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

    Neuronpedia

    INDEX
    Explanations

    titles of conferences, events, or academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rig
    -0.15
    finalize
    -0.15
    pts
    -0.15
    ories
    -0.15
     number
    -0.14
    lobs
    -0.14
    rack
    -0.13
     Pru
    -0.13
    ledge
    -0.13
    ynch
    -0.13
    POSITIVE LOGITS
     unto
    0.20
    inha
    0.18
    uze
    0.17
     Odyssey
    0.16
     Approach
    0.15
    anzi
    0.15
    CHandle
    0.14
    λεκ
    0.14
     consect
    0.14
    sei
    0.14
    Act Density 0.166%

    No Known Activations