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

    Neuronpedia

    INDEX
    Explanations

    words that contain the letter 'e' or specific letter patterns, particularly focusing on their frequency and variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    に
    -0.83
    bbene
    -0.75
    y
    -0.71
    eeee
    -0.69
    eeeeeeee
    -0.67
    ly
    -0.66
    是
    -0.65
    ae
    -0.63
    e
    -0.62
    eeeee
    -0.61
    POSITIVE LOGITS
    🏾
    0.58
    principalTable
    0.57
    🏽
    0.55
    🏼
    0.54
    🏻
    0.54
    bootstrapcdn
    0.50
     consultato
    0.49
    🏿
    0.48
    Przypisy
    0.47
    تقاوى
    0.46
    Act Density 0.373%

    No Known Activations