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

    Neuronpedia

    INDEX
    Explanations

    the name "Morgan" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Morgan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.92
    ension
    -0.69
    ract
    -0.68
    ensions
    -0.65
    Ħ¢
    -0.63
    ľ
    -0.62
    ================================================================
    -0.61
     salsa
    -0.61
    uction
    -0.60
     humble
    -0.60
    POSITIVE LOGITS
     Stanley
    0.94
     Spur
    0.90
    gage
    0.90
    dale
    0.90
     Freeman
    0.87
    igans
    0.87
    itic
    0.86
     Chase
    0.82
    tex
    0.80
    imet
    0.79
    Act Density 0.018%

    No Known Activations