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

    Neuronpedia

    INDEX
    Explanations

    numerical statistics and figures in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mara
    -0.15
    ivr
    -0.14
     Been
    -0.14
    evity
    -0.14
    ÄŁan
    -0.14
     Brit
    -0.14
     fore
    -0.14
    ¯¯
    -0.14
    евиÑĩ
    -0.13
     ÛĮاÙģت
    -0.13
    POSITIVE LOGITS
    康
    0.15
    others
    0.14
    ecies
    0.14
    reas
    0.14
    fa
    0.14
    icari
    0.14
     ëį°
    0.14
    ainless
    0.14
    772
    0.13
    FA
    0.13
    Act Density 0.038%

    No Known Activations