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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "We" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĢij
    -0.18
    bÃŃ
    -0.17
    lights
    -0.16
    rim
    -0.16
    ứ
    -0.15
    iaux
    -0.15
    ãĥ³ãĤ¸
    -0.14
     Lawn
    -0.14
    oub
    -0.14
    locate
    -0.14
    POSITIVE LOGITS
    avers
    0.18
    arehouse
    0.18
    ilder
    0.18
    imar
    0.17
    asley
    0.17
    bsp
    0.17
    evil
    0.16
    aire
    0.16
    ble
    0.16
     Energ
    0.16
    Act Density 0.055%

    No Known Activations