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

    Neuronpedia

    INDEX
    Explanations

    references to letters and related correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yan
    -0.19
    yon
    -0.18
    yum
    -0.17
    onet
    -0.16
    ertain
    -0.15
    shire
    -0.15
    emaker
    -0.15
    sid
    -0.15
    illet
    -0.14
    ARDS
    -0.14
    POSITIVE LOGITS
    press
    0.28
    head
    0.22
    atura
    0.20
    ed
    0.20
    -spacing
    0.20
    ìĹ´
    0.18
    boxed
    0.17
    pressed
    0.17
    ing
    0.16
    ewe
    0.16
    Act Density 0.023%

    No Known Activations