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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and related variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asiun
    -0.48
    binaan
    -0.46
    дакти
    -0.46
    nologue
    -0.45
     Accesat
    -0.42
     = 
    -0.41
    /$
    -0.41
     Schloß
    -0.41
     Superior
    -0.41
    bukkit
    -0.40
    POSITIVE LOGITS
     omega
    0.94
     rho
    0.92
     Omega
    0.86
     beta
    0.85
    omega
    0.85
     sigma
    0.84
    rho
    0.83
     phi
    0.83
    beta
    0.81
    tau
    0.81
    Act Density 1.555%

    No Known Activations