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

    Neuronpedia

    INDEX
    Explanations

    sequences indicating the order of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    second in a sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.53
    Tikang
    -0.52
    endpush
    -0.49
    اعمال
    -0.48
     PUB
    -0.44
     postData
    -0.43
     Carro
    -0.43
     newName
    -0.42
    Datuak
    -0.42
    hamshire
    -0.41
    POSITIVE LOGITS
    UrlResolution
    0.46
     zweiten
    0.40
    <bos>
    0.39
     насељу
    0.39
     second
    0.38
    satunya
    0.38
    complexContent
    0.37
     drugiej
    0.36
     Emits
    0.36
    ########.
    0.36
    Act Density 0.043%

    No Known Activations