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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the purpose or function of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лей
    -0.15
    ddb
    -0.15
    ukkan
    -0.14
    dd
    -0.14
    hog
    -0.13
    pus
    -0.13
    oz
    -0.13
    mouth
    -0.13
    itter
    -0.13
     circular
    -0.13
    POSITIVE LOGITS
    ipo
    0.17
    REFERENCE
    0.17
    edic
    0.16
    ches
    0.15
     ustanov
    0.15
    291
    0.14
    .hardware
    0.14
     Gors
    0.14
    ufs
    0.14
     pokoj
    0.14
    Act Density 0.267%

    No Known Activations