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

    Neuronpedia

    INDEX
    Explanations

    individuals who are in positions of authority or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating authority or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     corrid
    -0.56
    ©¶æ
    -0.56
     Parenthood
    -0.55
    guyen
    -0.54
     blat
    -0.54
     convol
    -0.53
     Scores
    -0.53
     deductible
    -0.52
    æĺ
    -0.52
     compr
    -0.52
    POSITIVE LOGITS
     of
    1.00
     overseeing
    0.96
     thereof
    0.86
    taker
    0.84
    posts
    0.74
    boards
    0.74
     OF
    0.74
    OF
    0.73
    of
    0.72
    enance
    0.70
    Act Density 0.032%

    No Known Activations