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

    Neuronpedia

    INDEX
    Explanations

    opinions or statements of position on various issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -1.14
    duct
    -0.74
    STON
    -0.72
    issance
    -0.70
     Explos
    -0.68
    batch
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.66
     Towers
    -0.66
     Sabha
    -0.65
    Luck
    -0.65
    POSITIVE LOGITS
     stances
    1.35
     stance
    1.35
     positions
    0.99
     views
    0.96
     beliefs
    0.91
     opinions
    0.90
     position
    0.89
     regarding
    0.89
     viewpoints
    0.89
     vehemently
    0.87
    Act Density 0.048%

    No Known Activations