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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "is" and its variations

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

    it's not, it's just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſte
    -0.61
    脚注の使い方
    -0.61
    TestingModule
    -0.59
     ſche
    -0.54
    JspWriter
    -0.51
     deleteUser
    -0.48
    RTLI
    -0.48
    parsedMessage
    -0.47
     ſtate
    -0.47
     ſta
    -0.47
    POSITIVE LOGITS
     is
    0.74
    ίναι
    0.69
     its
    0.65
    它是
    0.64
     είναι
    0.62
     blitt
    0.59
     not
    0.57
     není
    0.57
     оно
    0.56
     blevet
    0.56
    Act Density 0.120%

    No Known Activations