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

    Neuronpedia

    INDEX
    Explanations

    terms related to collaboration and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /do
    -0.16
    estar
    -0.16
    aring
    -0.16
    engin
    -0.15
    earer
    -0.15
    erton
    -0.15
    furt
    -0.15
    sz
    -0.15
    quer
    -0.15
    erness
    -0.15
    POSITIVE LOGITS
    hips
    0.31
    ships
    0.21
    ing
    0.20
    SHIP
    0.20
    uche
    0.19
    able
    0.18
    /client
    0.18
    hood
    0.18
    ings
    0.18
    hip
    0.18
    Act Density 0.032%

    No Known Activations