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

    Neuronpedia

    INDEX
    Explanations

    certain conjunctions and relational phrases that indicate connections or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.56
    tanleria
    -0.53
    randi
    -0.52
    redients
    -0.50
     vies
    -0.50
    Clipboard
    -0.49
    הערות
    -0.49
    indre
    -0.48
     مشارکت‌کنندگان
    -0.48
     débit
    -0.48
    POSITIVE LOGITS
     because
    0.41
     puisqu
    0.40
     courtesy
    0.39
     thanks
    0.37
    {}'.
    0.35
     parteci
    0.34
     благодаря
    0.34
     omdat
    0.33
     soon
    0.33
     palha
    0.33
    Act Density 0.045%

    No Known Activations