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

    Neuronpedia

    INDEX
    Explanations

    topics related to books, downloads, libraries, digital media, and specific historical events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     guiActiveUn
    -0.60
    ãĤ´ãĥ³
    -0.42
    obin
    -0.42
    ãĥ¼ãĥĨ
    -0.40
    gger
    -0.40
    addons
    -0.38
    adle
    -0.38
    umbn
    -0.38
    ragon
    -0.37
    icing
    -0.37
    POSITIVE LOGITS
     sake
    0.48
    pires
    0.47
    !--
    0.41
    IENCE
    0.39
     Indones
    0.39
    nar
    0.38
     Wond
    0.37
     successive
    0.36
     Sham
    0.36
    pired
    0.35
    Act Density 12.245%

    No Known Activations