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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate dependence or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.83
    JSONException
    -0.78
     enfance
    -0.73
    dyž
    -0.72
     quoque
    -0.71
    ője
    -0.68
     Sociales
    -0.66
     розта
    -0.65
     bienvenue
    -0.64
     eléctricas
    -0.64
    POSITIVE LOGITS
     without
    2.62
     Without
    2.59
    without
    2.52
    Without
    2.52
     WITHOUT
    2.32
    WITHOUT
    2.23
     ohne
    2.03
    Ohne
    2.00
     senza
    1.91
     zonder
    1.89
    Act Density 0.093%

    No Known Activations