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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is being observed or spotted

    oai_token-act-pair · gpt-3.5-turbo

    instances of someone observing or interacting with another person

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     %%
    -0.71
    \.
    -0.71
    aqu
    -0.67
    chwitz
    -0.66
    buster
    -0.65
     blah
    -0.63
    estones
    -0.62
     Posted
    -0.61
    '';
    -0.61
    ,,,,
    -0.61
    POSITIVE LOGITS
     his
    0.87
     fellow
    0.86
     himself
    0.83
     contemporaries
    0.79
     teammate
    0.76
     opponents
    0.73
     colleagues
    0.68
     detractors
    0.68
     unsuspecting
    0.67
    his
    0.67
    Act Density 1.214%

    No Known Activations