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

    Neuronpedia

    INDEX
    Explanations

    phrases related to spatial relationships and separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tte
    -0.15
    ingham
    -0.14
    ãĥĸãĥ«
    -0.14
     Chew
    -0.14
     buckle
    -0.13
    levant
    -0.13
    że
    -0.13
    olis
    -0.13
    -worker
    -0.13
    583
    -0.13
    POSITIVE LOGITS
     distance
    0.28
    gap
    0.25
     intervening
    0.24
     spaces
    0.24
     space
    0.23
     gap
    0.23
    distance
    0.23
     distances
    0.23
     Gap
    0.23
     Distance
    0.23
    Act Density 0.118%

    No Known Activations