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

    Neuronpedia

    INDEX
    Explanations

    references to research methodologies and findings in scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pty
    -0.15
    omat
    -0.15
    bil
    -0.14
    ãģ«è¦ĭ
    -0.14
     Saw
    -0.14
     Guar
    -0.13
    .keep
    -0.13
    "title
    -0.13
    çľĭè§ģ
    -0.13
     Follow
    -0.13
    POSITIVE LOGITS
     inform
    0.34
     shed
    0.33
     informing
    0.33
    inform
    0.32
     informs
    0.31
     Inform
    0.29
     shedding
    0.28
    Inform
    0.28
     sheds
    0.27
     aid
    0.26
    Act Density 0.181%

    No Known Activations