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

    Neuronpedia

    INDEX
    Explanations

    information related to academic publications, including author names, publication titles, article numbers, and journal names

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    udi
    -0.33
    ea
    -0.28
     Newsp
    -0.25
    hiba
    -0.25
    icia
    -0.24
    î
    -0.24
    ichever
    -0.24
    bernatorial
    -0.24
    isi
    -0.24
    uga
    -0.24
    POSITIVE LOGITS
     raft
    0.26
     casc
    0.26
     coupling
    0.23
    obil
    0.23
     tether
    0.23
    WP
    0.22
     reson
    0.22
     counters
    0.22
     Sioux
    0.21
     Kraken
    0.21
    Act Density 5.517%

    No Known Activations