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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the beginning or initiation of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "started" and related phrases indicating beginnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rored
    -0.81
    gypt
    -0.80
    obi
    -0.75
    omb
    -0.70
    acements
    -0.69
    dayName
    -0.69
    ugs
    -0.68
    inals
    -0.67
    verages
    -0.66
     entirety
    -0.66
    POSITIVE LOGITS
     noticing
    1.00
     practicing
    0.92
     experimenting
    0.91
     researching
    0.91
     acting
    0.88
     dating
    0.88
     behaving
    0.88
     blogging
    0.84
     bothering
    0.83
     experiencing
    0.83
    Act Density 0.072%

    No Known Activations