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

    Neuronpedia

    INDEX
    Explanations

    references to elevation, slopes, and movement in a landscape or terrain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    byt
    -0.16
     Lakes
    -0.15
    Wunused
    -0.15
    ymm
    -0.15
    Stretch
    -0.14
    /schema
    -0.14
     Maze
    -0.14
    otropic
    -0.14
    odal
    -0.14
    UIL
    -0.14
    POSITIVE LOGITS
     slope
    0.48
     hill
    0.44
     slopes
    0.41
     incl
    0.39
    slope
    0.38
     gradient
    0.35
     steep
    0.35
     slo
    0.35
    hill
    0.34
     Slo
    0.34
    Act Density 0.151%

    No Known Activations