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

    Neuronpedia

    INDEX
    Explanations

    references to tools and their applicability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icles
    -0.18
    icle
    -0.17
    ois
    -0.16
    貨
    -0.16
    est
    -0.16
    eners
    -0.16
    bons
    -0.15
    ester
    -0.15
    ety
    -0.15
    ãĥ³ãĥĹ
    -0.15
    POSITIVE LOGITS
    kits
    0.38
    chain
    0.32
    bars
    0.31
    chains
    0.27
    set
    0.26
     kit
    0.24
    shed
    0.24
    chest
    0.24
    -kit
    0.24
    belt
    0.23
    Act Density 0.028%

    No Known Activations