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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to machinery or equipment, particularly those related to environmental research, aircraft, and fermentation processes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    emonium
    -0.89
    ority
    -0.89
    aurus
    -0.85
    awaru
    -0.79
    aepernick
    -0.78
    utterstock
    -0.76
    CVE
    -0.75
    allery
    -0.75
    auri
    -0.74
    raltar
    -0.74
    POSITIVE LOGITS
    wall
    1.03
    ness
    0.93
    burn
    0.83
    den
    0.82
    cloth
    0.80
     cleaner
    0.80
     cleaners
    0.79
    stal
    0.78
    wallet
    0.77
     erase
    0.76
    Act Density 8.705%

    No Known Activations