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

    Neuronpedia

    INDEX
    Explanations

    references to political entities, specifically republics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "republic" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ack
    -0.81
    gaard
    -0.77
     Ammunition
    -0.74
    itton
    -0.74
     Kamp
    -0.69
    STD
    -0.67
     Petersen
    -0.67
    acha
    -0.63
    velength
    -0.63
    Oracle
    -0.63
    POSITIVE LOGITS
    lisher
    0.99
    s
    0.98
    rats
    0.95
    hips
    0.94
    rants
    0.84
    inals
    0.83
    teen
    0.80
    sie
    0.80
    etrical
    0.79
    sis
    0.79
    Act Density 0.038%

    No Known Activations