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

    Neuronpedia

    INDEX
    Explanations

    nerve-related terms, particularly focusing on nerve agents and nerve impulses

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    laws
    -0.88
    tions
    -0.74
    iesta
    -0.74
    aneers
    -0.74
    ies
    -0.70
    atchewan
    -0.69
    enance
    -0.69
    night
    -0.67
    anned
    -0.67
     Opportunity
    -0.65
    POSITIVE LOGITS
     endings
    1.01
     nerve
    1.01
     fibers
    0.88
    voy
    0.88
     agent
    0.79
     wrench
    0.78
     Stim
    0.78
    phrine
    0.78
     nerves
    0.77
     rod
    0.76
    Act Density 0.017%

    No Known Activations