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

    Neuronpedia

    INDEX
    Explanations

    references to partnerships or dual entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stad
    -0.17
    ees
    -0.16
    icken
    -0.16
    åłĤ
    -0.15
    ken
    -0.15
    isk
    -0.14
    ettes
    -0.14
    eur
    -0.14
     hors
    -0.14
    adil
    -0.13
    POSITIVE LOGITS
    /all
    0.22
     sexes
    0.21
     kinds
    0.20
    ways
    0.16
    chsel
    0.15
    inde
    0.15
    -sided
    0.15
     sides
    0.15
    aver
    0.15
     вида
    0.15
    Act Density 0.055%

    No Known Activations