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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     corridors
    -0.19
    eways
    -0.16
    å»Ĭ
    -0.14
    æ°Ĺ
    -0.14
    fone
    -0.14
     Harbour
    -0.14
    habit
    -0.13
    :type
    -0.13
     Attr
    -0.13
     Establish
    -0.12
    POSITIVE LOGITS
     western
    0.33
     eastern
    0.30
     mouth
    0.30
     entrance
    0.29
     edge
    0.29
     northern
    0.29
    western
    0.28
     southern
    0.28
    nor
    0.25
     intersection
    0.25
    Act Density 0.221%

    No Known Activations