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

    Neuronpedia

    INDEX
    Explanations

    affirmations and expressions of personal opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sail
    -0.17
    estre
    -0.16
    ullo
    -0.16
    ÑĴ
    -0.15
    ]={↵
    -0.15
    ´Ŀ
    -0.14
    ä¸įå¾Ĺ
    -0.14
    ราย
    -0.14
    æĺŃ
    -0.14
     whereas
    -0.14
    POSITIVE LOGITS
    yes
    0.33
     yes
    0.32
    Yes
    0.27
     Yes
    0.27
    YES
    0.26
     indeed
    0.26
     YES
    0.23
    =yes
    0.21
    Yep
    0.19
    .Yes
    0.19
    Act Density 0.100%

    No Known Activations