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

    Neuronpedia

    INDEX
    Explanations

    terms related to entities and their management in a framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.94
     ſever
    -0.92
    isSuccessful
    -0.92
     OkHttpClient
    -0.90
     <<-
    -0.90
    termilk
    -0.88
    BufferException
    -0.88
     Fros
    -0.86
     Koen
    -0.86
     fevere
    -0.86
    POSITIVE LOGITS
     entity
    2.04
    entity
    1.90
     entities
    1.89
    entities
    1.85
     Entities
    1.82
     Entity
    1.82
    ENTITY
    1.75
     ENTITY
    1.70
    Entities
    1.68
    Entity
    1.67
    Act Density 0.074%

    No Known Activations