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

    Neuronpedia

    INDEX
    Explanations

    terms related to various types of lanterns

    oai_token-act-pair · gpt-3.5-turbo

    terms related to lantern festivals and variations of the word "tern."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ABV
    -0.63
     yield
    -0.62
     Normandy
    -0.62
     probability
    -0.61
     postp
    -0.60
     divor
    -0.60
     probabilities
    -0.58
     NX
    -0.58
    ---------------
    -0.57
     likelihood
    -0.56
    POSITIVE LOGITS
    atural
    1.29
    tern
    1.12
    atures
    1.11
    ationally
    1.04
    orrow
    1.04
    aturally
    1.04
    ingen
    1.00
    umbered
    1.00
    esc
    0.99
    obyl
    0.98
    Act Density 0.007%

    No Known Activations