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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and stories of personal experiences

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

    Text after periods

    np_acts-logits-general · gemini-2.0-flash

    he or she

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ourselves
    -0.72
    istoitu
    -0.69
    AddHtmlAttribute
    -0.64
    enames
    -0.64
     تضيفلها
    -0.63
    )]{
    -0.63
    ]){
    -0.63
    ampang
    -0.62
    )];
    -0.61
    Aktualisiert
    -0.60
    POSITIVE LOGITS
     he
    0.80
     she
    0.60
     his
    0.59
     mengaku
    0.57
     He
    0.57
    He
    0.57
    的他
    0.55
     niyang
    0.55
     hän
    0.54
    他不
    0.53
    Act Density 0.282%

    No Known Activations