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

    Neuronpedia

    INDEX
    Explanations

    words that express certainty or frequency in a context

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

    the word "still" appearing in various contexts across different documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.55
    AsUp
    -0.49
    Према
    -0.42
    parsedMessage
    -0.41
    openConnection
    -0.41
     MenuView
    -0.41
     dokonce
    -0.41
     nemlig
    -0.40
     resourceCulture
    -0.40
     BaseActivity
    -0.40
    POSITIVE LOGITS
    følgelig
    0.67
     been
    0.57
    ेशा
    0.56
    satunya
    0.49
    ább
    0.47
    Sucesor
    0.47
    лтамалар
    0.46
    ً
    0.46
     going
    0.45
     be
    0.44
    Act Density 0.821%

    No Known Activations