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

    Neuronpedia

    INDEX
    Explanations

    personal references and admissions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Denn
    -0.16
    965
    -0.15
    661
    -0.15
    apol
    -0.14
    loh
    -0.14
    rawn
    -0.14
    asy
    -0.14
    изнеÑģ
    -0.14
     sist
    -0.14
    ucer
    -0.13
    POSITIVE LOGITS
     Bid
    0.16
     bid
    0.15
    Bid
    0.15
    conde
    0.15
    zman
    0.15
    esk
    0.14
    errat
    0.14
    κι
    0.14
    ÏĦια
    0.14
    нд
    0.14
    Act Density 0.085%

    No Known Activations