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

    Neuronpedia

    INDEX
    Explanations

    mentions of people's professions or affiliations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    words
    -0.68
    packs
    -0.66
    kids
    -0.65
    bugs
    -0.65
    mares
    -0.64
    attacks
    -0.64
    fixes
    -0.63
    Attack
    -0.61
    anism
    -0.61
    girls
    -0.60
    POSITIVE LOGITS
     member
    1.38
     fixture
    1.16
     contributor
    1.13
     participant
    1.12
     supporter
    1.12
     frequent
    1.08
     trustee
    1.08
     prominent
    1.05
     proponent
    1.01
     believer
    1.00
    Act Density 0.169%

    No Known Activations