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

    Neuronpedia

    INDEX
    Explanations

    references to characters and their actions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     welcoming
    -0.17
    ospace
    -0.16
    utin
    -0.16
     زÙĨدÙĩ
    -0.14
     Summon
    -0.14
    åı¬
    -0.14
     Jarvis
    -0.14
    REEN
    -0.14
    habi
    -0.14
    lices
    -0.14
    POSITIVE LOGITS
     arrival
    0.30
     visiting
    0.28
     arrives
    0.28
     visit
    0.28
     arrive
    0.27
     arrived
    0.27
     arriving
    0.26
     arrivals
    0.25
     visits
    0.24
    visit
    0.22
    Act Density 0.294%

    No Known Activations