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

    Neuronpedia

    INDEX
    Explanations

    articles and possessive pronouns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okes
    -0.16
    ahir
    -0.15
    pers
    -0.15
    ikut
    -0.15
    agle
    -0.14
    pis
    -0.14
    etta
    -0.14
    477
    -0.14
    аза
    -0.14
    uto
    -0.14
    POSITIVE LOGITS
    //{{
    0.18
    ellido
    0.15
    iode
    0.15
    paque
    0.15
    DataExchange
    0.15
    forge
    0.15
    iddy
    0.15
    cratch
    0.14
     MERCHANTABILITY
    0.14
    antaged
    0.14
    Act Density 0.029%

    No Known Activations