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

    Neuronpedia

    INDEX
    Explanations

    posts or content requesting engagement on social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express social media engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enary
    -0.74
     istg
    -0.72
    rift
    -0.72
    è¦ļéĨĴ
    -0.72
    duct
    -0.71
    inion
    -0.71
    ennes
    -0.70
    hiba
    -0.69
    Americ
    -0.69
    ranean
    -0.68
    POSITIVE LOGITS
    lihood
    1.83
    liest
    1.17
    lier
    1.06
    liness
    0.93
    minded
    0.91
     minded
    0.89
     ours
    0.77
     wildfire
    0.76
    ly
    0.75
     liking
    0.74
    Act Density 0.043%

    No Known Activations