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

    Neuronpedia

    INDEX
    Explanations

    references to political processes and legislative actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    инов
    -0.17
    aises
    -0.15
    .bd
    -0.14
    ãĥ¼ãĤ¹
    -0.14
     aggrav
    -0.14
    ä¾µ
    -0.14
    ellant
    -0.14
    tica
    -0.13
    Warnings
    -0.13
    .tc
    -0.13
    POSITIVE LOGITS
     block
    0.33
     kill
    0.29
     killed
    0.29
     blocks
    0.28
    -block
    0.28
     blocking
    0.28
    block
    0.27
     blocked
    0.27
     BLOCK
    0.27
     torpedo
    0.26
    Act Density 0.102%

    No Known Activations