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

    Neuronpedia

    INDEX
    Explanations

    references to engine-related topics in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entication
    -0.18
    peare
    -0.17
    pper
    -0.17
    ãĥªãĥ¼ãĤº
    -0.17
    ally
    -0.16
    rael
    -0.16
    izzle
    -0.15
    ppers
    -0.15
    rogen
    -0.14
     Krish
    -0.14
    POSITIVE LOGITS
    ered
    0.37
    ERING
    0.27
    ering
    0.23
    /trans
    0.19
    oil
    0.18
    less
    0.18
     compartment
    0.16
    Room
    0.16
    yard
    0.16
    eing
    0.16
    Act Density 0.021%

    No Known Activations