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

    Neuronpedia

    INDEX
    Explanations

    the word "extract" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "extract" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndra
    -0.77
    nd
    -0.77
    Die
    -0.73
    gaard
    -0.69
    die
    -0.68
    stand
    -0.64
    osuke
    -0.64
    ned
    -0.62
    nder
    -0.61
    present
    -0.61
    POSITIVE LOGITS
     extract
    0.99
    ions
    0.93
     extracting
    0.91
     extracted
    0.91
     extraction
    0.87
    ract
    0.87
    ngth
    0.86
    urized
    0.86
    ivist
    0.85
     extracts
    0.85
    Act Density 0.010%

    No Known Activations