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

    Neuronpedia

    INDEX
    Explanations

    references to news agencies or organizations such as "RIA Novosti."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific news agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aire
    -0.86
    ary
    -0.77
    ende
    -0.71
    mans
    -0.71
    selves
    -0.70
    istas
    -0.67
     Dragonbound
    -0.67
    wcsstore
    -0.67
    aires
    -0.67
    meyer
    -0.67
    POSITIVE LOGITS
    BILITY
    1.22
    BLE
    1.17
    ULT
    0.98
    BILITIES
    0.97
    zza
    0.93
    EA
    0.89
    ACA
    0.87
    ccess
    0.86
    LECT
    0.86
    BI
    0.86
    Act Density 0.015%

    No Known Activations