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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and phrases indicating understanding or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arta
    -0.15
    unami
    -0.14
    GLOBALS
    -0.14
    elper
    -0.13
    ĶåĽŀ
    -0.13
    ceptar
    -0.13
    обов
    -0.13
    innacle
    -0.13
    uzzi
    -0.13
    enci
    -0.13
    POSITIVE LOGITS
     idea
    0.45
     Idea
    0.41
    idea
    0.37
     drift
    0.28
     gist
    0.25
     IDEA
    0.25
     ideas
    0.24
     Ideas
    0.23
     principle
    0.22
     drill
    0.22
    Act Density 0.055%

    No Known Activations