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

    Neuronpedia

    INDEX
    Explanations

    Greek letters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols, particularly those that resemble currency or mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     poaching
    -0.75
     Lauder
    -0.74
     wildlife
    -0.74
     blacklist
    -0.72
     Brow
    -0.69
    orno
    -0.69
     timely
    -0.68
    iage
    -0.67
    hower
    -0.67
     drawer
    -0.66
    POSITIVE LOGITS
    ο
    2.11
    ÏĦ
    2.08
    Ï
    2.06
    Î
    2.06
    α
    2.05
    κ
    2.02
    λ
    2.01
    ν
    2.01
    ι
    1.98
    Ïģ
    1.96
    Act Density 0.025%

    No Known Activations