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

    Neuronpedia

    INDEX
    Explanations

    references to spatial relationships, particularly the term "across."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nery
    -0.73
    etic
    -0.70
    spot
    -0.67
    FORE
    -0.67
    rw
    -0.64
    nces
    -0.61
    Parents
    -0.61
    rics
    -0.60
    nce
    -0.58
    ns
    -0.58
    POSITIVE LOGITS
    roads
    0.82
    atform
    0.80
     rooft
    0.79
    side
    0.79
    country
    0.71
    hang
    0.71
     paths
    0.70
     continents
    0.69
     aisle
    0.68
     oceans
    0.67
    Act Density 0.020%

    No Known Activations