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

    Neuronpedia

    INDEX
    Explanations

    mentions of blankets

    oai_token-act-pair · gpt-3.5-turbo

    references to coverings or layers, particularly focusing on types of blankets and related items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymes
    -0.80
     sidx
    -0.70
    ctions
    -0.69
    ĸ
    -0.64
    Ķ
    -0.64
    ttle
    -0.64
    sych
    -0.63
    erence
    -0.63
    endants
    -0.63
    tics
    -0.62
    POSITIVE LOGITS
     blanket
    1.23
     carpet
    0.93
     blankets
    0.91
    spread
    0.88
     draped
    0.87
    shirt
    0.86
     COVER
    0.84
     applic
    0.83
     curtains
    0.82
    abies
    0.81
    Act Density 0.030%

    No Known Activations