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

    Neuronpedia

    INDEX
    Explanations

    references to toys

    oai_token-act-pair · gpt-3.5-turbo

    references to toys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulty
    -0.81
     transcripts
    -0.75
    icago
    -0.70
    idency
    -0.66
     transcript
    -0.66
    uth
    -0.65
    ornia
    -0.62
    aeda
    -0.62
    ignty
    -0.62
    mpeg
    -0.61
    POSITIVE LOGITS
     toys
    0.96
    boxes
    0.91
    ota
    0.91
    box
    0.91
    pole
    0.90
     dolls
    0.89
    slot
    0.89
     Crate
    0.87
     toy
    0.85
    bucks
    0.82
    Act Density 0.076%

    No Known Activations