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

    Neuronpedia

    INDEX
    Explanations

    historical figures and their significant contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Television
    -0.17
     Airport
    -0.17
    197
    -0.17
     Farage
    -0.16
    æľºåľº
    -0.16
     airports
    -0.16
    Airport
    -0.16
    룡
    -0.16
     BBC
    -0.16
     Ronnie
    -0.16
    POSITIVE LOGITS
    190
    0.33
    191
    0.32
    189
    0.32
     Progressive
    0.27
     railroad
    0.24
    188
    0.23
     suff
    0.23
     Reconstruction
    0.23
     WW
    0.22
    187
    0.22
    Act Density 0.317%

    No Known Activations