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

    Neuronpedia

    INDEX
    Explanations

    names of historically significant figures, particularly in politics and invention

    oai_token-act-pair · gpt-3.5-turbo

    names of historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seys
    -0.75
    players
    -0.67
    versions
    -0.64
     Perception
    -0.63
    tails
    -0.63
    juries
    -0.62
    Products
    -0.60
    Tools
    -0.59
    olves
    -0.59
    catch
    -0.59
    POSITIVE LOGITS
     Jr
    0.97
    Jr
    0.93
     III
    0.92
     assassinated
    0.87
    igham
    0.77
     Sr
    0.77
     grandson
    0.74
     memor
    0.71
     famously
    0.71
     prophes
    0.69
    Act Density 0.163%

    No Known Activations