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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and political documents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parables
    -0.85
     flowers
    -0.80
     pist
    -0.78
     masc
    -0.76
    ã
    -0.75
    à¥
    -0.75
    Whe
    -0.74
     Riding
    -0.74
    ð
    -0.73
     grapes
    -0.73
    POSITIVE LOGITS
    FBI
    1.53
     espionage
    1.46
     spying
    1.46
     surveillance
    1.44
     counterterrorism
    1.44
    CIA
    1.43
    ionage
    1.42
     CIA
    1.40
     FBI
    1.39
     intelligence
    1.37
    Act Density 1.222%

    No Known Activations