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

    Neuronpedia

    INDEX
    Explanations

    dates and locations of conferences or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     pse
    -0.85
     subscript
    -0.79
    xual
    -0.73
    attribute
    -0.72
    Versions
    -0.70
    nikov
    -0.70
     tremend
    -0.69
    rogens
    -0.66
    omorph
    -0.66
    utenberg
    -0.65
    POSITIVE LOGITS
     Atlanta
    1.51
     Seattle
    1.49
     Minneapolis
    1.46
     Pittsburgh
    1.44
     Chicago
    1.44
     Honolulu
    1.43
     Los
    1.43
     Philadelphia
    1.42
     Portland
    1.41
     Chattanooga
    1.39
    Act Density 0.105%

    No Known Activations