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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data extraction processes

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

    "extract" or "extracted"

    np_acts-logits-general · gemini-2.0-flash

    extract and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſche
    -0.69
    LookAnd
    -0.64
    bleshooting
    -0.63
     geſ
    -0.62
    EndGlobalSection
    -0.62
     Majefty
    -0.60
    QMetaType
    -0.59
    ſelf
    -0.59
     pauv
    -0.59
    readystatechange
    -0.58
    POSITIVE LOGITS
     extract
    2.09
     extraction
    1.97
     extracted
    1.94
    extract
    1.94
     Extract
    1.91
    Extract
    1.87
     extracting
    1.79
     Extraction
    1.77
    extracted
    1.73
     extracts
    1.73
    Act Density 0.234%

    No Known Activations