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

    Neuronpedia

    INDEX
    Explanations

    themes related to self-improvement and social validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iw
    -0.15
    alta
    -0.14
    YLES
    -0.14
     Kam
    -0.14
    quest
    -0.14
    ÙĪØ«
    -0.14
     Chatt
    -0.14
    ÑĤон
    -0.13
    amon
    -0.13
    çĻº
    -0.13
    POSITIVE LOGITS
    icho
    0.17
    εξ
    0.16
    oha
    0.15
    èĨľ
    0.15
    erchant
    0.14
    è¯Ŀ
    0.14
    agini
    0.14
    aso
    0.14
    ernes
    0.14
    .ObjectModel
    0.14
    Act Density 0.305%

    No Known Activations