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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of enlightenment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    den
    -0.15
    .Atomic
    -0.15
    c
    -0.15
    cff
    -0.15
    asting
    -0.15
    cq
    -0.14
    éc
    -0.14
    panic
    -0.14
    dden
    -0.14
    gas
    -0.14
    POSITIVE LOGITS
    GLISH
    0.24
    .wikipedia
    0.23
    igma
    0.23
    abler
    0.20
    abling
    0.19
    vironments
    0.18
    ugu
    0.17
    sembles
    0.17
    sched
    0.17
    yclopedia
    0.17
    Act Density 0.026%

    No Known Activations