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

    Neuronpedia

    INDEX
    Explanations

    references to telescopes and astronomical observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gall
    -0.17
    NX
    -0.16
     hâl
    -0.16
    reeze
    -0.15
    rell
    -0.15
    ĶåĽŀ
    -0.14
     Torch
    -0.14
     GW
    -0.14
    ibbon
    -0.14
     quad
    -0.14
    POSITIVE LOGITS
     обÑģ
    0.21
     Kitt
    0.21
     Observatory
    0.18
    plate
    0.18
    WISE
    0.18
     Hale
    0.17
     Observ
    0.17
     Catal
    0.17
     observ
    0.17
    observ
    0.16
    Act Density 0.016%

    No Known Activations