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

    Neuronpedia

    INDEX
    Explanations

    phrases or contexts indicating relationships between concepts, particularly involving the word "in"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hitch
    -0.15
    yn
    -0.15
    wart
    -0.14
    iegel
    -0.14
    den
    -0.14
    itch
    -0.14
     parch
    -0.13
    assel
    -0.13
    CE
    -0.13
     bunch
    -0.13
    POSITIVE LOGITS
     which
    0.26
    which
    0.23
     który
    0.18
     które
    0.18
     cui
    0.18
    .openConnection
    0.17
    Which
    0.17
     οÏĢοίο
    0.17
     οÏĢοία
    0.17
     اÙĦتÙĬ
    0.16
    Act Density 0.285%

    No Known Activations