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

    Neuronpedia

    INDEX
    Explanations

    references to exile and situations involving fleeing or escaping

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

    fled to avoid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     credit
    -0.32
     even
    -0.31
     sobres
    -0.29
     drivers
    -0.29
     pio
    -0.29
     испыты
    -0.29
    rrggbb
    -0.29
     pi
    -0.29
     struggling
    -0.28
    icordia
    -0.28
    POSITIVE LOGITS
    featureID
    0.57
     surla
    0.56
     overseas
    0.55
    IVEREF
    0.55
     Мексичка
    0.55
     exiles
    0.54
    0.53
    Overseas
    0.52
     abroad
    0.52
     autorytatywna
    0.52
    Act Density 0.041%

    No Known Activations