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

    Neuronpedia

    INDEX
    Explanations

    content related to formal statements and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.82
    cstdlib
    -0.73
     recevrez
    -0.66
    ])):
    -0.65
    archiviato
    -0.65
    𝘅
    -0.64
    lenül
    -0.63
    -0.62
     doPost
    -0.62
    principalColumn
    -0.61
    POSITIVE LOGITS
     statement
    2.53
     statements
    2.42
     Statement
    2.35
     Statements
    2.27
    statement
    2.20
     STATEMENT
    2.17
    statements
    2.14
    Statement
    2.05
     STATEMENTS
    2.00
    Statements
    1.96
    Act Density 0.098%

    No Known Activations