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

    Neuronpedia

    INDEX
    Explanations

    numbers and fractions in sentence structures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    essa
    -0.80
    etsk
    -0.78
    iqueness
    -0.75
    hemy
    -0.74
    ament
    -0.73
    iane
    -0.73
    agne
    -0.72
    ique
    -0.71
    orph
    -0.69
    iewicz
    -0.68
    POSITIVE LOGITS
    ï¸ı
    1.05
    ¿
    0.95
    ·
    0.93
    ¹
    0.93
    ¸
    0.92
    ¼
    0.86
    ±
    0.85
    ¤
    0.85
    ¥
    0.85
    ¾
    0.85
    Act Density 0.020%

    No Known Activations