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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political or governmental systems and processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social structures and political systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IMAGES
    -0.69
    姫
    -0.65
    Cause
    -0.58
    issions
    -0.58
    cause
    -0.56
    Topics
    -0.56
    itars
    -0.55
    levels
    -0.54
     doesnt
    -0.54
     Topic
    -0.54
    POSITIVE LOGITS
     overseen
    0.98
     designed
    0.96
     dubbed
    0.94
     championed
    0.93
     pioneered
    0.92
     conceived
    0.91
     forged
    0.91
     devised
    0.91
     perfected
    0.90
     spearheaded
    0.90
    Act Density 0.743%

    No Known Activations