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

    Neuronpedia

    INDEX
    Explanations

    phrases related to direction and movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.86
    HtmlAttribute
    -0.74
    ftagPool
    -0.70
    </tfoot>
    -0.70
    iastical
    -0.65
    AntiForgeryToken
    -0.65
    AndEndTag
    -0.65
    CloseOperation
    -0.62
    tagHelperRunner
    -0.61
    apimachinery
    -0.61
    POSITIVE LOGITS
     direction
    1.35
     richting
    1.22
     toward
    1.16
    direction
    1.14
     Richtung
    1.13
     Direction
    1.12
     towards
    1.10
     directions
    1.10
    的方向
    1.10
    toward
    1.09
    Act Density 0.259%

    No Known Activations