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

    Neuronpedia

    INDEX
    Explanations

    keywords related to legal processes and courtroom details

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

    Precedes the word "were."

    np_acts-logits-general · gemini-2.0-flash

    followed by were

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     was
    -1.19
     is
    -1.00
    was
    -0.97
     isn
    -0.92
     wasn
    -0.86
     wordt
    -0.84
     έχει
    -0.83
     has
    -0.83
    wasn
    -0.76
     doesn
    -0.74
    POSITIVE LOGITS
     were
    2.78
    were
    2.03
    Were
    2.00
     Were
    1.95
     WERE
    1.84
     weren
    1.65
     étaient
    1.23
     waren
    1.23
     były
    1.20
     fueron
    1.20
    Act Density 0.889%

    No Known Activations