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

    Neuronpedia

    INDEX
    Explanations

    the number of votes received

    oai_token-act-pair · gpt-3.5-turbo

    references to voting or numerical results associated with candidates or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rums
    -0.62
    rum
    -0.61
    rology
    -0.57
    osi
    -0.56
    own
    -0.55
    lord
    -0.55
    ependence
    -0.55
    ologist
    -0.55
     McCl
    -0.55
    SPONSORED
    -0.55
    POSITIVE LOGITS
     apiece
    1.55
    poons
    1.21
     per
    1.01
    paces
    0.94
    omething
    0.90
     total
    0.84
    hips
    0.79
    pace
    0.78
    awatts
    0.75
    poon
    0.74
    Act Density 0.213%

    No Known Activations