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

    Neuronpedia

    INDEX
    Explanations

    descriptions of objects, particularly those conveying their physical characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intérieure
    -0.54
     écl
    -0.53
     magique
    -0.49
     buurt
    -0.49
    ándalo
    -0.49
    limate
    -0.48
     juſ
    -0.48
     civility
    -0.47
     assise
    -0.47
    levance
    -0.47
    POSITIVE LOGITS
     flat
    1.14
     rounded
    1.03
     narrow
    0.94
     flattened
    0.93
     broad
    0.93
     round
    0.92
     flatter
    0.91
     wide
    0.91
    flat
    0.89
     smooth
    0.86
    Act Density 0.469%

    No Known Activations