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

    Neuronpedia

    INDEX
    Explanations

    indicators of continuation or ongoing discussion in text

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

    continuation text markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kháu
    -0.47
     Gubernur
    -0.42
     Monfieur
    -0.41
    Архівовано
    -0.40
     dAtA
    -0.39
     mariée
    -0.39
     tuya
    -0.39
    AccessorTable
    -0.39
    jspb
    -0.38
    pośred
    -0.38
    POSITIVE LOGITS
    RTCK
    0.49
     Continuation
    0.48
    Personendaten
    0.46
     CONTINUED
    0.45
    devamını
    0.44
     continue
    0.43
     autorytatywna
    0.43
    Tikang
    0.43
    continuation
    0.43
    continue
    0.42
    Act Density 0.176%

    No Known Activations