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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expectations and standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Портал
    -0.45
    ngulo
    -0.42
    }}{(
    -0.42
    Reducer
    -0.41
     aastal
    -0.41
     lauter
    -0.41
    )}{(
    -0.40
     situation
    -0.40
     stupid
    -0.40
     here
    -0.40
    POSITIVE LOGITS
     EXPECT
    0.85
     expectation
    0.84
     expected
    0.83
     expectations
    0.82
    expected
    0.82
     expect
    0.79
     expects
    0.76
     Expected
    0.75
     krä
    0.75
    Expect
    0.72
    Act Density 0.265%

    No Known Activations