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

    Neuronpedia

    INDEX
    Explanations

    the word "up" in various contexts, indicating a focus on upward movement or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ushman
    -0.17
    chner
    -0.16
    åij¨å¹´
    -0.15
    ChangeListener
    -0.15
    ypad
    -0.14
    .openapi
    -0.14
    AlmostEqual
    -0.14
    itchens
    -0.14
    ting
    -0.14
    ıy
    -0.14
    POSITIVE LOGITS
    wards
    0.19
    WARDS
    0.17
    ward
    0.17
     bis
    0.16
    è¾¾
    0.16
    -front
    0.16
    otre
    0.16
    otos
    0.15
    aid
    0.15
    ussy
    0.15
    Act Density 0.017%

    No Known Activations