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

    Neuronpedia

    INDEX
    Explanations

    references to personal development and self-improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hell
    -0.14
    alen
    -0.14
    vard
    -0.14
     åľŁ
    -0.13
     Hayward
    -0.13
     ima
    -0.13
    cord
    -0.13
    marker
    -0.13
    üz
    -0.13
     supplementation
    -0.13
    POSITIVE LOGITS
     ourselves
    0.40
     abych
    0.21
    chg
    0.18
    Ñħодим
    0.18
    аем
    0.15
    angep
    0.15
    ï¼ĮæĪij们
    0.15
     Chapman
    0.15
    ours
    0.15
    Ú¯ÛĮ
    0.15
    Act Density 0.398%

    No Known Activations