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

    Neuronpedia

    INDEX
    Explanations

    terms related to stability and performance metrics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.64
     Италијани
    -0.57
     виправивши
    -0.52
    Ath
    -0.51
    AndPassword
    -0.47
    pandas
    -0.47
     Beads
    -0.46
     pand
    -0.46
    anglès
    -0.45
    tdessen
    -0.45
    POSITIVE LOGITS
    unstable
    1.04
     Stable
    1.00
     stabilis
    0.97
     stabilization
    0.96
     Stabili
    0.94
     Stabilization
    0.94
    Stable
    0.93
     stabilité
    0.91
     Stab
    0.91
     stabilisation
    0.90
    Act Density 0.096%

    No Known Activations