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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their relationships to others or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.65
    iqué
    -0.56
    UnusedPrivate
    -0.55
     two
    -0.55
    вую
    -0.54
     kív
    -0.53
     تضيفلها
    -0.53
    two
    -0.52
    hews
    -0.51
    uite
    -0.51
    POSITIVE LOGITS
     Nadie
    1.13
     Somebody
    1.11
    Somebody
    1.08
    Someone
    0.98
    Nadie
    0.97
     somebody
    0.97
     anybody
    0.96
     Someone
    0.95
     who
    0.95
    somebody
    0.95
    Act Density 0.380%

    No Known Activations