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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating birth dates and birthplace information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acaktır
    -0.47
    feitura
    -0.42
    TableField
    -0.41
     automat
    -0.40
    sinki
    -0.40
     Thü
    -0.40
     mode
    -0.40
     novità
    -0.38
     autopilot
    -0.38
    Mode
    -0.38
    POSITIVE LOGITS
     birth
    0.93
     born
    0.91
     مواليد
    0.89
    ंदीखरीदारी
    0.86
    lahir
    0.83
    GEBURTSDATUM
    0.83
    birth
    0.79
     BIRTH
    0.78
     BORN
    0.77
     Birth
    0.76
    Act Density 0.183%

    No Known Activations