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

    Neuronpedia

    INDEX
    Explanations

    references to specific missions or goals related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ture
    -0.15
    elier
    -0.15
    asan
    -0.14
    asmus
    -0.14
    amac
    -0.14
    icts
    -0.14
    shan
    -0.14
    ãĤ¤ãĤ¯
    -0.14
    /list
    -0.14
    ided
    -0.14
    POSITIVE LOGITS
    naire
    0.23
    erchant
    0.18
    aries
    0.18
    ingu
    0.18
    avicon
    0.17
    atic
    0.17
    naires
    0.16
    omez
    0.15
    nal
    0.15
    .Charting
    0.14
    Act Density 0.026%

    No Known Activations