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

    Neuronpedia

    INDEX
    Explanations

    references to different contexts or types of environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    environment and environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     getLast
    -0.57
     getCustomer
    -0.56
     Cientí
    -0.54
     Palgrave
    -0.49
     noDo
    -0.48
    MessageOf
    -0.48
     getPlayer
    -0.48
    Katso
    -0.48
    GEBURTSDATUM
    -0.48
     queſta
    -0.47
    POSITIVE LOGITS
     environment
    1.11
     environments
    0.94
    environment
    0.92
     Environments
    0.91
     ENVIRONMENT
    0.88
     Environment
    0.86
     ambiente
    0.83
     prostředí
    0.83
    Environment
    0.82
    vironment
    0.80
    Act Density 0.014%

    No Known Activations