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

    Neuronpedia

    INDEX
    Explanations

    references to historical events or economic transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    缼
    -0.16
     Brexit
    -0.16
    adlo
    -0.15
     Wenger
    -0.15
    roman
    -0.15
    sume
    -0.14
    ilos
    -0.14
    екÑģи
    -0.14
     mo
    -0.14
    –↵↵
    -0.14
    POSITIVE LOGITS
     DM
    0.27
     Korean
    0.27
     Inch
    0.25
     UNC
    0.25
     Seoul
    0.25
     UN
    0.24
     Korea
    0.22
     Koreans
    0.21
    DM
    0.21
     Pyongyang
    0.21
    Act Density 0.007%

    No Known Activations