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

    Neuronpedia

    INDEX
    Explanations

    references to tools or tool sets used for various applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eners
    -0.19
    ema
    -0.18
    icles
    -0.17
    ãĥ³ãĥĹ
    -0.16
    est
    -0.16
    bons
    -0.16
    oken
    -0.15
    wu
    -0.15
    apas
    -0.15
    貨
    -0.15
    POSITIVE LOGITS
    kits
    0.45
    chain
    0.35
    set
    0.34
    -kit
    0.32
    bars
    0.32
    kit
    0.31
     kit
    0.30
    boxes
    0.29
    KIT
    0.29
    chains
    0.28
    Act Density 0.027%

    No Known Activations