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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to political figures and organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uria
    -0.86
    thia
    -0.84
    NetMessage
    -0.82
    terday
    -0.77
    ocrates
    -0.75
    riel
    -0.74
    cedes
    -0.72
    haps
    -0.71
    itars
    -0.71
    verbs
    -0.68
    POSITIVE LOGITS
     portion
    1.00
     universe
    0.99
    osphere
    0.99
     era
    0.96
     Institute
    0.96
     bandwagon
    0.96
     debacle
    0.95
     ecosystem
    0.94
     logo
    0.92
     community
    0.91
    Act Density 3.856%

    No Known Activations