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

    Neuronpedia

    INDEX
    Explanations

    references to political calls for action or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ↵
    -0.15
    -↵
    -0.14
    ô
    -0.14
    ¬
    -0.14
     [[
    -0.13
    ãģĹãģ¾
    -0.13
     наÑģÑĤ
    -0.13
    [[
    -0.13
    ħĮ
    -0.13
    ãģĵãģĿ
    -0.12
    POSITIVE LOGITS
     ‘
    0.19
    ï¿
    0.16
     '
    0.16
     %↵↵
    0.15
    ï¼ģï¼ģ↵↵
    0.15
     &#
    0.15
     intl
    0.14
    ï½ŀ↵↵
    0.14
     '&#
    0.14
     '(
    0.14
    Act Density 0.914%

    No Known Activations