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

    Neuronpedia

    INDEX
    Explanations

    references to entities and types in a framework or data model

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isSuccessful
    -0.93
    __(/*!
    -0.93
     Fros
    -0.90
     JAS
    -0.90
     Koen
    -0.88
     <<-
    -0.86
    termilk
    -0.86
     Shakspeare
    -0.86
     ſever
    -0.85
     OkHttpClient
    -0.85
    POSITIVE LOGITS
     entity
    1.83
    entity
    1.72
    entities
    1.70
     entities
    1.68
     Entity
    1.65
     Entities
    1.65
    ENTITY
    1.59
     ENTITY
    1.56
    Entity
    1.51
    Entities
    1.50
    Act Density 0.075%

    No Known Activations