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

    Neuronpedia

    INDEX
    Explanations

    words related to extracting or extraction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "extract" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nd
    -0.80
    early
    -0.80
    Die
    -0.73
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.72
    cas
    -0.67
    die
    -0.65
     Gry
    -0.62
    âĤ¬
    -0.61
    nder
    -0.60
    rien
    -0.60
    POSITIVE LOGITS
     extract
    1.18
     Extract
    1.01
    ions
    0.98
     extracts
    0.96
    ivist
    0.94
     extracted
    0.93
    anol
    0.90
     extracting
    0.88
     extraction
    0.84
    ract
    0.82
    Act Density 0.006%

    No Known Activations