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

    Neuronpedia

    INDEX
    Explanations

    occurrences of discussions and panels

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

    panel discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    supplies
    -0.41
    styleType
    -0.40
    strings
    -0.40
     respira
    -0.40
    électricité
    -0.40
    sugar
    -0.38
    CountryCode
    -0.38
    removal
    -0.37
    Geografie
    -0.37
     Crockett
    -0.37
    POSITIVE LOGITS
     panelists
    0.69
     discussion
    0.64
    InSection
    0.61
     panel
    0.61
     discussions
    0.60
    featureID
    0.60
    +#+#
    0.57
     debate
    0.57
     discussão
    0.56
     opinião
    0.52
    Act Density 0.009%

    No Known Activations