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

    Neuronpedia

    INDEX
    Explanations

    terms related to science, politics, and social issues

    oai_token-act-pair · gpt-3.5-turbo

    key terms and concepts related to societal structures and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    local
    -0.73
    lihood
    -0.57
    ometown
    -0.56
    ospital
    -0.55
    ewitness
    -0.55
    bia
    -0.52
    AMD
    -0.52
    Merit
    -0.51
    bestos
    -0.50
    Ward
    -0.50
    POSITIVE LOGITS
     theorist
    0.66
     jargon
    0.62
     manuals
    0.57
    women
    0.55
    zsche
    0.54
     experimented
    0.54
     nowadays
    0.53
     insofar
    0.53
     discourse
    0.52
     manifesto
    0.52
    Act Density 0.986%

    No Known Activations