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

    Neuronpedia

    INDEX
    Explanations

    references to significant changes or reforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spyOn
    -0.41
    cerol
    -0.40
    acamata
    -0.39
     playing
    -0.38
     Adler
    -0.38
    matmul
    -0.38
    iligt
    -0.38
    eder
    -0.37
    son
    -0.37
     instances
    -0.37
    POSITIVE LOGITS
     Changes
    1.32
     changes
    1.30
    Changes
    1.30
    changes
    1.28
     CHANGES
    1.20
     change
    1.20
    CHANGES
    1.13
     Change
    1.11
     changement
    1.09
     cambios
    1.08
    Act Density 0.459%

    No Known Activations