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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    place
    -0.15
    ейн
    -0.14
    jin
    -0.14
    Äħ
    -0.14
    lek
    -0.14
    ian
    -0.14
     tac
    -0.14
    rello
    -0.14
    ella
    -0.14
    erals
    -0.14
    POSITIVE LOGITS
    iad
    0.16
    anism
    0.16
    eos
    0.15
    ppers
    0.15
    tle
    0.15
    ãĥ¡ãĥ³ãĥĪ
    0.15
    arf
    0.15
    ermann
    0.15
    ạt
    0.14
    ÙijÙı
    0.14
    Act Density 0.011%

    No Known Activations