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

    Neuronpedia

    INDEX
    Explanations

    statements and responses related to political or official communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Prov
    -0.15
    696
    -0.15
     pitched
    -0.14
    owers
    -0.14
    prov
    -0.14
     prov
    -0.14
     stro
    -0.14
     directly
    -0.14
    aul
    -0.13
     Bour
    -0.13
    POSITIVE LOGITS
     Trang
    0.15
     semiclass
    0.15
     Bund
    0.15
     Soup
    0.14
    warts
    0.14
    extr
    0.14
    cu
    0.14
    UNK
    0.14
     Ñģви
    0.13
    zsche
    0.13
    Act Density 0.062%

    No Known Activations