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

    Neuronpedia

    INDEX
    Explanations

    phrases that highlight contrasting ideas or opinions

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

    Follows conjunctions like "and" or "but"

    np_acts-logits-general · gemini-2.0-flash

    and but conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.76
     propOrder
    -0.75
    kháu
    -0.69
     estekak
    -0.62
     AssemblyTitle
    -0.61
     ModelExpression
    -0.61
    featureID
    -0.60
     Shakspeare
    -0.60
    DockStyle
    -0.58
    ValueStyle
    -0.58
    POSITIVE LOGITS
     quite
    0.89
     very
    0.81
    也是
    0.78
     worth
    0.75
     certainly
    0.74
     beneficial
    0.72
    quite
    0.71
     extremely
    0.70
     highly
    0.70
     worthy
    0.69
    Act Density 0.274%

    No Known Activations