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

    Neuronpedia

    INDEX
    Explanations

    frequent pronouns and verbs indicative of personal perspectives or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    
    -0.57
    eleste
    -0.55
     spagnolo
    -0.50
    。"
    -0.49
    "';
    -0.49
    Vidite
    -0.49
    ✷
    -0.49
     morreu
    -0.49
    {§
    -0.49
    ...?"
    -0.48
    POSITIVE LOGITS
    المناصب
    0.75
    Encyklopedia
    0.72
     utafitiHapana
    0.71
     snippetHide
    0.62
    Personensuche
    0.58
    يتر
    0.58
    ագրություններ
    0.57
     تانيه
    0.57
     createState
    0.56
    市镇
    0.56
    Act Density 0.417%

    No Known Activations