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

    Neuronpedia

    INDEX
    Explanations

    numeric values usually in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms typically related to locations or specific entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Arlington
    -0.80
     Waste
    -0.75
    585
    -0.75
     Fairfax
    -0.74
     âĹı
    -0.72
     Alexandria
    -0.72
     Archangel
    -0.71
     grounding
    -0.70
     Vapor
    -0.68
     privat
    -0.67
    POSITIVE LOGITS
    j
    1.47
    J
    1.46
    JD
    1.25
    Js
    1.23
    IJ
    1.22
    jit
    1.21
    jo
    1.20
    jer
    1.20
    JP
    1.17
    ji
    1.16
    Act Density 0.323%

    No Known Activations