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

    Neuronpedia

    INDEX
    Explanations

    terms related to directional movement and alignment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.44
    حياته
    -0.43
    HasAnnotation
    -0.42
    ########.
    -0.41
     cahier
    -0.40
    abbix
    -0.38
     spon
    -0.38
    ItemBackground
    -0.37
    CEC
    -0.36
    Ciri
    -0.36
    POSITIVE LOGITS
     direction
    0.66
     orientations
    0.66
     angle
    0.63
     angles
    0.63
     oriented
    0.60
     directional
    0.60
     perpendicular
    0.59
     orientation
    0.58
    direction
    0.57
     kierunku
    0.56
    Act Density 0.824%

    No Known Activations