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

    Neuronpedia

    INDEX
    Explanations

    references to causation or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     causes
    -1.19
    causes
    -1.05
     Causes
    -0.98
    Causes
    -0.95
     causas
    -0.63
     Ursachen
    -0.38
     triggers
    -0.38
    Causas
    -0.34
    causing
    -0.34
     provoque
    -0.33
    POSITIVE LOGITS
    0.75
    expandindo
    0.73
     חיצוניים
    0.71
    GEBURTSDATUM
    0.71
    AnchorStyles
    0.70
     kasarigan
    0.69
     مشين
    0.68
    ंदीखरीदारी
    0.67
     تضيفلها
    0.65
    rungsseite
    0.65
    Act Density 0.005%

    No Known Activations