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

    Neuronpedia

    INDEX
    Explanations

    capitalized words

    oai_token-act-pair · gpt-3.5-turbo

    acronyms or abbreviations related to sports and medical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄŁ
    -0.75
    ct
    -0.71
     fa
    -0.64
    ks
    -0.63
    cc
    -0.60
    quire
    -0.60
    uphem
    -0.59
    alam
    -0.59
     Brus
    -0.59
    cs
    -0.59
    POSITIVE LOGITS
    ERY
    1.35
    ITION
    1.29
    ERS
    1.28
    ICAL
    1.28
    INGTON
    1.27
    ITS
    1.27
    IFIED
    1.24
    EST
    1.23
    ING
    1.23
    ISH
    1.22
    Act Density 0.095%

    No Known Activations