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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to locations, names, and identifiers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.52
     Notting
    -0.47
    ogle
    -0.45
    ifestyle
    -0.41
     Dame
    -0.41
    soDeliveryDate
    -0.40
    #$
    -0.40
    daq
    -0.40
    kill
    -0.39
    brance
    -0.39
    POSITIVE LOGITS
    ERT
    0.39
     Zhang
    0.38
    ert
    0.37
    parts
    0.36
     heights
    0.35
    itled
    0.35
     TY
    0.34
     technical
    0.34
     UCH
    0.34
     evident
    0.33
    Act Density 0.046%

    No Known Activations