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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating returning or going back to a previous state or place

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

    back to replies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ifstream
    -0.38
    ểu
    -0.37
     catholique
    -0.35
     changement
    -0.33
     scolaires
    -0.33
     nocturno
    -0.33
     occhiali
    -0.33
    NameIn
    -0.33
     night
    -0.32
    ografía
    -0.32
    POSITIVE LOGITS
    PMailer
    0.73
     reply
    0.65
    Reply
    0.65
    ValueStyle
    0.61
    reply
    0.59
     Reply
    0.59
     REPLY
    0.59
     respond
    0.58
     Replies
    0.56
     replies
    0.56
    Act Density 0.005%

    No Known Activations