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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to public figures and organizations

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and associations in a context involving figures in media or public life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pees
    -0.88
    ciating
    -0.81
    acci
    -0.79
    ayers
    -0.72
    owitz
    -0.70
    ETS
    -0.69
    ibble
    -0.69
    lems
    -0.67
    isson
    -0.67
    llo
    -0.66
    POSITIVE LOGITS
     educator
    0.93
     vice
    0.91
     activist
    0.90
     philosopher
    0.90
     longtime
    0.88
     collaborator
    0.88
     politician
    0.86
     former
    0.85
     entrepreneur
    0.84
     friend
    0.84
    Act Density 0.089%

    No Known Activations