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

    Neuronpedia

    INDEX
    Explanations

    references to social media posts and content sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ween
    -0.18
    akis
    -0.17
     targ
    -0.15
    istrovstvÃŃ
    -0.15
    ale
    -0.14
    кин
    -0.14
    æķ¬
    -0.14
     papers
    -0.14
     Tw
    -0.14
    572
    -0.14
    POSITIVE LOGITS
    æݪ
    0.16
    ToFront
    0.16
    itou
    0.16
    antz
    0.16
    xies
    0.15
    ToProps
    0.15
    pty
    0.15
    slaught
    0.15
    ãģ¡ãģ¯
    0.15
    -plugins
    0.14
    Act Density 0.106%

    No Known Activations