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

    Neuronpedia

    INDEX
    Explanations

    spatial relationships and directional references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oise
    -0.18
    alim
    -0.17
    YSTEM
    -0.17
     Dud
    -0.16
    åģ
    -0.16
    شاÙĨ
    -0.15
     Bölüm
    -0.15
    abin
    -0.15
    '&&
    -0.14
    rox
    -0.14
    POSITIVE LOGITS
     sides
    0.25
     side
    0.23
     left
    0.21
    side
    0.19
    Side
    0.19
     right
    0.19
    åģ´
    0.19
    left
    0.18
    (side
    0.17
     direction
    0.17
    Act Density 0.086%

    No Known Activations