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

    Neuronpedia

    INDEX
    Explanations

    terms related to formal documents and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nation
    -0.17
    iens
    -0.16
     nation
    -0.15
    Nation
    -0.15
    ROTO
    -0.15
    INY
    -0.14
    esk
    -0.14
     Econom
    -0.14
    alse
    -0.14
    IMA
    -0.14
    POSITIVE LOGITS
     WORLD
    0.19
    /world
    0.17
    World
    0.17
     World
    0.17
    world
    0.17
     world
    0.17
    orz
    0.16
    idor
    0.16
    tra
    0.15
    rsa
    0.15
    Act Density 0.030%

    No Known Activations