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

    Neuronpedia

    INDEX
    Explanations

    words that express positive sentiments or reviews about experiences and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansson
    -0.15
    reten
    -0.15
     trú
    -0.15
    apture
    -0.14
    rez
    -0.14
    ìŀIJìĿ¸
    -0.14
    anzi
    -0.14
    ény
    -0.14
    zell
    -0.14
    overn
    -0.14
    POSITIVE LOGITS
    iar
    0.17
    ÏĦÏģι
    0.15
    лей
    0.14
     ÎłÎ¿
    0.14
    ocop
    0.14
     Fat
    0.14
    ëĭ´
    0.14
    ÏĢιÏĥ
    0.14
    isco
    0.14
    ape
    0.14
    Act Density 0.196%

    No Known Activations