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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations or institutions

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

    Chambers, Sparks, Waters, Tonga, Townsend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    queryInterface
    -0.56
    adaptiveStyles
    -0.54
    guenos
    -0.54
     poème
    -0.53
     Erhaltung
    -0.49
    addCriterion
    -0.47
     kyse
    -0.47
     ModelExpression
    -0.47
     delà
    -0.47
     Aufführung
    -0.47
    POSITIVE LOGITS
     Chambers
    1.16
     Tong
    1.11
    Chambers
    1.01
    Tong
    0.94
     Townsend
    0.88
     Sparks
    0.87
     Waters
    0.82
     tong
    0.75
     Ramos
    0.74
    Sparks
    0.74
    Act Density 0.006%

    No Known Activations