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

    Neuronpedia

    INDEX
    Explanations

    references to specific groups or categories of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utura
    -0.16
    portun
    -0.15
    ÌĤ
    -0.15
    ieg
    -0.14
    bis
    -0.14
    izzas
    -0.14
    ahat
    -0.14
    à¹Īà¹Ģà¸Ľ
    -0.14
     Laden
    -0.14
    issant
    -0.14
    POSITIVE LOGITS
     Anton
    0.16
     Wit
    0.15
    å·
    0.14
    ods
    0.14
    -flash
    0.14
    cil
    0.14
     наб
    0.14
    .jupiter
    0.13
     regs
    0.13
    tle
    0.13
    Act Density 0.071%

    No Known Activations