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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intention or purpose

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases that begin with "for."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illin
    -0.70
    Champ
    -0.67
    Introduced
    -0.65
    ,.
    -0.62
    plate
    -0.62
    clair
    -0.61
    Enlarge
    -0.60
     nicknamed
    -0.59
    olan
    -0.57
     penned
    -0.57
    POSITIVE LOGITS
     instance
    1.17
    bidden
    1.15
     example
    1.14
    gotten
    1.13
    cing
    1.11
     starters
    1.10
    geries
    0.99
    gery
    0.98
     purposes
    0.97
     reasons
    0.89
    Act Density 0.101%

    No Known Activations