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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe methods or approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azor
    -0.16
    tron
    -0.15
    arg
    -0.15
    bens
    -0.15
    δει
    -0.15
    çĽ
    -0.14
     Helm
    -0.14
    STRACT
    -0.14
    gren
    -0.14
    Overview
    -0.14
    POSITIVE LOGITS
    @nate
    0.15
    .Reporting
    0.15
     eof
    0.14
     seins
    0.14
    oplay
    0.14
    iola
    0.14
    ffffffff
    0.14
    DataTask
    0.14
    ivol
    0.13
    -fontawesome
    0.13
    Act Density 0.001%

    No Known Activations