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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and logical connectors in sentences

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

    and then $

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.90
    ReusableCell
    -0.83
    featureID
    -0.78
    transQ
    -0.78
    wapV
    -0.76
    PerformLayout
    -0.75
    UrlResolution
    -0.74
    AsUp
    -0.74
    [@BOS@]
    -0.72
    <unused8>
    -0.72
    POSITIVE LOGITS
    和
    0.44
     Undang
    0.39
     Gubernur
    0.39
     kuin
    0.36
     Umum
    0.36
     Egipto
    0.36
     circonst
    0.32
     和
    0.32
     Belanda
    0.32
     Keuangan
    0.32
    Act Density 0.208%

    No Known Activations