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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "express" and its variants, indicating a focus on communication or formal declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vip
    -0.16
     wh
    -0.15
    acre
    -0.15
    awah
    -0.15
    uteur
    -0.15
     other
    -0.15
    aktu
    -0.15
    ίκ
    -0.15
    ètre
    -0.15
     exempt
    -0.15
    POSITIVE LOGITS
    mond
    0.15
    iena
    0.15
    iegel
    0.15
    orado
    0.14
    ynos
    0.14
    ance
    0.14
    nest
    0.14
    ively
    0.14
    EDA
    0.14
    430
    0.14
    Act Density 0.031%

    No Known Activations