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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or contrasts between expectations and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alse
    -0.15
    گر
    -0.15
    emek
    -0.15
    buz
    -0.15
    .Parcel
    -0.14
    alon
    -0.14
    QualifiedName
    -0.14
    yor
    -0.13
    kazy
    -0.13
    ismet
    -0.13
    POSITIVE LOGITS
     expected
    0.45
     expectations
    0.39
    expected
    0.38
     Expected
    0.36
     expectation
    0.36
    Expected
    0.34
     Expect
    0.33
     EXPECT
    0.32
     anticipated
    0.31
     expecting
    0.30
    Act Density 0.121%

    No Known Activations