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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing inclusivity and collective experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ationale
    -0.15
    inning
    -0.15
    onna
    -0.15
    vern
    -0.14
    491
    -0.14
    odore
    -0.14
    fol
    -0.13
     dif
    -0.13
     Saul
    -0.13
    apon
    -0.13
    POSITIVE LOGITS
    agem
    0.15
    enna
    0.14
    maal
    0.14
    ujet
    0.14
    инг
    0.14
    izard
    0.14
    CellValue
    0.14
    mand
    0.14
    sla
    0.14
    otton
    0.14
    Act Density 0.048%

    No Known Activations