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

    Neuronpedia

    INDEX
    Explanations

    phrases related to managing assistance and support

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

    "that" after conjunctions/punctuation

    np_acts-logits-general · gemini-2.0-flash

    and that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    命中
    -0.49
    TestingModule
    -0.48
    :][
    -0.44
    %
    -0.42
     promoção
    -0.42
    遇见
    -0.41
     pertence
    -0.40
    asteroide
    -0.39
     fark
    -0.39
    deckte
    -0.39
    POSITIVE LOGITS
     They
    0.85
     they
    0.84
     ایشان
    0.83
     ایش
    0.79
    SourceChecksum
    0.79
    enumi
    0.79
    they
    0.78
    Mereka
    0.78
    They
    0.78
     transférez
    0.77
    Act Density 0.349%

    No Known Activations