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

    Neuronpedia

    INDEX
    Explanations

    references to database operations and their internal components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ackers
    -0.16
     plac
    -0.16
    uckles
    -0.15
    raud
    -0.15
    andr
    -0.14
     meaning
    -0.14
    §
    -0.14
     Lambert
    -0.14
    cstdlib
    -0.14
    blank
    -0.14
    POSITIVE LOGITS
    erland
    0.18
    modele
    0.15
    uncios
    0.15
    StartPosition
    0.15
    _reporting
    0.15
    RAP
    0.15
    phin
    0.15
    ↵↵
    0.15
    ullet
    0.15
    etail
    0.15
    Act Density 0.004%

    No Known Activations