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

    Neuronpedia

    INDEX
    Explanations

    political figures and events in news articles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     artif
    -0.82
    Lear
    -0.78
     blat
    -0.75
     ak
    -0.75
     metab
    -0.65
    Reloaded
    -0.65
    edIn
    -0.65
     assum
    -0.64
     crate
    -0.63
     paran
    -0.63
    POSITIVE LOGITS
    aughs
    0.84
    inational
    0.71
     Abortion
    0.70
     respectively
    0.68
    igious
    0.68
    lees
    0.67
    culosis
    0.67
    ilitary
    0.67
    osponsors
    0.67
    illon
    0.66
    Act Density 6.127%

    No Known Activations