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

    Neuronpedia

    INDEX
    Explanations

    political terminology and names related to government and political figures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ibaba
    -0.72
    itionally
    -0.69
    stals
    -0.68
    inki
    -0.67
    iculty
    -0.66
    ptin
    -0.66
    ulia
    -0.64
     Compos
    -0.64
     Folk
    -0.62
    ournals
    -0.62
    POSITIVE LOGITS
    CVE
    0.74
    CLASSIFIED
    0.71
    Jer
    0.69
     foregoing
    0.66
    Attach
    0.60
    AAAA
    0.60
    Market
    0.59
    Je
    0.59
    noon
    0.59
    WARD
    0.58
    Act Density 0.022%

    No Known Activations