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

    Neuronpedia

    INDEX
    Explanations

    references to underground settings or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    
    -0.56
    rungsseite
    -0.45
     umo
    -0.44
     honor
    -0.44
     outcome
    -0.44
     Ort
    -0.44
     AI
    -0.43
     equipped
    -0.42
     unit
    -0.42
    oslav
    -0.42
    POSITIVE LOGITS
     prisoners
    0.70
     prisoner
    0.64
     Prisoners
    0.61
     housed
    0.57
     BoxFit
    0.56
    ItemBackground
    0.56
     Prisoner
    0.56
     Powder
    0.56
     refugee
    0.56
     refugees
    0.55
    Act Density 0.252%

    No Known Activations