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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or authors in academic publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kud
    -0.15
     Brace
    -0.15
     HAL
    -0.15
    (h
    -0.14
     gall
    -0.14
    |h
    -0.14
    olid
    -0.13
    awei
    -0.13
    pat
    -0.13
    landa
    -0.13
    POSITIVE LOGITS
    artner
    0.20
    lox
    0.17
    ara
    0.16
    abeth
    0.16
    ÙĪÙĬت
    0.15
    ernel
    0.15
    CTX
    0.14
    byn
    0.14
    -addon
    0.14
    odes
    0.14
    Act Density 0.071%

    No Known Activations