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

    Neuronpedia

    INDEX
    Explanations

    phrases related to business or political campaigns

    oai_token-act-pair · gpt-3.5-turbo

    references to campaigns and political events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oneself
    -0.84
     ourselves
    -0.77
    aples
    -0.74
     GOODMAN
    -0.66
    urers
    -0.66
     Feder
    -0.64
    ickson
    -0.61
    pires
    -0.61
    Ĥª
    -0.61
     Kejriwal
    -0.60
    POSITIVE LOGITS
     autobiography
    0.84
     antics
    0.78
     persona
    0.75
     woes
    0.69
     spree
    0.69
     masterpiece
    0.68
     career
    0.68
     theorem
    0.67
     biography
    0.66
     tenure
    0.66
    Act Density 0.558%

    No Known Activations