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

    Neuronpedia

    INDEX
    Explanations

    terms related to progress or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.66
     ComVisible
    -0.61
     defaultstate
    -0.54
     surla
    -0.54
     yym
    -0.48
     zusätzlichen
    -0.44
     Exactos
    -0.43
    Abit
    -0.42
    /*---
    -0.42
    batore
    -0.41
    POSITIVE LOGITS
     advance
    1.16
    advance
    1.05
     advancement
    1.03
     advancing
    1.01
    Advance
    1.00
     Advance
    0.99
     advances
    0.90
     advanced
    0.89
     Advancement
    0.83
     advancements
    0.80
    Act Density 0.162%

    No Known Activations