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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that express significance or value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHAT
    -0.72
    ĺħ
    -0.62
    cot
    -0.61
    alsh
    -0.60
    owell
    -0.60
    brook
    -0.59
    essler
    -0.58
    Sharp
    -0.57
    avery
    -0.57
     vast
    -0.55
    POSITIVE LOGITS
     than
    1.89
    than
    1.62
     Than
    1.33
    erous
    0.75
    iating
    0.74
    iable
    0.74
    ially
    0.70
    iated
    0.69
    worldly
    0.69
     sounding
    0.68
    Act Density 0.158%

    No Known Activations