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

    Neuronpedia

    INDEX
    Explanations

    phrases related to control, manipulation, orientation, and physical properties of materials

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    moil
    -0.73
    nr
    -0.71
    nos
    -0.70
    Catalog
    -0.68
    displayText
    -0.67
    advertising
    -0.65
    Merit
    -0.65
    KK
    -0.65
    ength
    -0.64
    )].
    -0.64
    POSITIVE LOGITS
     each
    1.09
     incoming
    0.91
     these
    0.88
     atoms
    0.84
     those
    0.84
     our
    0.83
     the
    0.81
     planets
    0.80
     your
    0.80
     molecules
    0.80
    Act Density 0.164%

    No Known Activations