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

    Neuronpedia

    INDEX
    Explanations

    locations and directions related to places and landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ledge
    -0.17
    ir
    -0.14
    adir
    -0.14
    pon
    -0.14
    acer
    -0.14
     superf
    -0.13
    prise
    -0.13
    oint
    -0.13
    adding
    -0.13
    Vertical
    -0.13
    POSITIVE LOGITS
     near
    0.19
     nær
    0.16
     directly
    0.16
     behind
    0.15
     alongside
    0.15
     immediately
    0.15
    neau
    0.15
     près
    0.15
     next
    0.15
     yol
    0.14
    Act Density 0.095%

    No Known Activations