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

    Neuronpedia

    INDEX
    Explanations

    important descriptors and indicators of significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ApplicationTests
    -0.92
     Efq
    -0.88
     intptr
    -0.88
    évaluateur
    -0.83
     Jefus
    -0.82
    tvguidetime
    -0.81
     Roskov
    -0.80
     الرياضيه
    -0.78
    queryInterface
    -0.73
     perfons
    -0.70
    POSITIVE LOGITS
      
    0.49
     ("
    0.47
     (
    0.45
     (“
    0.45
    Continue
    0.45
    ↵
    0.44
    (!)
    0.43
    (?)
    0.43
    /
    0.42
     rather
    0.42
    Act Density 0.946%

    No Known Activations