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

    Neuronpedia

    INDEX
    Explanations

    examples in text that illustrate a point or concept

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    oreal
    -0.75
    acy
    -0.64
    ensor
    -0.63
    ariat
    -0.62
    aintain
    -0.61
    abit
    -0.61
    shaw
    -0.60
    ency
    -0.58
     edges
    -0.58
    ieties
    -0.57
    POSITIVE LOGITS
    example
    0.87
     Case
    0.82
     example
    0.78
     recent
    0.74
     exempl
    0.70
     Fukushima
    0.70
    Example
    0.69
     Example
    0.68
    Case
    0.68
     case
    0.68
    Act Density 0.291%

    No Known Activations