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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs in a document

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

    Follows quotation marks or "to"

    np_acts-logits-general · gemini-2.0-flash

    to + modal verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    odotus
    -0.67
    ViewType
    -0.58
    </h6>
    -0.57
     JSONException
    -0.54
     betweenstory
    -0.53
    ↵↵↵↵↵↵↵↵↵↵↵
    -0.53
     <<=
    -0.53
     van
    -0.52
     gel
    -0.52
     ơn
    -0.52
    POSITIVE LOGITS
    There
    1.03
    It
    0.96
    This
    0.94
    They
    0.94
    Even
    0.92
    While
    0.89
    If
    0.88
    When
    0.86
    Their
    0.85
    The
    0.85
    Act Density 0.083%

    No Known Activations