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

    Neuronpedia

    INDEX
    Explanations

    technical details related to connections and parts in machinery or devices

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tours
    -0.70
    seeking
    -0.68
     Limbaugh
    -0.62
     Mans
    -0.62
     finances
    -0.60
     Newsp
    -0.59
    dogs
    -0.58
     waging
    -0.58
     Presidents
    -0.58
    funding
    -0.57
    POSITIVE LOGITS
     placeholder
    0.97
     protr
    0.93
     interchangeable
    0.92
     clutter
    0.84
     handy
    0.84
     unused
    0.83
     glyph
    0.81
     diagonal
    0.80
     incre
    0.80
     overpowered
    0.78
    Act Density 0.746%

    No Known Activations