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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing directionality and location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     africaine
    -0.39
     africain
    -0.39
    بان
    -0.35
     объектов
    -0.35
     chines
    -0.34
     Mancha
    -0.34
     대해
    -0.34
     ailleurs
    -0.34
     ár
    -0.34
    ofern
    -0.34
    POSITIVE LOGITS
     RIGHT
    0.78
     Directly
    0.77
     right
    0.76
     directly
    0.74
    directly
    0.71
     Right
    0.71
    addGap
    0.69
     direttamente
    0.67
     непосредственно
    0.67
     Immediately
    0.66
    Act Density 0.255%

    No Known Activations