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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate statistical averages or calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ald
    -0.17
     kop
    -0.15
     Hats
    -0.14
     Ri
    -0.14
     Javier
    -0.14
    ly
    -0.14
    ¢
    -0.14
    ÌĨ
    -0.14
    tras
    -0.14
     surf
    -0.14
    POSITIVE LOGITS
    onne
    0.16
    /archive
    0.16
    ecycle
    0.15
    edList
    0.15
    adera
    0.15
    Anywhere
    0.14
    ande
    0.14
    steder
    0.14
    .Ultra
    0.14
    arResult
    0.14
    Act Density 0.005%

    No Known Activations