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

    Neuronpedia

    INDEX
    Explanations

    references to the term "lean" or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     onBackPressed
    -0.65
     мәкал
    -0.63
    transmission
    -0.61
    ArgumentParser
    -0.61
    ornada
    -0.58
     công
    -0.57
    verifyException
    -0.57
     CURIAM
    -0.56
    UserScript
    -0.55
     Jornada
    -0.54
    POSITIVE LOGITS
     lean
    1.00
     Lean
    0.97
    Lean
    0.85
     ABC
    0.85
     drain
    0.82
    ABC
    0.78
     leans
    0.78
     drained
    0.75
    lean
    0.75
    fmt
    0.74
    Act Density 0.060%

    No Known Activations