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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to statistical analysis and data attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    кономі
    -0.69
    UrlResolution
    -0.67
    BufferException
    -0.66
    roek
    -0.66
    ocyan
    -0.66
    testens
    -0.64
    verständ
    -0.64
    rawDesc
    -0.62
    verständlich
    -0.62
    orianCalendar
    -0.62
    POSITIVE LOGITS
    -
    1.78
    ‑
    0.93
    ‐
    0.91
    expandindo
    0.86
    -...
    0.82
    _
    0.73
    –
    0.72
    ־
    0.66
    -|
    0.66
    -[
    0.65
    Act Density 0.804%

    No Known Activations