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

    Neuronpedia

    INDEX
    Explanations

    tokens related to temporal indicators and specific references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ildo
    -0.15
    å½¹
    -0.15
    pth
    -0.15
    abh
    -0.15
    duit
    -0.15
    upo
    -0.14
     niche
    -0.14
    ãĥ³ãĥķ
    -0.14
     Gim
    -0.14
     Hick
    -0.14
    POSITIVE LOGITS
    agar
    0.15
    agine
    0.15
    anik
    0.15
    appa
    0.14
     TArray
    0.14
    rq
    0.14
     infinity
    0.14
    agers
    0.14
    infinity
    0.14
    acent
    0.14
    Act Density 0.012%

    No Known Activations