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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "au" and its variations, indicating a focus on time or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Giappone
    -0.58
     Romains
    -0.55
     piele
    -0.54
    áce
    -0.54
    complexContent
    -0.53
     Toujours
    -0.52
     francès
    -0.52
     Jerusalén
    -0.51
     للاسماء
    -0.51
     pilgrims
    -0.50
    POSITIVE LOGITS
     context
    0.75
     vicinity
    0.73
     surroundings
    0.72
     loob
    0.66
    addGap
    0.64
     moment
    0.61
     ProtoMessage
    0.60
     midst
    0.60
     confines
    0.59
     environs
    0.59
    Act Density 0.018%

    No Known Activations