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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criticism or negativity towards certain topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avel
    -0.16
    boss
    -0.15
    wo
    -0.15
    tron
    -0.15
    hs
    -0.14
     Nursery
    -0.14
     swo
    -0.14
    226
    -0.14
    cade
    -0.14
    ore
    -0.14
    POSITIVE LOGITS
    ThreadId
    0.15
    Inlining
    0.15
    Wunused
    0.15
    upal
    0.14
    CompleteListener
    0.14
     ÙħÙĤد
    0.14
     âĨĴ↵↵
    0.14
    ضا
    0.14
     cud
    0.14
    äs
    0.14
    Act Density 0.000%

    No Known Activations