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

    Neuronpedia

    INDEX
    Explanations

    medical terms, technical or scientific jargon, and legal or governmental concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     à¤
    -0.90
     Ãī
    -0.75
    UES
    -0.70
    leaders
    -0.69
     ..........
    -0.69
     CHRIST
    -0.68
     Congratulations
    -0.66
    ublic
    -0.64
    ired
    -0.64
    along
    -0.63
    POSITIVE LOGITS
     allowable
    1.32
     permissible
    1.22
     scope
    1.06
     permitted
    0.91
     access
    0.90
     allowed
    0.89
     freedoms
    0.89
     exceptions
    0.88
     maximum
    0.88
     size
    0.87
    Act Density 0.165%

    No Known Activations