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

    Neuronpedia

    INDEX
    Explanations

    mentions of ponies

    oai_token-act-pair · gpt-3.5-turbo

    references to the "My Little Pony" franchise and its characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yer
    -0.79
    enance
    -0.69
    WINDOWS
    -0.68
    Las
    -0.64
     Judgment
    -0.64
    HER
    -0.63
    INST
    -0.62
    scape
    -0.62
    ENA
    -0.61
    Jul
    -0.60
    POSITIVE LOGITS
     pony
    1.08
     ponies
    1.02
     Pony
    0.96
     Sparkle
    0.93
    tail
    0.85
    atron
    0.81
    bley
    0.80
     tremend
    0.78
    hyde
    0.77
     suscept
    0.75
    Act Density 0.015%

    No Known Activations