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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and entities related to social media accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.85
    Ļ½
    -0.72
    bably
    -0.68
    gged
    -0.63
    itutes
    -0.63
    bidden
    -0.62
     grop
    -0.61
     dstg
    -0.61
     irreversible
    -0.61
    ledged
    -0.60
    POSITIVE LOGITS
    !:
    0.79
    !'
    0.76
     (@
    0.74
     homepage
    0.72
    !
    0.70
    pedia
    0.70
     »
    0.68
    Quotes
    0.63
     HERE
    0.63
    FAQ
    0.62
    Act Density 0.694%

    No Known Activations