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

    Neuronpedia

    INDEX
    Explanations

    phrases referencing legal statements and their evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.93
    ])):
    -0.86
     ?>">
    -0.80
    didSet
    -0.78
    archiviato
    -0.76
    lenül
    -0.73
    cstdlib
    -0.73
    -0.71
    𝘅
    -0.71
     LEYENDO
    -0.70
    POSITIVE LOGITS
     statement
    1.96
     statements
    1.93
     Statement
    1.80
     Statements
    1.77
    statement
    1.72
     STATEMENT
    1.66
    statements
    1.64
    Statement
    1.64
    Statements
    1.54
    STATEMENT
    1.54
    Act Density 0.121%

    No Known Activations