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

    Neuronpedia

    INDEX
    Explanations

    social media links, specifically related to Facebook and Twitter

    oai_token-act-pair · gpt-3.5-turbo

    URLs related to Facebook

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.63
    onics
    -0.62
     exhaustion
    -0.58
    REM
    -0.58
    izophren
    -0.56
     formula
    -0.55
    Ĺ
    -0.54
    DK
    -0.52
    adra
    -0.52
     Balt
    -0.52
    POSITIVE LOGITS
    /#
    1.21
    /_
    1.13
    /+
    0.91
    /
    0.82
    /?
    0.81
    pose
    0.79
    jong
    0.79
    hovah
    0.78
    \/
    0.76
    /
    0.76
    Act Density 0.023%

    No Known Activations