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

    Neuronpedia

    INDEX
    Explanations

    numerical expressions such as ordinals and measurements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rooms
    -0.84
    istas
    -0.76
    Tokens
    -0.74
    details
    -0.72
    POST
    -0.70
    lords
    -0.66
    Attributes
    -0.65
    bda
    -0.65
    politics
    -0.64
    stones
    -0.64
    POSITIVE LOGITS
     consecutive
    1.20
     longest
    0.94
     largest
    0.93
     busiest
    0.92
     fastest
    0.85
     highest
    0.85
     successive
    0.84
     oldest
    0.84
     anniversary
    0.84
     shortest
    0.83
    Act Density 0.066%

    No Known Activations