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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating completeness or fullness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aparcamiento
    -0.40
     Schick
    -0.39
     messaging
    -0.39
     debilidad
    -0.39
     Sme
    -0.38
     Mice
    -0.38
     Hag
    -0.36
     پد
    -0.36
    brainer
    -0.36
     coches
    -0.36
    POSITIVE LOGITS
     Full
    1.85
     full
    1.84
    Full
    1.83
     FULL
    1.63
    full
    1.58
    FULL
    1.53
    isFull
    1.27
     fuller
    1.23
    getFull
    1.16
     fullest
    1.11
    Act Density 0.086%

    No Known Activations