1.50
    TRADE
    1.47
     trading
    1.41
     Trades
    1.32
    Act Density 0.057%

    No Known Activations