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

    Neuronpedia

    INDEX
    Explanations

    nouns and titles related to individuals in sports and government contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.73
     ſtate
    -0.70
    ſelves
    -0.70
    ſelf
    -0.67
     ftate
    -0.66
    GEBURTSDATUM
    -0.66
     houſe
    -0.65
     himſelf
    -0.65
     themſelves
    -0.64
     ſta
    -0.62
    POSITIVE LOGITS
     Rabbi
    0.53
     Professor
    0.50
     Senator
    0.49
     Councilman
    0.47
     Mayor
    0.47
    Senator
    0.46
     Congressman
    0.46
    Rabbi
    0.46
     Dr
    0.45
     Minister
    0.44
    Act Density 0.346%

    No Known Activations