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

    Neuronpedia

    INDEX
    Explanations

    mentions of research and development teams or departments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rabbit
    -0.15
    ourg
    -0.14
    uger
    -0.14
    iol
    -0.13
     âĹĦ
    -0.13
     Buchanan
    -0.13
    ozor
    -0.13
    êµŃìĿĺ
    -0.13
    882
    -0.13
    ÙIJÙĩ
    -0.12
    POSITIVE LOGITS
    &
    0.34
    (&
    0.32
     &
    0.31
     &___
    0.27
     '&
    0.26
    /&
    0.26
     "&
    0.26
    )&
    0.26
    ï¼Ĩ
    0.25
    }&
    0.25
    Act Density 0.035%

    No Known Activations