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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.82
    windowFixed
    -0.65
     avoient
    -0.64
    SharedCtor
    -0.59
    GEBURTSDATUM
    -0.56
    enumii
    -0.55
    RegressionTest
    -0.55
     säll
    -0.54
     AssemblyVersion
    -0.54
    :✨
    -0.54
    POSITIVE LOGITS
    Delta
    0.54
    alpha
    0.51
    mu
    0.49
    nu
    0.49
    sum
    0.48
    beta
    0.48
    chi
    0.47
    tau
    0.47
    pi
    0.47
    bar
    0.46
    Act Density 1.513%

    No Known Activations