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

    Neuronpedia

    INDEX
    Explanations

    the concept of uniformity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     setw
    -0.61
     dimentic
    -0.61
    łek
    -0.56
    Substring
    -0.56
     iVar
    -0.56
     Hedges
    -0.56
     kolye
    -0.55
    CppMethod
    -0.55
     tvb
    -0.55
     Amendment
    -0.54
    POSITIVE LOGITS
     friendly
    0.84
     compression
    0.73
    UrlResolution
    0.71
     uniform
    0.70
    PROOF
    0.68
    ]))
    0.66
    proof
    0.66
     unified
    0.65
    uniform
    0.65
     disambiguazione
    0.65
    Act Density 0.110%

    No Known Activations