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

    Neuronpedia

    INDEX
    Explanations

    technical identifiers and segment markers in structured text or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.65
     a
    -0.62
     you
    -0.61
     what
    -0.60
     
    -0.58
     word
    -0.57
     come
    -0.55
     the
    -0.55
     list
    -0.55
     one
    -0.53
    POSITIVE LOGITS
     propOrder
    0.95
    <bos>
    0.86
    تقاوى
    0.84
     poffe
    0.83
     '\\;'
    0.81
     Efq
    0.81
     Chriftian
    0.80
     deſt
    0.79
     NSCoder
    0.79
    WebVitals
    0.79
    Act Density 3.957%

    No Known Activations