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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political conspiracies and anti-Marxist sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :+:
    -0.56
     AssemblyCompany
    -0.55
    AndEndTag
    -0.54
    laub
    -0.52
    uarts
    -0.50
     tauto
    -0.50
    elas
    -0.49
     dAtA
    -0.48
    baum
    -0.47
    balanceOf
    -0.47
    POSITIVE LOGITS
     plot
    1.52
     plotting
    1.46
     plots
    1.45
    plot
    1.33
     plotted
    1.32
     Plot
    1.30
     Plots
    1.30
    plotting
    1.29
    Plot
    1.22
     Plotting
    1.19
    Act Density 0.689%

    No Known Activations