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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official documents and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aka
    -0.18
    elyn
    -0.18
    olit
    -0.17
     Ein
    -0.15
     aka
    -0.15
    _rw
    -0.14
     Wald
    -0.14
    agine
    -0.14
     courtesy
    -0.14
     referencing
    -0.14
    POSITIVE LOGITS
     vide
    0.23
    vide
    0.19
     Bord
    0.18
     Vide
    0.17
    latlong
    0.17
     cum
    0.16
     pais
    0.16
    ãĥ¼ãĥĢ
    0.15
    serialize
    0.15
     Cum
    0.15
    Act Density 0.100%

    No Known Activations