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

    Neuronpedia

    INDEX
    Explanations

    references to trails and trail-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipers
    -0.18
    ugins
    -0.17
    zell
    -0.16
    panse
    -0.15
    pill
    -0.15
    615
    -0.15
     mũi
    -0.14
    ÅĻeba
    -0.14
    IMER
    -0.14
    lü
    -0.14
    POSITIVE LOGITS
    side
    0.25
    ways
    0.23
    bl
    0.22
    head
    0.22
    way
    0.21
    /path
    0.19
     Blazers
    0.18
    ster
    0.16
    map
    0.16
    ogen
    0.16
    Act Density 0.013%

    No Known Activations