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

    Neuronpedia

    INDEX
    Explanations

    references to changes or modifications in systems or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ảo
    -0.14
    erra
    -0.14
     pseud
    -0.14
     decomposition
    -0.14
    .measure
    -0.14
    ç¸
    -0.14
    _mapped
    -0.13
    inic
    -0.13
    _extensions
    -0.13
     mand
    -0.13
    POSITIVE LOGITS
     structure
    0.23
     rules
    0.20
     Structure
    0.19
    structure
    0.19
    estruct
    0.18
     policies
    0.18
    rules
    0.17
     way
    0.17
     handling
    0.16
    Structure
    0.16
    Act Density 0.141%

    No Known Activations