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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "extract."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fontaine
    -0.78
     Gifford
    -0.76
    مصادر
    -0.74
    Alonso
    -0.70
    gapi
    -0.69
    AppRoutingModule
    -0.69
    mpto
    -0.69
    jupiter
    -0.66
    modelBuilder
    -0.65
    hoea
    -0.63
    POSITIVE LOGITS
     extract
    2.61
     extracts
    2.52
     Extract
    2.45
     extracted
    2.35
    Extract
    2.32
    extract
    2.27
     Extracts
    2.26
     extraction
    2.26
     extracting
    2.21
     EXTRACT
    2.15
    Act Density 0.183%

    No Known Activations