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

    Neuronpedia

    INDEX
    Explanations

    key actions or events that indicate progression or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    empo
    -0.16
     vd
    -0.15
    erli
    -0.14
    obus
    -0.14
    sled
    -0.14
    /*/
    -0.14
     Precision
    -0.13
    ÑĢÑĥÑĩ
    -0.13
    552
    -0.13
    estar
    -0.13
    POSITIVE LOGITS
    ida
    0.15
    ÛĮدا
    0.14
    /ns
    0.14
    RIPTION
    0.13
    zn
    0.13
     RK
    0.13
     Dunk
    0.13
    IDA
    0.13
    illing
    0.13
     learned
    0.12
    Act Density 0.470%

    No Known Activations