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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal and political terms and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     alpes
    -0.86
     adal
    -0.83
     utop
    -0.81
     nera
    -0.79
     torba
    -0.78
     marte
    -0.77
     marmor
    -0.76
     polig
    -0.76
     sement
    -0.76
     ananas
    -0.75
    POSITIVE LOGITS
     him
    0.94
     he
    0.90
     himself
    0.75
     his
    0.72
     acesta
    0.71
     shenan
    0.71
     He
    0.70
     she
    0.69
     éste
    0.67
    He
    0.66
    Act Density 1.349%

    No Known Activations