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

    Neuronpedia

    INDEX
    Explanations

    references to legal proceedings and decisions

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

    Follows a name or pronoun, precedes "said" or "stated"

    np_acts-logits-general · gemini-2.0-flash

    verbs of saying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    interopRequire
    -0.83
    +#+
    -0.73
     Monfieur
    -0.70
    Rhestr
    -0.70
    AddTagHelper
    -0.68
     насељу
    -0.66
    StructEnd
    -0.64
     оригіналу
    -0.63
    SBATCH
    -0.62
    adaptiveStyles
    -0.60
    POSITIVE LOGITS
     said
    1.22
     berkata
    1.14
    Said
    1.07
     says
    1.06
     saying
    1.04
     Says
    1.00
     Said
    0.98
    said
    0.98
     stated
    0.96
    Says
    0.93
    Act Density 0.444%

    No Known Activations