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

    Neuronpedia

    INDEX
    Explanations

    string literals or values associated with message strings in code or user interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FailureListener
    -0.74
    sizeCache
    -0.64
    oredCriteria
    -0.64
    Rohy
    -0.64
    gatsby
    -0.62
    gnore
    -0.61
    ########.
    -0.61
    windowFixed
    -0.59
     Ritchie
    -0.59
     OFDb
    -0.58
    POSITIVE LOGITS
    translation
    1.96
     translation
    1.04
     Translation
    0.95
    Translation
    0.94
     translations
    0.83
    TRANSL
    0.79
    numerusform
    0.75
     TRANSLATION
    0.74
     الاطلاع
    0.72
    translated
    0.69
    Act Density 0.006%

    No Known Activations