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

    Neuronpedia

    INDEX
    Explanations

    technical terms and variables related to data structures and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ness
    -1.10
    n
    -1.07
    d
    -0.93
    s
    -0.82
    r
    -0.81
    nya
    -0.73
    н
    -0.72
     Révolution
    -0.71
    ship
    -0.70
    م
    -0.68
    POSITIVE LOGITS
     CME
    1.18
     CIE
    1.16
     SSE
    1.08
     SCE
    1.07
    ede
    1.06
     ORE
    1.05
     CTE
    1.05
     ATE
    1.05
     Euse
    1.02
    PIE
    1.02
    Act Density 2.903%

    No Known Activations