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

    Neuronpedia

    INDEX
    Explanations

    references to specific political or activist groups and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ı
    -0.17
    hardt
    -0.15
    orno
    -0.14
    ãĥIJãĤ¤
    -0.14
    ìķĻ
    -0.14
    arga
    -0.14
    ota
    -0.14
    ãĤĤãĤĬ
    -0.14
    aisal
    -0.14
    onta
    -0.14
    POSITIVE LOGITS
     Fal
    0.19
     regime
    0.18
     Bucc
    0.16
     ex
    0.16
     cult
    0.16
     Geld
    0.16
     democratic
    0.16
     Moj
    0.15
    iyon
    0.15
    ollar
    0.15
    Act Density 0.005%

    No Known Activations