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

    Neuronpedia

    INDEX
    Explanations

    numerical references and identifiers associated with scientific publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrat
    -0.17
    Äĥr
    -0.17
    azi
    -0.15
    WG
    -0.15
    .Offset
    -0.14
    istrar
    -0.14
    lage
    -0.14
    ä¸
    -0.14
    istr
    -0.13
    alse
    -0.13
    POSITIVE LOGITS
    DRV
    0.16
    Powered
    0.15
     ============================================================================↵
    0.15
    vf
    0.15
    phans
    0.14
    hart
    0.14
    bps
    0.14
    ìĶ
    0.14
     rep
    0.14
    orte
    0.14
    Act Density 0.017%

    No Known Activations