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

    Neuronpedia

    INDEX
    Explanations

    specific actions or tasks that need to be done

    oai_token-act-pair · gpt-3.5-turbo

    simple present and past forms of the verb "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     receipt
    -0.72
     Columb
    -0.70
     vict
    -0.67
     senses
    -0.64
     Trave
    -0.62
     suits
    -0.61
     Maver
    -0.60
    iture
    -0.60
     nearby
    -0.58
     uniforms
    -0.58
    POSITIVE LOGITS
     emulate
    0.81
    create
    0.80
     reproduce
    0.78
    olate
    0.78
    apply
    0.76
    :]
    0.75
    strip
    0.73
    æĸ¹
    0.73
    bourg
    0.71
    ozy
    0.71
    Act Density 0.033%

    No Known Activations