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

    Neuronpedia

    INDEX
    Explanations

    numbers and measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and specific counts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Huck
    -0.84
     Illegal
    -0.83
     Unic
    -0.83
     Uni
    -0.82
     Kus
    -0.80
    UI
    -0.76
    uta
    -0.76
     HM
    -0.75
    Ul
    -0.75
    088
    -0.74
    POSITIVE LOGITS
     points
    1.66
     Points
    1.57
    point
    1.41
     point
    1.40
     Point
    1.39
    Points
    1.36
    points
    1.31
    Point
    1.29
     pts
    1.18
    arks
    1.06
    Act Density 0.182%

    No Known Activations