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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anges
    -0.15
     pev
    -0.15
    ltk
    -0.15
    sville
    -0.15
    hoe
    -0.15
    pled
    -0.14
    zens
    -0.14
    PU
    -0.14
    aget
    -0.14
    edes
    -0.13
    POSITIVE LOGITS
     point
    0.42
     Point
    0.32
     points
    0.31
    point
    0.31
     POINT
    0.29
    -point
    0.28
    _point
    0.27
    Point
    0.27
     punto
    0.26
    _Point
    0.24
    Act Density 0.015%

    No Known Activations