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

    Neuronpedia

    INDEX
    Explanations

    instances of parentheses and curly brackets in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TestingModule
    -1.11
    LookAnd
    -1.06
    MLLoader
    -1.02
     ModelExpression
    -0.99
     GenerationType
    -0.96
    IntoConstraints
    -0.92
     ostavi
    -0.89
    HtmlAttribute
    -0.88
    SuccessListener
    -0.88
    ThroughAttribute
    -0.87
    POSITIVE LOGITS
    ,
    0.49
    beginTransaction
    0.49
    áñez
    0.47
     her
    0.46
     non
    0.45
     pprint
    0.44
     huid
    0.43
     hack
    0.43
    tiz
    0.43
    izados
    0.41
    Act Density 0.039%

    No Known Activations