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

    Neuronpedia

    INDEX
    Explanations

    mentions of Russian interference

    oai_token-act-pair · gpt-3.5-turbo

    references to Russian interference in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etically
    -0.84
    sal
    -0.81
    ille
    -0.76
    than
    -0.76
    imb
    -0.76
    char
    -0.75
    chat
    -0.73
    neys
    -0.73
    xious
    -0.73
    \\\\\\\\
    -0.72
    POSITIVE LOGITS
     interference
    1.33
     meddling
    1.05
     interfere
    0.96
     interfered
    0.95
     destro
    0.94
     tampering
    0.93
     medd
    0.88
     interfering
    0.87
     undermin
    0.79
     intrusion
    0.78
    Act Density 0.011%

    No Known Activations