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

    Neuronpedia

    INDEX
    Explanations

    instances of location and conflict-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isle
    -0.16
    quil
    -0.15
     jadx
    -0.15
    HWND
    -0.15
    ıs
    -0.14
    bulan
    -0.14
    -anchor
    -0.14
    isbury
    -0.14
    æī¶
    -0.14
    umeric
    -0.14
    POSITIVE LOGITS
     compound
    0.28
     compounds
    0.23
     Compound
    0.22
     offices
    0.22
    Compound
    0.22
    compound
    0.21
     gates
    0.20
     main
    0.20
     gate
    0.19
     market
    0.18
    Act Density 0.121%

    No Known Activations