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

    Neuronpedia

    INDEX
    Explanations

    organizations or entities related to think tanks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to think tanks and organizations that influence policy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptoms
    -0.64
    VID
    -0.64
     Winds
    -0.63
     Shades
    -0.62
     Ago
    -0.62
     Sever
    -0.61
    FIX
    -0.61
     Rid
    -0.60
     Isles
    -0.60
     Novel
    -0.60
    POSITIVE LOGITS
    arian
    1.17
    arians
    1.16
    alyst
    0.90
    ucker
    0.88
    isphere
    0.84
    ivist
    0.83
    iness
    0.80
    arios
    0.79
    aly
    0.77
    krit
    0.77
    Act Density 0.036%

    No Known Activations