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

    Neuronpedia

    INDEX
    Explanations

    phrases and contexts related to extensive or detailed investigations, studies, or analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sworth
    -0.16
    ispers
    -0.16
    ILLISE
    -0.15
    asley
    -0.15
    agne
    -0.15
    ukkan
    -0.14
    utt
    -0.14
    heim
    -0.14
    216
    -0.14
    bie
    -0.14
    POSITIVE LOGITS
    amount
    0.22
     amount
    0.19
     amounts
    0.19
    ively
    0.19
    /ext
    0.17
    -reaching
    0.17
    ented
    0.16
     Amount
    0.15
     enough
    0.15
    evin
    0.15
    Act Density 0.024%

    No Known Activations