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

    Neuronpedia

    INDEX
    Explanations

    terms related to recognition or familiarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ares
    -0.18
    fts
    -0.15
    lixir
    -0.14
    зд
    -0.14
    azio
    -0.14
    GLOSS
    -0.14
    _flux
    -0.14
    hest
    -0.14
     Dum
    -0.13
    isson
    -0.13
    POSITIVE LOGITS
     simply
    0.28
    Simply
    0.23
     Simply
    0.23
     simplement
    0.19
     commonly
    0.18
    s
    0.18
     inform
    0.18
    ä¿Ĺ
    0.17
     throughout
    0.17
     collo
    0.17
    Act Density 0.023%

    No Known Activations