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

    Neuronpedia

    INDEX
    Explanations

    frequent use of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sense
    -0.16
    dej
    -0.15
    arris
    -0.15
    etto
    -0.15
    vie
    -0.15
    herent
    -0.14
    tein
    -0.14
     sense
    -0.14
    bers
    -0.14
    oen
    -0.14
    POSITIVE LOGITS
    orex
    0.20
    ediator
    0.17
     Frozen
    0.15
    缸åIJĮ
    0.15
     Nazi
    0.15
     Babe
    0.15
     kro
    0.15
    Frozen
    0.14
    TT
    0.14
    oci
    0.14
    Act Density 0.139%

    No Known Activations