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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the significance or importance of specific facts

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

    explains from the fact that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.61
     незавершена
    -0.54
    prepareStatement
    -0.50
    findpost
    -0.50
    ftagPool
    -0.48
    romyalgia
    -0.47
    AndEndTag
    -0.46
     ModelExpression
    -0.45
    
    -0.45
     beginnetje
    -0.45
    POSITIVE LOGITS
     المعيارى
    0.50
    ilares
    0.45
    Pautan
    0.42
    뀜
    0.42
    #
    0.41
    ECAUSE
    0.41
    CPtr
    0.39
    thâu
    0.39
    idxs
    0.39
     fact
    0.37
    Act Density 0.083%

    No Known Activations