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

    Neuronpedia

    INDEX
    Explanations

    references to environmental impact and pollution reduction

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

    preceding adverbs or persuasive language

    np_acts-logits-general · gemini-2.0-flash

    describing actions or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BindingResult
    -0.57
     idéia
    -0.56
     biß
    -0.55
     EnglishChoose
    -0.53
    kezik
    -0.52
    Ecotoxicity
    -0.51
     nice
    -0.51
     :-)
    -0.50
    unkel
    -0.50
     Moslem
    -0.50
    POSITIVE LOGITS
     captivating
    0.77
     transformative
    0.71
     Notably
    0.70
    Embrace
    0.68
     consultato
    0.67
     cherished
    0.66
     meticulously
    0.65
    
    0.65
     ChatGPT
    0.64
    enderror
    0.64
    Act Density 0.020%

    No Known Activations