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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names and titles related to people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Teen
    -0.67
     Thief
    -0.65
     Playstation
    -0.64
    Bound
    -0.63
     Tup
    -0.63
     downtime
    -0.63
     Dolphin
    -0.62
    gamer
    -0.62
     Warehouse
    -0.61
     PlayStation
    -0.61
    POSITIVE LOGITS
    enegger
    1.16
    ricks
    0.89
    yk
    0.82
    kson
    0.81
    halla
    0.80
    jen
    0.80
    inson
    0.78
    esson
    0.76
    lein
    0.75
    irez
    0.75
    Act Density 0.332%

    No Known Activations