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

    Neuronpedia

    INDEX
    Explanations

    references to various types of tools and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ally
    -0.18
    untime
    -0.18
    aldi
    -0.16
    fy
    -0.15
    ëľ
    -0.15
    jug
    -0.15
    uzzi
    -0.15
    emd
    -0.15
    bons
    -0.15
    ned
    -0.15
    POSITIVE LOGITS
    kits
    0.17
    chain
    0.16
    fully
    0.16
    shed
    0.15
    bars
    0.15
    set
    0.15
    266
    0.15
    244
    0.15
    sets
    0.15
    stock
    0.15
    Act Density 0.036%

    No Known Activations