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

    Neuronpedia

    INDEX
    Explanations

    first-person perspective statements and declarations

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

    expressing personal feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.51
     raiſ
    -0.48
     queſta
    -0.48
     myſelf
    -0.47
     igjen
    -0.47
    sizeCache
    -0.47
    続きます
    -0.46
     faſt
    -0.45
     leſs
    -0.45
     ſtre
    -0.44
    POSITIVE LOGITS
    MemoryWarning
    0.58
     glad
    0.58
     Glad
    0.50
    SequentialGroup
    0.49
     freut
    0.47
    Glad
    0.45
     definitely
    0.45
     freuen
    0.44
    とにかく
    0.44
     مشين
    0.43
    Act Density 0.016%

    No Known Activations