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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the origins or beginnings of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    origins of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.56
     Chriftian
    -0.52
     ſch
    -0.52
    copg
    -0.52
    nologue
    -0.50
    ngdoc
    -0.50
     suspen
    -0.48
     fubject
    -0.47
    ußt
    -0.47
     houſe
    -0.47
    POSITIVE LOGITS
    Origins
    1.59
     Origins
    1.57
     origins
    1.50
    origins
    1.45
     orígenes
    1.14
     beginnings
    1.13
     Beginnings
    1.02
     ORIG
    0.99
    roots
    0.87
     roots
    0.86
    Act Density 0.005%

    No Known Activations