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

    Neuronpedia

    INDEX
    Explanations

    websites and URLs

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Imperium
    -1.03
     Ammo
    -1.01
    arantine
    -1.00
     mate
    -0.94
     creep
    -0.94
     Panzer
    -0.93
    theless
    -0.93
     wards
    -0.93
     aggro
    -0.93
     Fighter
    -0.89
    POSITIVE LOGITS
    etc
    1.50
    Accessory
    1.50
    index
    1.45
    photos
    1.45
    comments
    1.43
    products
    1.40
    icons
    1.37
    pol
    1.37
    sites
    1.36
    dq
    1.35
    Act Density 0.376%

    No Known Activations