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

    Neuronpedia

    INDEX
    Explanations

    dialogue and interactions between characters, particularly focusing on formal address and responses

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

    speaking after a quote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.64
    BibitemShut
    -0.57
     محفوظة
    -0.54
    RectangleBorder
    -0.54
     noqa
    -0.54
    ſt
    -0.54
    éez
    -0.54
    estinations
    -0.52
    GeneratedValue
    -0.51
     eſt
    -0.50
    POSITIVE LOGITS
     answer
    0.41
     risposta
    0.39
     answered
    0.37
    GOTREF
    0.36
     answers
    0.34
    jsxFileName
    0.34
     replied
    0.33
    responseType
    0.33
     Then
    0.33
     then
    0.32
    Act Density 0.044%

    No Known Activations