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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a call to action or requests

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

    Follows punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    benefit and offerings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TAWA
    -0.60
    limsy
    -0.54
    Портал
    -0.53
     Wiktionnaire
    -0.52
    forKey
    -0.52
    wollen
    -0.51
    ='%
    -0.51
     chẳng
    -0.51
    adeloupe
    -0.50
    })_{
    -0.50
    POSITIVE LOGITS
     benefiting
    0.74
     Extern
    0.66
     benefit
    0.65
     benefits
    0.64
    Enjoying
    0.61
     Offered
    0.61
     beneficia
    0.60
     Intern
    0.59
    ThroughAttribute
    0.58
     enjoying
    0.57
    Act Density 0.059%

    No Known Activations