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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expectations and predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aislado
    -0.44
     aislada
    -0.42
     privada
    -0.41
     individuales
    -0.40
    nier
    -0.39
    <bos>
    -0.39
     Swartz
    -0.38
     aisladas
    -0.37
     Otras
    -0.36
     Waterman
    -0.36
    POSITIVE LOGITS
     Expect
    1.63
     expect
    1.63
    expect
    1.55
     EXPECT
    1.55
     expected
    1.54
    Expect
    1.53
     expectation
    1.49
     Expected
    1.46
    expected
    1.41
     Expectation
    1.38
    Act Density 0.204%

    No Known Activations