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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Pokémon"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Pokémon franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iffe
    -0.82
    perial
    -0.72
    ubb
    -0.72
    ijk
    -0.70
    rikes
    -0.70
    ¿½
    -0.69
     tiss
    -0.69
    ickson
    -0.69
    bush
    -0.68
    lain
    -0.67
    POSITIVE LOGITS
    Dex
    1.00
    Pokémon
    0.89
     Trainer
    0.86
     Pokémon
    0.86
    athlon
    0.85
    arium
    0.84
     pokemon
    0.82
     Pikachu
    0.82
     Pokemon
    0.80
     Poké
    0.79
    Act Density 0.035%

    No Known Activations