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

    Neuronpedia

    INDEX
    Explanations

    encoded symbols or characters that are not standard in typical text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eya
    -0.16
     naken
    -0.14
     Liberties
    -0.14
    boro
    -0.14
     invade
    -0.13
    åºŁ
    -0.13
    .preview
    -0.13
    éĹ²
    -0.13
     freedoms
    -0.12
    ãĤĵãģ¨
    -0.12
    POSITIVE LOGITS
     Swiss
    0.28
     luggage
    0.27
     baggage
    0.26
     Bag
    0.23
     Zurich
    0.23
     bag
    0.22
     bags
    0.22
    Lost
    0.22
     Bags
    0.21
    lost
    0.21
    Act Density 0.008%

    No Known Activations