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

    Neuronpedia

    INDEX
    Explanations

    occurrences of HTML tags and their attributes

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

    names like Paul and Austin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.71
    parsedMessage
    -0.66
    twimg
    -0.65
     mergeFrom
    -0.65
    +#+
    -0.63
     transfieras
    -0.63
    msgTypes
    -0.61
    waitKey
    -0.60
    inSlope
    -0.59
     noDo
    -0.59
    POSITIVE LOGITS
     Paul
    0.39
     enca
    0.37
    Paul
    0.37
     where
    0.36
     Schmerz
    0.35
     Paulista
    0.34
    Austin
    0.34
    mez
    0.33
     Atkinson
    0.33
     Austin
    0.33
    Act Density 0.006%

    No Known Activations