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

    Neuronpedia

    INDEX
    Explanations

    Twitter usernames

    oai_token-act-pair · gpt-3.5-turbo

    usernames or handles in a social media context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tsu
    -0.87
     Nightmares
    -0.85
     Sabb
    -0.80
     Nightmare
    -0.78
     Rez
    -0.76
     Palmer
    -0.75
     Polk
    -0.72
     Maur
    -0.71
     Toby
    -0.71
     Siren
    -0.71
    POSITIVE LOGITS
    g
    1.53
    Gs
    1.43
    G
    1.38
    GC
    1.36
    gs
    1.35
    gc
    1.34
    gd
    1.34
    ga
    1.33
    gm
    1.31
    gart
    1.30
    Act Density 0.589%

    No Known Activations