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

    Neuronpedia

    INDEX
    Explanations

    relationships and connections between various elements and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -valu
    -0.16
    -urlencoded
    -0.15
    imity
    -0.15
     merk
    -0.15
    aley
    -0.14
    pmat
    -0.14
     BOTH
    -0.14
    以å¤ĸ
    -0.14
    Ñıз
    -0.14
    iversal
    -0.14
    POSITIVE LOGITS
     independent
    0.32
     separate
    0.29
     unrelated
    0.28
     individual
    0.28
     constituent
    0.26
    individual
    0.25
     component
    0.25
    çĭ¬ç«ĭ
    0.25
     distinct
    0.25
     seperate
    0.24
    Act Density 0.264%

    No Known Activations