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

    Neuronpedia

    INDEX
    Explanations

    dates or years in the 1900s

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    unts
    -0.82
     ditch
    -0.78
     allowance
    -0.78
     idle
    -0.75
     consistency
    -0.75
     hug
    -0.73
     extinct
    -0.73
     candy
    -0.71
     curb
    -0.70
     goodbye
    -0.70
    POSITIVE LOGITS
     Previously
    1.31
     Its
    1.31
     Initially
    1.29
     Specifically
    1.27
     Originally
    1.26
     Essentially
    1.26
     Though
    1.22
     Located
    1.22
     It
    1.21
     Basically
    1.20
    Act Density 1.930%

    No Known Activations