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

    Neuronpedia

    INDEX
    Explanations

    references to time and numerical values related to events or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    552
    -0.17
    endon
    -0.15
    upa
    -0.15
    id
    -0.15
    537
    -0.14
    336
    -0.14
     ahead
    -0.14
    延
    -0.14
    ct
    -0.14
    hang
    -0.14
    POSITIVE LOGITS
    /Dk
    0.17
    ĺIJ
    0.17
    ilon
    0.16
    CHASE
    0.16
    DMIN
    0.15
    rtl
    0.15
     Shirley
    0.14
    IIIK
    0.14
    victim
    0.14
    tails
    0.14
    Act Density 0.019%

    No Known Activations