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

    Neuronpedia

    INDEX
    Explanations

    occurrences of periods in the text

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

    start of turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijanski
    -0.60
     Roskov
    -0.59
    oa̍t
    -0.57
     OMITBAD
    -0.56
     Италијани
    -0.56
    titleMargin
    -0.55
    afficheront
    -0.55
     PeEnEo
    -0.54
     архивлан
    -0.54
     يتيمه
    -0.53
    POSITIVE LOGITS
     Tapia
    0.40
     “
    0.38
     terribly
    0.36
    .
    0.36
    Contain
    0.36
     Kraus
    0.35
     Maurer
    0.35
     
    0.35
     benne
    0.35
    ↵↵
    0.35
    Act Density 0.002%

    No Known Activations