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

    Neuronpedia

    INDEX
    Explanations

    instances of passive voice and references to individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .flink
    -0.17
    Filled
    -0.17
    argon
    -0.15
    iedo
    -0.15
    licer
    -0.15
     ÙħÙĦÙĬ
    -0.14
    andest
    -0.14
    onders
    -0.14
    lassian
    -0.14
    ãĥ¼ãĥĨ
    -0.14
    POSITIVE LOGITS
     selected
    0.29
     allowed
    0.28
     admitted
    0.27
     chosen
    0.27
     given
    0.26
     brought
    0.25
     sent
    0.25
    selected
    0.24
    allowed
    0.23
     appointed
    0.22
    Act Density 0.444%

    No Known Activations