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

    Neuronpedia

    INDEX
    Explanations

    the word "were" and its various occurrences

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

    past participles following were

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.58
     Arhi
    -0.45
    ting
    -0.44
    pyplot
    -0.44
    onSubmit
    -0.43
     csin
    -0.43
    tan
    -0.42
    inet
    -0.41
     Mail
    -0.41
     Lait
    -0.41
    POSITIVE LOGITS
     were
    1.42
    were
    1.28
     Were
    1.16
    Were
    1.11
     были
    1.11
     WERE
    1.11
     były
    1.05
     byly
    0.99
     були
    0.98
     estavam
    0.94
    Act Density 0.149%

    No Known Activations