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

    Neuronpedia

    INDEX
    Explanations

    references to financial policies or economic measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Owls
    -0.75
     Owl
    -0.74
    owl
    -0.74
    Owl
    -0.71
     owl
    -0.70
     Bowling
    -0.69
     Jerry
    -0.69
    Bowling
    -0.69
     OW
    -0.68
     Florence
    -0.68
    POSITIVE LOGITS
     Ye
    1.02
     Carlson
    1.02
    Ye
    0.87
    Carl
    0.71
     Manny
    0.71
     PAL
    0.70
     Carl
    0.68
     Rolf
    0.65
     ADI
    0.64
     Dixon
    0.64
    Act Density 1.646%

    No Known Activations