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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their context within sentences

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

    preceding punctuation

    np_acts-logits-general · gemini-2.0-flash

    describing service and atmosphere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.60
    ธ์
    -0.54
     resourceCulture
    -0.52
     références
    -0.52
     hóspedes
    -0.51
     henceforth
    -0.49
     getRule
    -0.49
     Vertrauen
    -0.49
     hereinafter
    -0.48
     recours
    -0.47
    POSITIVE LOGITS
     staff
    1.00
     friendly
    0.94
     Friendly
    0.94
     Staff
    0.90
    Friendly
    0.86
     nice
    0.82
    Staff
    0.80
     lots
    0.79
     personale
    0.78
     atmosphere
    0.78
    Act Density 0.033%

    No Known Activations