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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to time and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.64
     contextLoads
    -0.60
     Rojo
    -0.56
    Décès
    -0.54
     LTE
    -0.52
    RUnlock
    -0.52
     nær
    -0.52
    ()<
    -0.51
    Население
    -0.50
     ?";
    -0.50
    POSITIVE LOGITS
    ormais
    0.78
     henceforth
    0.74
     compter
    0.66
     onwards
    0.61
    <bos>
    0.61
    ANDUM
    0.60
     vanaf
    0.57
     hereafter
    0.55
     partir
    0.53
     désormais
    0.53
    Act Density 0.228%

    No Known Activations