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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate legal arguments and courtroom procedures

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

    legal and debate arguments

    np_acts-logits-general · gemini-2.0-flash

    oral arguments and legal briefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StreetMap
    -0.54
     Erişim
    -0.52
    #+#
    -0.51
    qrstuvwxyz
    -0.50
     photographe
    -0.48
    kelijkheid
    -0.48
     sightings
    -0.46
     yoksa
    -0.46
     adventurers
    -0.46
     koke
    -0.46
    POSITIVE LOGITS
     arguments
    1.38
     argument
    1.29
     Arguments
    1.23
     Argument
    1.22
    arguments
    1.15
     argumenta
    1.11
    argument
    1.11
    Arguments
    1.11
     argumentos
    1.09
    Argument
    1.09
    Act Density 0.688%

    No Known Activations