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

    Neuronpedia

    INDEX
    Explanations

    specific references to time-related phrases or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĬار
    -0.16
    uhan
    -0.15
    antar
    -0.14
    éIJĺ
    -0.14
     precaution
    -0.14
    .Direction
    -0.13
    زÙħ
    -0.13
    elts
    -0.13
    leon
    -0.13
    ocrates
    -0.13
    POSITIVE LOGITS
     point
    1.16
    point
    0.96
     Point
    0.88
    -point
    0.84
    Point
    0.81
    _point
    0.80
     punto
    0.77
     POINT
    0.75
    çĤ¹
    0.73
    .point
    0.72
    Act Density 0.101%

    No Known Activations