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

    Neuronpedia

    INDEX
    Explanations

    references to social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Facebook
    -0.17
     Tweet
    -0.16
    opak
    -0.16
    ê¶Į
    -0.15
     facebook
    -0.15
    ãĥ©ãĥĥãĤ¯
    -0.14
    lessly
    -0.14
    aight
    -0.14
    ÑĢеÑĪ
    -0.14
    getDb
    -0.14
    POSITIVE LOGITS
    .com
    0.35
    /google
    0.24
     account
    0.23
    .COM
    0.22
    verse
    0.20
    ian
    0.20
    /T
    0.19
    /email
    0.19
    /Y
    0.19
    /twitter
    0.18
    Act Density 0.076%

    No Known Activations