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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of places, people, and titles

    oai_token-act-pair · gpt-3.5-turbo

    topics related to sports and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Salvador
    -0.65
    ULL
    -0.59
     Mell
    -0.58
     Bris
    -0.58
    Fla
    -0.57
     Cantor
    -0.57
    ocamp
    -0.57
     Lank
    -0.56
     Legislative
    -0.56
     Cull
    -0.56
    POSITIVE LOGITS
     existed
    0.94
     ain
    0.93
     sucks
    0.92
     shouldn
    0.90
     doesnt
    0.90
     exists
    0.89
     hadn
    0.88
    ?).
    0.87
     wouldn
    0.87
     hasn
    0.86
    Act Density 0.852%

    No Known Activations