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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, in particular the name "Norm"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Norm" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    packing
    -0.74
     thumbs
    -0.73
    Desk
    -0.70
    hig
    -0.64
    Hour
    -0.63
    Tea
    -0.63
     tea
    -0.62
    gery
    -0.61
     Oo
    -0.61
    volume
    -0.61
    POSITIVE LOGITS
    Norm
    1.07
     Norm
    1.02
    acies
    0.92
    osate
    0.88
    heastern
    0.85
    heast
    0.85
     Seym
    0.81
    als
    0.81
    orrow
    0.81
    entric
    0.81
    Act Density 0.008%

    No Known Activations