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

    Neuronpedia

    INDEX
    Explanations

    directional instructions related to travel or navigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chn
    -0.17
     Independence
    -0.15
    asa
    -0.14
    æ¿
    -0.14
    podob
    -0.14
    تÙģ
    -0.14
    852
    -0.14
    orum
    -0.14
    789
    -0.14
    ovny
    -0.14
    POSITIVE LOGITS
     indicated
    0.16
     right
    0.16
     entrance
    0.15
    loha
    0.14
     left
    0.14
     marked
    0.14
    iez
    0.14
    енÑĤи
    0.13
    Ignore
    0.13
     signs
    0.13
    Act Density 0.042%

    No Known Activations