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

    Neuronpedia

    INDEX
    Explanations

    positive interactions and communication effectiveness

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

    help and resolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.59
     autorytatywna
    -0.57
     चीज़ों
    -0.54
     مشين
    -0.49
    Personensuche
    -0.48
    Бахар
    -0.47
     Signalez
    -0.47
    Portale
    -0.47
    UrlResolution
    -0.46
     Мексичка
    -0.46
    POSITIVE LOGITS
     perfecta
    0.41
     calmed
    0.40
     perfect
    0.40
     asegurar
    0.39
     perfectly
    0.39
     parfaitement
    0.38
     responded
    0.37
     help
    0.37
     perfecto
    0.36
     did
    0.35
    Act Density 0.006%

    No Known Activations