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

    Neuronpedia

    INDEX
    Explanations

    markers of emphasis and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ressee
    -0.72
     sadly
    -0.68
    aczy
    -0.61
     sometimes
    -0.61
    mybatisplus
    -0.60
     désolés
    -0.59
     rospy
    -0.58
     vaguely
    -0.58
     unfortunately
    -0.58
    どうやら
    -0.57
    POSITIVE LOGITS
     advantages
    0.95
     Advantages
    0.88
    Utiliz
    0.82
     advantage
    0.81
    Преимущества
    0.79
     Using
    0.79
     Utilizing
    0.78
     Designed
    0.78
    Designed
    0.78
     Vorteile
    0.78
    Act Density 0.240%

    No Known Activations