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

    Neuronpedia

    INDEX
    Explanations

    phrases that begin with the word "Say."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Moran
    -0.15
    ials
    -0.15
     ç½
    -0.15
    nut
    -0.15
    itals
    -0.13
    omic
    -0.13
    gran
    -0.13
    /Dk
    -0.13
     Lens
    -0.13
    devil
    -0.13
    POSITIVE LOGITS
    abin
    0.17
    çĴĥ
    0.16
    олÑİ
    0.15
    ept
    0.15
    ippi
    0.15
    778
    0.15
    Ïģιν
    0.15
    APT
    0.14
    اع
    0.14
    ĶåĽŀ
    0.14
    Act Density 0.026%

    No Known Activations