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

    Neuronpedia

    INDEX
    Explanations

    acronyms and their definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <=",
    -0.60
    TargetException
    -0.56
    CppCodeGen
    -0.56
     CCPA
    -0.56
     remoto
    -0.56
    SFD
    -0.56
    estay
    -0.55
     wetter
    -0.54
    ))*
    -0.54
     flavoured
    -0.54
    POSITIVE LOGITS
     abbreviation
    0.96
     acronym
    0.90
     abbreviations
    0.80
     abbre
    0.77
    abbreviation
    0.76
    Abbreviation
    0.73
     acronyms
    0.66
     initials
    0.66
     ABBREVIATIONS
    0.63
     abbreviated
    0.62
    Act Density 0.274%

    No Known Activations