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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitions in arguments

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

    Preceding "it" or a pronoun

    np_acts-logits-general · gemini-2.0-flash

    that it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ISNI
    -0.64
     OFDb
    -0.57
    ubov
    -0.56
    исленность
    -0.56
    haustible
    -0.55
    uição
    -0.55
    Distribuzione
    -0.54
     ddelweddau
    -0.54
     ہیں۔
    -0.53
    wnież
    -0.52
    POSITIVE LOGITS
     it
    3.11
    它
    2.17
     оно
    2.15
     It
    2.04
    It
    1.89
     nó
    1.87
    它是
    1.86
     它
    1.75
     its
    1.73
     Оно
    1.71
    Act Density 1.319%

    No Known Activations