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

    Neuronpedia

    INDEX
    Explanations

    references to legal institutions, specifically courts

    oai_token-act-pair · gpt-3.5-turbo

    references to courts or judicial systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Soldier
    -0.68
     Prosper
    -0.65
     Valkyrie
    -0.64
     Horus
    -0.64
     Austral
    -0.63
     Hallow
    -0.63
     Scout
    -0.62
     sow
    -0.62
    ulus
    -0.61
     Horde
    -0.61
    POSITIVE LOGITS
    hip
    1.09
    esan
    0.94
    suits
    0.84
    cour
    0.84
    zona
    0.83
    hips
    0.82
    iard
    0.81
    assic
    0.81
    peer
    0.81
    krit
    0.81
    Act Density 0.024%

    No Known Activations