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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential classification or evaluation of subjects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.01
     EconPapers
    -0.92
    bootstrapcdn
    -0.88
     houſe
    -0.84
     fubject
    -0.84
     purpoſe
    -0.84
     Houſe
    -0.81
     Shakspeare
    -0.81
    TestingModule
    -0.80
     Chriftian
    -0.79
    POSITIVE LOGITS
     sayfası
    0.46
    lean
    0.44
     em
    0.44
     typelib
    0.41
    роль
    0.41
    ":
    0.40
    Tradu
    0.40
    vensko
    0.39
     tr
    0.39
    াক
    0.38
    Act Density 0.472%

    No Known Activations