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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing expectations or anticipations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bindParam
    -0.73
    ization
    -0.66
    uasaan
    -0.65
    extAlignment
    -0.64
    romycin
    -0.63
     Administ
    -0.63
     Administration
    -0.62
     Guna
    -0.62
    ணை
    -0.62
     Poitiers
    -0.61
    POSITIVE LOGITS
     expect
    2.97
     Expect
    2.94
    expect
    2.78
    Expect
    2.68
     expecting
    2.40
     expects
    2.30
     EXPECT
    2.07
    EXPECT
    1.77
     expectancy
    1.72
     expectation
    1.70
    Act Density 0.106%

    No Known Activations