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

    Neuronpedia

    INDEX
    Explanations

    references to tourist attractions and related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aqu
    -0.16
    alus
    -0.15
    /*č↵
    -0.15
    riger
    -0.15
    UnitTest
    -0.14
    vier
    -0.14
    oppable
    -0.14
    abile
    -0.14
    ailable
    -0.14
    erson
    -0.14
    POSITIVE LOGITS
     margin
    0.15
    çīĮ
    0.15
    awns
    0.15
     alarms
    0.14
    askell
    0.14
     natural
    0.14
     nic
    0.14
     Shaw
    0.14
     chap
    0.14
     Chap
    0.14
    Act Density 0.001%

    No Known Activations