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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software versions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esModule
    -0.16
    lashes
    -0.14
    illard
    -0.14
     Gig
    -0.14
    reste
    -0.13
    _Impl
    -0.13
    วà¸Ķ
    -0.13
    íıIJ
    -0.13
    央
    -0.13
    lope
    -0.13
    POSITIVE LOGITS
     release
    0.44
     Release
    0.39
     releases
    0.38
    release
    0.36
     released
    0.35
    Release
    0.34
    _release
    0.33
    -release
    0.33
    .release
    0.32
     RELEASE
    0.31
    Act Density 0.060%

    No Known Activations