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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official announcements or press releases

    oai_token-act-pair · gpt-3.5-turbo

    references to press releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ń·
    -0.74
    iop
    -0.70
     Pratt
    -0.69
    MpServer
    -0.68
     Boh
    -0.68
     Et
    -0.67
    aque
    -0.66
     Fi
    -0.65
     imperson
    -0.65
    mic
    -0.64
    POSITIVE LOGITS
     release
    1.16
     RELEASE
    1.14
     releases
    1.02
    release
    0.98
    released
    0.92
    Release
    0.91
     Release
    0.90
     releasing
    0.90
     RELE
    0.89
    LEASE
    0.84
    Act Density 0.025%

    No Known Activations