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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal actions and accusations

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

    implying accusations or allegations

    np_acts-logits-general · gemini-2.0-flash

    accusations and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __*/
    -0.74
    
    -0.70
    makeConstraints
    -0.65
     protoimpl
    -0.63
    +#+#
    -0.61
    complexContent
    -0.59
    ønne
    -0.57
     épar
    -0.56
    butuhkan
    -0.56
     населення
    -0.56
    POSITIVE LOGITS
     allegedly
    0.97
     accidentally
    0.88
    alleg
    0.71
     inadvertently
    0.70
     confessed
    0.68
     alleged
    0.67
     وسلم
    0.62
     accused
    0.62
     reportedly
    0.61
     supuestamente
    0.60
    Act Density 0.561%

    No Known Activations