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

    Neuronpedia

    INDEX
    Explanations

    content related to retweeting on Twitter

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Ret" indicating a retweet or references to social media sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tips
    -0.84
     hearts
    -0.70
    STEM
    -0.67
    hower
    -0.67
    ãĥ¼ãĥĨ
    -0.66
     similarities
    -0.65
    aughtered
    -0.65
    EngineDebug
    -0.64
     Passion
    -0.64
    SHIP
    -0.62
    POSITIVE LOGITS
    ention
    1.07
    ired
    1.05
    rieving
    1.05
    rieved
    1.04
    ribut
    1.04
    rieve
    1.02
    reating
    1.00
    ract
    1.00
    irement
    0.99
    ribution
    0.99
    Act Density 0.009%

    No Known Activations