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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a point of initiation or starting process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StackNavigator
    -0.17
    oultry
    -0.15
    enment
    -0.14
    jekt
    -0.14
     Steering
    -0.14
    465
    -0.14
     Goose
    -0.14
    Į¨
    -0.13
     Nose
    -0.13
    oul
    -0.13
    POSITIVE LOGITS
     point
    0.59
    çĤ¹
    0.47
    point
    0.47
    -point
    0.46
    é»ŀ
    0.45
    _point
    0.42
     Point
    0.42
     points
    0.42
     POINT
    0.41
    Point
    0.40
    Act Density 0.097%

    No Known Activations