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

    Neuronpedia

    INDEX
    Explanations

    terms associated with statistical estimation and model convergence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     passes
    -0.16
    ův
    -0.15
     passe
    -0.15
     vice
    -0.14
     Poe
    -0.14
     unsuccessful
    -0.14
     noh
    -0.13
    æ¢
    -0.13
    passes
    -0.13
    ala
    -0.13
    POSITIVE LOGITS
    опаÑģ
    0.17
    ocity
    0.16
    اسب
    0.16
    lus
    0.15
    xae
    0.15
    oration
    0.15
     Wass
    0.15
    utes
    0.14
    åĭ
    0.14
    ProcAddress
    0.14
    Act Density 0.103%

    No Known Activations