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

    Neuronpedia

    INDEX
    Explanations

    pronouns representing a specific person

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual or player

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wendy
    -0.73
     Dominion
    -0.73
     censorship
    -0.71
     Millennium
    -0.70
     Prohibition
    -0.69
     privatization
    -0.67
     Confederacy
    -0.63
     Sovereign
    -0.62
    actionDate
    -0.62
     Straw
    -0.62
    POSITIVE LOGITS
    'll
    1.36
    'd
    1.28
     scored
    1.21
     averaged
    1.19
     hasn
    1.19
     deserves
    1.06
     plays
    1.06
     coached
    1.05
     earns
    1.04
    zbollah
    1.04
    Act Density 0.144%

    No Known Activations