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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expectations or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expecting outcomes or results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WritableDatabase
    -0.43
     folhas
    -0.42
     Whitehead
    -0.40
     deputado
    -0.38
     ausges
    -0.38
     namorado
    -0.37
     mijne
    -0.37
     Investigaciones
    -0.37
     weißem
    -0.37
     belangrij
    -0.37
    POSITIVE LOGITS
     Expect
    0.92
     expect
    0.91
     expectations
    0.91
    Expect
    0.89
     Expectations
    0.85
     EXPECT
    0.84
    expectations
    0.79
    expect
    0.77
     expectation
    0.73
    Expectations
    0.72
    Act Density 0.003%

    No Known Activations