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

    Neuronpedia

    INDEX
    Explanations

    references to plug-related items or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to "plug-in" or related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AMERICA
    -0.66
    EMBER
    -0.66
     Butterfly
    -0.65
    birth
    -0.65
     Lann
    -0.61
    quez
    -0.61
     Plane
    -0.61
    perse
    -0.61
     Sons
    -0.61
     Wildcats
    -0.60
    POSITIVE LOGITS
    ging
    1.41
    ged
    1.27
    glers
    1.23
    plug
    1.08
     plug
    1.07
     plugs
    0.92
    odox
    0.90
    bling
    0.88
    atis
    0.87
    ocr
    0.87
    Act Density 0.012%

    No Known Activations