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

    Neuronpedia

    INDEX
    Explanations

    linguistic structures that suggest expectations or ideals related to progress and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    era
    -0.18
    inson
    -0.15
    elenium
    -0.15
    prov
    -0.14
    sert
    -0.14
    fur
    -0.14
    erve
    -0.14
    erece
    -0.14
     Tmin
    -0.14
    coop
    -0.14
    POSITIVE LOGITS
     Leer
    0.17
    æĩĤ
    0.15
     bil
    0.15
    ronym
    0.14
    -analytics
    0.14
     Gian
    0.13
    eyen
    0.13
    uggage
    0.13
    .pm
    0.13
     âĤ¹
    0.13
    Act Density 0.014%

    No Known Activations