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

    Neuronpedia

    INDEX
    Explanations

    terms related to searching and retrieval processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     searchable
    -0.20
    search
    -0.20
    serter
    -0.20
    _search
    -0.20
    Search
    -0.19
    ials
    -0.19
    æIJľç´¢
    -0.16
    usp
    -0.15
    uzzi
    -0.15
    aga
    -0.15
    POSITIVE LOGITS
    light
    0.33
     engine
    0.32
    lights
    0.31
    ers
    0.31
     engines
    0.31
     Engine
    0.28
    able
    0.27
    -engine
    0.27
    ingly
    0.25
     Engines
    0.25
    Act Density 0.038%

    No Known Activations