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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of places and individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettle
    -0.90
    onica
    -0.79
    ledged
    -0.76
    ovan
    -0.75
    amed
    -0.72
    cloth
    -0.71
    adr
    -0.71
    ophe
    -0.70
    ards
    -0.69
    ugu
    -0.68
    POSITIVE LOGITS
     periods
    1.11
     adolescence
    0.99
     renovations
    0.96
     daylight
    0.93
     wartime
    0.93
     infancy
    0.92
     halftime
    0.91
     emergencies
    0.89
     weekends
    0.87
     recess
    0.85
    Act Density 0.653%

    No Known Activations