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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating subjective opinions or personal reflections

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

    qualifying personal opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.56
    -0.52
    AddHtmlAttribute
    -0.48
    rungsseite
    -0.47
    VIAF
    -0.46
     שוליים
    -0.45
    UserScript
    -0.45
     inalámbrica
    -0.44
     terbaik
    -0.42
    Aholisi
    -0.42
    POSITIVE LOGITS
    ViewFeatures
    0.62
    ConfigureAwait
    0.44
     though
    0.43
    .
    0.42
    endphp
    0.39
    toHaveBeenCalled
    0.38
    though
    0.38
     صلى
    0.36
     Bay
    0.36
    eraard
    0.36
    Act Density 0.026%

    No Known Activations