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

    Neuronpedia

    INDEX
    Explanations

    usage of the word "were."

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

    were followed by adjective or verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.52
    WithIOException
    -0.52
     فريبيس
    -0.51
     doInBackground
    -0.50
     Arhi
    -0.50
     antif
    -0.49
    lexus
    -0.49
    ContentAlignment
    -0.48
    tisgarh
    -0.48
    AX
    -0.48
    POSITIVE LOGITS
     Were
    1.27
    Were
    1.16
    were
    1.06
     were
    1.01
     WERE
    0.94
     Where
    0.73
     weren
    0.70
    weren
    0.69
    where
    0.67
     where
    0.65
    Act Density 0.047%

    No Known Activations