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

    Neuronpedia

    INDEX
    Explanations

    names of authors and contributors in academic or research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utterstock
    -0.15
    imore
    -0.15
    åĨĬ
    -0.14
     Kraft
    -0.13
    ilians
    -0.13
    ct
    -0.13
    elles
    -0.13
    олÑĮно
    -0.13
    pher
    -0.13
    kö
    -0.13
    POSITIVE LOGITS
    umer
    0.15
    619
    0.15
     H
    0.14
     sâu
    0.14
     Ere
    0.13
     cubes
    0.13
    sea
    0.12
    ocaly
    0.12
    ayan
    0.12
    075
    0.12
    Act Density 0.005%

    No Known Activations