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

    Neuronpedia

    INDEX
    Explanations

    high-frequency functional words that serve grammatical purposes in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (Editor
    -0.19
    ãĥĵãĥ¼
    -0.15
    çłĤ
    -0.15
    ispecies
    -0.15
     jadx
    -0.14
    UnderTest
    -0.14
    ardu
    -0.14
    lesi
    -0.14
    amac
    -0.14
    EntryPoint
    -0.14
    POSITIVE LOGITS
    antan
    0.15
    omo
    0.15
     Likely
    0.15
    ears
    0.15
    ates
    0.15
     Gates
    0.15
    ackage
    0.15
    sa
    0.15
     McA
    0.14
    iky
    0.14
    Act Density 0.003%

    No Known Activations