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

    Neuronpedia

    INDEX
    Explanations

    the conjunction "and" used repeatedly in various contexts

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

    and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ije
    -0.46
     esercit
    -0.40
    tizo
    -0.40
    otex
    -0.39
    iyi
    -0.39
    Virgo
    -0.38
    PIO
    -0.38
    uaikan
    -0.38
    fig
    -0.38
     (!__
    -0.38
    POSITIVE LOGITS
    and
    2.17
    AND
    1.68
    And
    1.33
    ands
    1.24
     AND
    1.13
     And
    1.10
    andt
    1.06
    anden
    1.06
    和
    1.05
     and
    1.02
    Act Density 0.015%

    No Known Activations