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

    Neuronpedia

    INDEX
    Explanations

    instances of political positions and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RICT
    -0.16
    eref
    -0.15
    oves
    -0.15
    æĸŃ
    -0.15
    yre
    -0.15
     اÙĦÙĪÙĦ
    -0.14
    ysa
    -0.14
    oufl
    -0.14
    ило
    -0.14
    uchen
    -0.14
    POSITIVE LOGITS
     hum
    0.16
     unt
    0.16
     Vulner
    0.15
    112
    0.15
    urg
    0.14
     sor
    0.14
    chk
    0.14
     Disclosure
    0.14
     vulner
    0.14
    razil
    0.14
    Act Density 0.278%

    No Known Activations