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

    Neuronpedia

    INDEX
    Explanations

    terms related to relevance and appropriateness in various contexts

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

    preceding "administrative", "agencies", "industry", or "stream"

    np_acts-logits-general · gemini-2.0-flash

    relevant and appropriate qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portály
    -0.48
     <=",
    -0.41
    IntoConstraints
    -0.40
    Kariera
    -0.40
     ویکی‌آمباردا
    -0.37
    GenerationType
    -0.37
    ſtand
    -0.32
    straat
    -0.31
    }'.
    -0.31
     hipó
    -0.31
    POSITIVE LOGITS
    Appropriate
    1.02
     appropriate
    1.02
     Appropriate
    1.01
    appropriate
    0.88
     Relevant
    0.77
     appropriately
    0.77
     accordingly
    0.76
    Relevant
    0.76
     соответству
    0.75
     relevant
    0.75
    Act Density 0.353%

    No Known Activations