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

    Neuronpedia

    INDEX
    Explanations

    conjunctions that connect phrases or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ura
    -0.17
    arm
    -0.16
    uml
    -0.16
    arms
    -0.16
     xmin
    -0.15
    -metadata
    -0.14
    ound
    -0.14
    änn
    -0.14
    efd
    -0.14
    ViewInit
    -0.14
    POSITIVE LOGITS
    ocado
    0.16
    tain
    0.15
    ecome
    0.15
     Landing
    0.14
    åĭ
    0.14
    bjerg
    0.13
    ãĥ¡ãĥ³ãĥĪ
    0.13
    ãĥ´ãĤ£
    0.13
    ledo
    0.13
    Sphere
    0.13
    Act Density 0.321%

    No Known Activations