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

    Neuronpedia

    INDEX
    Explanations

    references to 'TODO' and related annotations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isle
    -0.16
    DO
    -0.14
    abant
    -0.14
    SCO
    -0.14
    mani
    -0.13
    igon
    -0.13
    ãĤ¤ãĤ¯
    -0.13
    inent
    -0.13
     Estr
    -0.13
    ORMAL
    -0.13
    POSITIVE LOGITS
    itsu
    0.17
    indr
    0.16
    ynos
    0.15
    elik
    0.15
    oggles
    0.14
     vụ
    0.14
    ungan
    0.13
    iÅŁ
    0.13
    _msgs
    0.13
    ervice
    0.13
    Act Density 0.009%

    No Known Activations