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

    Neuronpedia

    INDEX
    Explanations

    questions or inquiries that begin with "Are" or related word forms

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

    "Are" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    are you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    It
    -0.60
    一个
    -0.52
     it
    -0.51
     varandra
    -0.49
     aikaa
    -0.49
     verksamhet
    -0.49
     helft
    -0.48
     alcuna
    -0.48
     množství
    -0.48
     zboží
    -0.47
    POSITIVE LOGITS
     these
    1.03
    ']],
    0.97
     those
    0.96
     they
    0.93
     οι
    0.87
     THESE
    0.84
     ligiloj
    0.81
     متعلقه
    0.80
     esternos
    0.78
     THOSE
    0.78
    Act Density 0.153%

    No Known Activations