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

    Neuronpedia

    INDEX
    Explanations

    numbers within a range of 0 to 10 that represent important aspects of a situation or an object

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases and concepts associated with the word "another"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clubs
    -0.67
     Ajax
    -0.65
     Sporting
    -0.62
     Moonlight
    -0.62
     Reprodu
    -0.62
    ople
    -0.61
     Apprentice
    -0.60
     Hobby
    -0.60
     Symbol
    -0.58
     Reporter
    -0.58
    POSITIVE LOGITS
    worldly
    0.99
    roller
    0.85
    anche
    0.83
    ioch
    0.80
    than
    0.78
    ypes
    0.76
    rolling
    0.75
     than
    0.75
     besides
    0.73
    blance
    0.72
    Act Density 0.247%

    No Known Activations