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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of the United States and its related departments or agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulling
    -0.15
    ÅĻej
    -0.14
    urette
    -0.14
    oes
    -0.14
    alysis
    -0.14
    beat
    -0.14
    taÅŁ
    -0.14
    ijo
    -0.14
    ergus
    -0.13
    ynes
    -0.13
    POSITIVE LOGITS
    âĢĮâĢĮ
    0.17
     Aires
    0.16
    inson
    0.15
     semiclass
    0.15
    oret
    0.14
     wides
    0.14
    mach
    0.14
     tentang
    0.13
     disproportion
    0.13
    intern
    0.13
    Act Density 0.089%

    No Known Activations