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

    Neuronpedia

    INDEX
    Explanations

    references to global concepts or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noDo
    -0.47
     MenuView
    -0.47
     parms
    -0.41
     Ay
    -0.40
    Literatuur
    -0.40
    teeth
    -0.39
     TestCase
    -0.38
    structors
    -0.38
     Utilizamos
    -0.38
     Pee
    -0.38
    POSITIVE LOGITS
    Global
    1.02
     global
    0.99
     Global
    0.98
    global
    0.98
     GLOBAL
    0.91
    GLOBAL
    0.91
    lobal
    0.84
     Glob
    0.81
     globe
    0.76
     globales
    0.75
    Act Density 0.060%

    No Known Activations