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

    Neuronpedia

    INDEX
    Explanations

    references to annotation-related terms in the text

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

    annotation information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    -0.45
     Económica
    -0.43
    s
    -0.42
    <bos>
    -0.41
    i
    -0.41
    Left
    -0.39
    getC
    -0.39
    Wes
    -0.39
    Tcp
    -0.39
    <h3>
    -0.38
    POSITIVE LOGITS
     annotation
    1.77
     Annotation
    1.71
    annotation
    1.66
     annotations
    1.45
    Annotation
    1.39
     annot
    1.34
    annotations
    1.14
     annotated
    1.13
    Annotations
    1.09
    Annot
    1.08
    Act Density 0.004%

    No Known Activations