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

    Neuronpedia

    INDEX
    Explanations

    words related to completing, balancing, or filling out something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "separating" or "differentiating" elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.86
    eries
    -0.63
    interstitial
    -0.62
     Mub
    -0.60
     Tong
    -0.57
    PIN
    -0.56
     Jade
    -0.56
     tyr
    -0.54
    FLAG
    -0.53
    fters
    -0.53
    POSITIVE LOGITS
    flows
    0.98
    wards
    0.90
    stretched
    0.89
    posts
    0.85
    ricular
    0.84
    smart
    0.82
    flow
    0.81
    lier
    0.80
    fitted
    0.77
    )=(
    0.77
    Act Density 0.056%

    No Known Activations