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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "left" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipple
    -0.18
    utes
    -0.16
    interest
    -0.16
    theast
    -0.15
    agi
    -0.15
    бÑĢа
    -0.15
    ptive
    -0.15
    ixed
    -0.14
    rist
    -0.14
    olean
    -0.14
    POSITIVE LOGITS
    wing
    0.16
    -wing
    0.16
    ustain
    0.16
    jen
    0.15
    ë²Ķ
    0.15
    tings
    0.15
    mann
    0.14
    enschaft
    0.14
     stick
    0.14
    987
    0.14
    Act Density 0.032%

    No Known Activations