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

    Neuronpedia

    INDEX
    Explanations

    words related to identification and classification of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eron
    -0.17
    hek
    -0.15
    isma
    -0.15
    ocaust
    -0.14
    elin
    -0.14
    545
    -0.14
    ovie
    -0.14
    Mahon
    -0.13
    наÑĢод
    -0.13
     Hawk
    -0.13
    POSITIVE LOGITS
    oldem
    0.18
    ANCELED
    0.17
    endar
    0.15
    ackbar
    0.15
    coord
    0.14
     comp
    0.14
     Reed
    0.14
    anceled
    0.14
    osate
    0.14
    .Transactional
    0.14
    Act Density 0.001%

    No Known Activations