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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or indicators of causation and conditions surrounding events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The neuron detects the start-of-sequence / document position (it fires strongly on the <bos> token and other sequence-beginning positions).

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Negative Logits
    بوابة
    -0.60
    small
    -0.54
    -0.51
     small
    -0.49
    stable
    -0.47
    #+#
    -0.46
     रेटिंग
    -0.46
    Small
    -0.45
    inki
    -0.45
     bảng
    -0.45
    POSITIVE LOGITS
    +#+#
    0.90
    AndEndTag
    0.85
    DockStyle
    0.76
     volna
    0.73
     '\\;'
    0.73
    setVerticalGroup
    0.71
    WithIOException
    0.68
     démarche
    0.67
    webElementXpaths
    0.66
    rungsseite
    0.65
    Act Density 0.655%

    No Known Activations