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

    Neuronpedia

    INDEX
    Explanations

    content that critiques societal issues and injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nors
    -0.15
    irit
    -0.13
     Beled
    -0.13
     Uint
    -0.13
     kariy
    -0.12
     aktivit
    -0.12
     Aura
    -0.12
    icorn
    -0.11
     nebu
    -0.11
     Famil
    -0.11
    POSITIVE LOGITS
     history
    0.26
     America
    0.25
     capitalism
    0.24
     Hitler
    0.24
     fascism
    0.24
     Adolf
    0.22
     communism
    0.22
     Roosevelt
    0.22
     Eisenhower
    0.21
     Stalin
    0.21
    Act Density 1.368%

    No Known Activations