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

    Neuronpedia

    INDEX
    Explanations

    instances of specific keywords or tokens that indicate measurements, functions, or entities in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baugh
    -0.17
    chio
    -0.15
    AINED
    -0.15
     BLE
    -0.15
    bins
    -0.14
    ccione
    -0.14
    nis
    -0.14
    äng
    -0.14
     Cru
    -0.14
     ble
    -0.14
    POSITIVE LOGITS
    gd
    0.17
    inar
    0.16
    -dir
    0.15
    umpy
    0.14
    562
    0.14
    ÑĤаб
    0.14
    LL
    0.14
    feed
    0.14
    MMdd
    0.14
    飯
    0.14
    Act Density 0.019%

    No Known Activations